The NLP Index

Updated: 07/21/21 - Total repos: 6,245
hits:
time: ms
Added Title Abstract Authors Paper Graph Code
7/21/2021 Measuring and Improving Model-Moderator Collaboration using Uncertainty Estimation
Content moderation is often performed by a collaboration between humans and machine learning models. However, it is not well understood how to design the collaborative process so as to maximize the combined moderator-model system performance. This work presents a rigorous study of this problem, focusing on an approach that incorporates model uncertainty into the collaborative process. First, we introduce principled metrics to describe the performance of the collaborative system under capacity constraints on the human moderator, quantifying how efficiently the combined system utilizes human decisions. Using these metrics, we conduct a large benchmark study evaluating the performance of state-of-the-art uncertainty models under different collaborative review strategies. We find that an uncertainty-based strategy consistently outperforms the widely used strategy based on toxicity scores, and moreover that the choice of review strategy drastically changes the overall system performance. Our results demonstrate the importance of rigorous metrics for understanding and developing effective moderator-model systems for content moderation, as well as the utility of uncertainty estimation in this domain.
Ian D. Kivlichan, Zi Lin, Jeremiah Liu, Lucy Vasserman
472
Python
7/21/2021 FewCLUE: A Chinese Few-shot Learning Evaluation Benchmark
Pretrained Language Models (PLMs) have achieved tremendous success in natural language understanding tasks. While different learning schemes -- fine-tuning, zero-shot and few-shot learning -- have been widely explored and compared for languages such as English, there is comparatively little work in Chinese to fairly and comprehensively evaluate and compare these methods. This work first introduces Chinese Few-shot Learning Evaluation Benchmark (FewCLUE), the first comprehensive small sample evaluation benchmark in Chinese. It includes nine tasks, ranging from single-sentence and sentence-pair classification tasks to machine reading comprehension tasks. Given the high variance of the few-shot learning performance, we provide multiple training/validation sets to facilitate a more accurate and stable evaluation of few-shot modeling. An unlabeled training set with up to 20,000 additional samples per task is provided, allowing researchers to explore better ways of using unlabeled samples. Next, we implement a set of state-of-the-art (SOTA) few-shot learning methods (including PET, ADAPET, LM-BFF, P-tuning and EFL), and compare their performance with fine-tuning and zero-shot learning schemes on the newly constructed FewCLUE benchmark.Our results show that: 1) all five few-shot learning methods exhibit better performance than fine-tuning or zero-shot learning; 2) among the five methods, PET is the best performing few-shot method; 3) few-shot learning performance is highly dependent on the specific task. Our benchmark and code are available at this https URL
Liang Xu, Xiaojing Lu, Chenyang Yuan, Xuanwei Zhang, Hu Yuan, Huilin Xu, Guoao Wei, Xiang Pan, Hai Hu
140
Python
7/21/2021 Learning Algebraic Recombination for Compositional Generalization
Neural sequence models exhibit limited compositional generalization ability in semantic parsing tasks. Compositional generalization requires algebraic recombination, i.e., dynamically recombining structured expressions in a recursive manner. However, most previous studies mainly concentrate on recombining lexical units, which is an important but not sufficient part of algebraic recombination. In this paper, we propose LeAR, an end-to-end neural model to learn algebraic recombination for compositional generalization. The key insight is to model the semantic parsing task as a homomorphism between a latent syntactic algebra and a semantic algebra, thus encouraging algebraic recombination. Specifically, we learn two modules jointly: a Composer for producing latent syntax, and an Interpreter for assigning semantic operations. Experiments on two realistic and comprehensive compositional generalization benchmarks demonstrate the effectiveness of our model. The source code is publicly available at this https URL.
Chenyao Liu, Shengnan An, Zeqi Lin, Qian Liu, Bei Chen, Jian-Guang Lou, Lijie Wen, Nanning Zheng, Dongmei Zhang
129
Python
7/21/2021 How Much Can CLIP Benefit Vision-and-Language Tasks?
Most existing Vision-and-Language (V&L) models rely on pre-trained visual encoders, using a relatively small set of manually-annotated data (as compared to web-crawled data), to perceive the visual world. However, it has been observed that large-scale pretraining usually can result in better generalization performance, e.g., CLIP (Contrastive Language-Image Pre-training), trained on a massive amount of image-caption pairs, has shown a strong zero-shot capability on various vision tasks. To further study the advantage brought by CLIP, we propose to use CLIP as the visual encoder in various V&L models in two typical scenarios: 1) plugging CLIP into task-specific fine-tuning; 2) combining CLIP with V&L pre-training and transferring to downstream tasks. We show that CLIP significantly outperforms widely-used visual encoders trained with in-domain annotated data, such as BottomUp-TopDown. We achieve competitive or better results on diverse V&L tasks, while establishing new state-of-the-art results on Visual Question Answering, Visual Entailment, and V&L Navigation tasks. We release our code at this https URL.
Sheng Shen, Liunian Harold Li, Hao Tan, Mohit Bansal, Anna Rohrbach, Kai-Wei Chang, Zhewei Yao, Kurt Keutzer
90
Python
7/21/2021 Deduplicating Training Data Makes Language Models Better
We find that existing language modeling datasets contain many near-duplicate examples and long repetitive substrings. As a result, over 1% of the unprompted output of language models trained on these datasets is copied verbatim from the training data. We develop two tools that allow us to deduplicate training datasets -- for example removing from C4 a single 61 word English sentence that is repeated over 60,000 times. Deduplication allows us to train models that emit memorized text ten times less frequently and require fewer train steps to achieve the same or better accuracy. We can also reduce train-test overlap, which affects over 4% of the validation set of standard datasets, thus allowing for more accurate evaluation. We release code for reproducing our work and performing dataset deduplication at this https URL.
Katherine Lee, Daphne Ippolito, Andrew Nystrom, Chiyuan Zhang, Douglas Eck, Chris Callison-Burch, Nicholas Carlini
83
Rust
7/21/2021 DaCy: A Unified Framework for Danish NLP
Danish natural language processing (NLP) has in recent years obtained considerable improvements with the addition of multiple new datasets and models. However, at present, there is no coherent framework for applying state-of-the-art models for Danish. We present DaCy: a unified framework for Danish NLP built on SpaCy. DaCy uses efficient multitask models which obtain state-of-the-art performance on named entity recognition, part-of-speech tagging, and dependency parsing. DaCy contains tools for easy integration of existing models such as for polarity, emotion, or subjectivity detection. In addition, we conduct a series of tests for biases and robustness of Danish NLP pipelines through augmentation of the test set of DaNE. DaCy large compares favorably and is especially robust to long input lengths and spelling variations and errors. All models except DaCy large display significant biases related to ethnicity while only Polyglot shows a significant gender bias. We argue that for languages with limited benchmark sets, data augmentation can be particularly useful for obtaining more realistic and fine-grained performance estimates. We provide a series of augmenters as a first step towards a more thorough evaluation of language models for low and medium resource languages and encourage further development.
Kenneth Enevoldsen, Lasse Hansen, Kristoffer Nielbo
33
Jupyter Notebook
7/21/2021 Spanish Language Models
This paper presents the Spanish RoBERTa-base and RoBERTa-large models, as well as the corresponding performance evaluations. Both models were pre-trained using the largest Spanish corpus known to date, with a total of 570GB of clean and deduplicated text processed for this work, compiled from the web crawlings performed by the National Library of Spain from 2009 to 2019.
Asier Gutierrez-Fandino, Jordi Armengol-Estape, Marc Pamies, Joan Llop-Palao, Joaquin Silveira-Ocampo, Casimiro Pio Carrino, Aitor Gonzalez-Agirre, Carme Armentano-Oller, Carlos Rodriguez-Penagos, Marta Villegas
26
Python
7/21/2021 UniRE: A Unified Label Space for Entity Relation Extraction
Many joint entity relation extraction models setup two separated label spaces for the two sub-tasks (i.e., entity detection and relation classification). We argue that this setting may hinder the information interaction between entities and relations. In this work, we propose to eliminate the different treatment on the two sub-tasks' label spaces. The input of our model is a table containing all word pairs from a sentence. Entities and relations are represented by squares and rectangles in the table. We apply a unified classifier to predict each cell's label, which unifies the learning of two sub-tasks. For testing, an effective (yet fast) approximate decoder is proposed for finding squares and rectangles from tables. Experiments on three benchmarks (ACE04, ACE05, SciERC) show that, using only half the number of parameters, our model achieves competitive accuracy with the best extractor, and is faster.
Yijun Wang, Changzhi Sun, Yuanbin Wu, Hao Zhou, Lei Li, Junchi Yan
25
Python
7/21/2021 MultiBench: Multiscale Benchmarks for Multimodal Representation Learning
Learning multimodal representations involves integrating information from multiple heterogeneous sources of data. It is a challenging yet crucial area with numerous real-world applications in multimedia, affective computing, robotics, finance, human-computer interaction, and healthcare. Unfortunately, multimodal research has seen limited resources to study (1) generalization across domains and modalities, (2) complexity during training and inference, and (3) robustness to noisy and missing modalities. In order to accelerate progress towards understudied modalities and tasks while ensuring real-world robustness, we release MultiBench, a systematic and unified large-scale benchmark spanning 15 datasets, 10 modalities, 20 prediction tasks, and 6 research areas. MultiBench provides an automated end-to-end machine learning pipeline that simplifies and standardizes data loading, experimental setup, and model evaluation. To enable holistic evaluation, MultiBench offers a comprehensive methodology to assess (1) generalization, (2) time and space complexity, and (3) modality robustness. MultiBench introduces impactful challenges for future research, including scalability to large-scale multimodal datasets and robustness to realistic imperfections. To accompany this benchmark, we also provide a standardized implementation of 20 core approaches in multimodal learning. Simply applying methods proposed in different research areas can improve the state-of-the-art performance on 9/15 datasets. Therefore, MultiBench presents a milestone in unifying disjoint efforts in multimodal research and paves the way towards a better understanding of the capabilities and limitations of multimodal models, all the while ensuring ease of use, accessibility, and reproducibility. MultiBench, our standardized code, and leaderboards are publicly available, will be regularly updated, and welcomes inputs from the community.
Paul Pu Liang, Yiwei Lyu, Xiang Fan, Zetian Wu, Yun Cheng, Jason Wu, Leslie Chen, Peter Wu, Michelle A. Lee, Yuke Zhu, Ruslan Salakhutdinov, Louis-Philippe Morency
24
Python
7/21/2021 CLSRIL-23: Cross Lingual Speech Representations for Indic Languages
We present a CLSRIL-23, a self supervised learning based audio pre-trained model which learns cross lingual speech representations from raw audio across 23 Indic languages. It is built on top of wav2vec 2.0 which is solved by training a contrastive task over masked latent speech representations and jointly learns the quantization of latents shared across all languages. We compare the language wise loss during pretraining to compare effects of monolingual and multilingual pretraining. Performance on some downstream fine-tuning tasks for speech recognition is also compared and our experiments show that multilingual pretraining outperforms monolingual training, in terms of learning speech representations which encodes phonetic similarity of languages and also in terms of performance on down stream tasks. A decrease of 5% is observed in WER and 9.5% in CER when a multilingual pretrained model is used for finetuning in Hindi. All the code models are also open sourced. CLSRIL-23 is a model trained on $23$ languages and almost 10,000 hours of audio data to facilitate research in speech recognition for Indic languages. We hope that new state of the art systems will be created using the self supervised approach, especially for low resources Indic languages.
Anirudh Gupta, Harveen Singh Chadha, Priyanshi Shah, Neeraj Chimmwal, Ankur Dhuriya, Rishabh Gaur, Vivek Raghavan
18
Python
7/21/2021 Benchmarking for Biomedical Natural Language Processing Tasks with a Domain Specific ALBERT
The availability of biomedical text data and advances in natural language processing (NLP) have made new applications in biomedical NLP possible. Language models trained or fine tuned using domain specific corpora can outperform general models, but work to date in biomedical NLP has been limited in terms of corpora and tasks. We present BioALBERT, a domain-specific adaptation of A Lite Bidirectional Encoder Representations from Transformers (ALBERT), trained on biomedical (PubMed and PubMed Central) and clinical (MIMIC-III) corpora and fine tuned for 6 different tasks across 20 benchmark datasets. Experiments show that BioALBERT outperforms the state of the art on named entity recognition (+11.09% BLURB score improvement), relation extraction (+0.80% BLURB score), sentence similarity (+1.05% BLURB score), document classification (+0.62% F1-score), and question answering (+2.83% BLURB score). It represents a new state of the art in 17 out of 20 benchmark datasets. By making BioALBERT models and data available, our aim is to help the biomedical NLP community avoid computational costs of training and establish a new set of baselines for future efforts across a broad range of biomedical NLP tasks.
Usman Naseem, Adam G. Dunn, Matloob Khushi, Jinman Kim
6
7/21/2021 Between Flexibility and Consistency: Joint Generation of Captions and Subtitles
Speech translation (ST) has lately received growing interest for the generation of subtitles without the need for an intermediate source language transcription and timing (i.e. captions). However, the joint generation of source captions and target subtitles does not only bring potential output quality advantages when the two decoding processes inform each other, but it is also often required in multilingual scenarios. In this work, we focus on ST models which generate consistent captions-subtitles in terms of structure and lexical content. We further introduce new metrics for evaluating subtitling consistency. Our findings show that joint decoding leads to increased performance and consistency between the generated captions and subtitles while still allowing for sufficient flexibility to produce subtitles conforming to language-specific needs and norms.
Alina Karakanta, Marco Gaido, Matteo Negri, Marco Turchi
4
Python
7/21/2021 FLEX: Unifying Evaluation for Few-Shot NLP
Few-shot NLP research is highly active, yet conducted in disjoint research threads with evaluation suites that lack challenging-yet-realistic testing setups and fail to employ careful experimental design. Consequently, the community does not know which techniques perform best or even if they outperform simple baselines. We formulate desiderata for an ideal few-shot NLP benchmark and present FLEX, the first benchmark, public leaderboard, and framework that provides unified, comprehensive measurement for few-shot NLP techniques. FLEX incorporates and introduces new best practices for few-shot evaluation, including measurement of four transfer settings, textual labels for zero-shot evaluation, and a principled approach to benchmark design that optimizes statistical accuracy while keeping evaluation costs accessible to researchers without large compute resources. In addition, we present UniFew, a simple yet strong prompt-based model for few-shot learning which unifies the pretraining and finetuning prompt formats, eschewing complex machinery of recent prompt-based approaches in adapting downstream task formats to language model pretraining objectives. We demonstrate that despite simplicity UniFew achieves results competitive with both popular meta-learning and prompt-based approaches.
Jonathan Bragg, Arman Cohan, Kyle Lo, Iz Beltagy
3
Python
7/21/2021 Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills
Models pre-trained with a language modeling objective possess ample world knowledge and language skills, but are known to struggle in tasks that require reasoning. In this work, we propose to leverage semi-structured tables, and automatically generate at scale question-paragraph pairs, where answering the question requires reasoning over multiple facts in the paragraph. We add a pre-training step over this synthetic data, which includes examples that require 16 different reasoning skills such as number comparison, conjunction, and fact composition. To improve data efficiency, we propose sampling strategies that focus training on reasoning skills the model is currently lacking. We evaluate our approach on three reading comprehension datasets that are focused on reasoning, and show that our model, PReasM, substantially outperforms T5, a popular pre-trained encoder-decoder model. Moreover, sampling examples based on current model errors leads to faster training and higher overall performance.
Ori Yoran, Alon Talmor, Jonathan Berant
2
7/21/2021 Transition-based Bubble Parsing: Improvements on Coordination Structure Prediction
We propose a transition-based bubble parser to perform coordination structure identification and dependency-based syntactic analysis simultaneously. Bubble representations were proposed in the formal linguistics literature decades ago; they enhance dependency trees by encoding coordination boundaries and internal relationships within coordination structures explicitly. In this paper, we introduce a transition system and neural models for parsing these bubble-enhanced structures. Experimental results on the English Penn Treebank and the English GENIA corpus show that our parsers beat previous state-of-the-art approaches on the task of coordination structure prediction, especially for the subset of sentences with complex coordination structures.
Tianze Shi, Lillian Lee
2
7/21/2021 Solving ESL Sentence Completion Questions via Pre-trained Neural Language Models
Sentence completion (SC) questions present a sentence with one or more blanks that need to be filled in, three to five possible words or phrases as options. SC questions are widely used for students learning English as a Second Language (ESL) and building computational approaches to automatically solve such questions is beneficial to language learners. In this work, we propose a neural framework to solve SC questions in English examinations by utilizing pre-trained language models. We conduct extensive experiments on a real-world K-12 ESL SC question dataset and the results demonstrate the superiority of our model in terms of prediction accuracy. Furthermore, we run precision-recall trade-off analysis to discuss the practical issues when deploying it in real-life scenarios. To encourage reproducible results, we make our code publicly available at \url{this https URL}.
Qiongqiong Liu, Tianqiao Liu, Jiafu Zhao, Qiang Fang, Wenbiao Ding, Zhongqin Wu, Feng Xia, Jiliang Tang, Zitao Liu
1
Python
7/21/2021 Multi-Task Learning based Online Dialogic Instruction Detection with Pre-trained Language Models
In this work, we study computational approaches to detect online dialogic instructions, which are widely used to help students understand learning materials, and build effective study habits. This task is rather challenging due to the widely-varying quality and pedagogical styles of dialogic instructions. To address these challenges, we utilize pre-trained language models, and propose a multi-task paradigm which enhances the ability to distinguish instances of different classes by enlarging the margin between categories via contrastive loss. Furthermore, we design a strategy to fully exploit the misclassified examples during the training stage. Extensive experiments on a real-world online educational data set demonstrate that our approach achieves superior performance compared to representative baselines. To encourage reproducible results, we make our implementation online available at \url{this https URL}.
Yang Hao, Hang Li, Wenbiao Ding, Zhongqin Wu, Jiliang Tang, Rose Luckin, Zitao Liu
1
Python
7/21/2021 ZR-2021VG: Zero-Resource Speech Challenge, Visually-Grounded Language Modelling track, 2021 edition
We present the visually-grounded language modelling track that was introduced in the Zero-Resource Speech challenge, 2021 edition, 2nd round. We motivate the new track and discuss participation rules in detail. We also present the two baseline systems that were developed for this track.
Afra Alishahia, áGrzegorz Chrupala, Alejandrina Cristia,áEmmanuel Dupoux,áBertrand Higy,áMarvin Lavechin,áOkko Rasanen,áChen Yu
-
1
Python
7/21/2021 CatVRNN: Generating Category Texts via Multi-task Learning
Controlling the model to generate texts of different categories is a challenging task that is getting more and more attention. Recently, generative adversarial net (GAN) has shown promising results in category text generation. However, the texts generated by GANs usually suffer from the problems of mode collapse and training instability. To avoid the above problems, we propose a novel model named category-aware variational recurrent neural network (CatVRNN), which is inspired by multi-task learning. In our model, generation and classification are trained simultaneously, aiming at generating texts of different categories. Moreover, the use of multi-task learning can improve the quality of generated texts, when the classification task is appropriate. And we propose a function to initialize the hidden state of CatVRNN to force model to generate texts of a specific category. Experimental results on three datasets demonstrate that our model can do better than several state-of-the-art text generation methods based GAN in the category accuracy and quality of generated texts.
Pengsen Cheng, Jiayong Liu, Jinqiao Dai
1
Python
7/21/2021 Levi Graph AMR Parser using Heterogeneous Attention
Coupled with biaffine decoders, transformers have been effectively adapted to text-to-graph transduction and achieved state-of-the-art performance on AMR parsing. Many prior works, however, rely on the biaffine decoder for either or both arc and label predictions although most features used by the decoder may be learned by the transformer already. This paper presents a novel approach to AMR parsing by combining heterogeneous data (tokens, concepts, labels) as one input to a transformer to learn attention, and use only attention matrices from the transformer to predict all elements in AMR graphs (concepts, arcs, labels). Although our models use significantly fewer parameters than the previous state-of-the-art graph parser, they show similar or better accuracy on AMR 2.0 and 3.0.
Han He, Jinho D. Choi
1
Python
7/21/2021 Legal Judgment Prediction with Multi-Stage CaseRepresentation Learning in the Real Court Setting
Legal judgment prediction(LJP) is an essential task for legal AI. While prior methods studied on this topic in a pseudo setting by employing the judge-summarized case narrative as the input to predict the judgment, neglecting critical case life-cycle information in real court setting could threaten the case logic representation quality and prediction correctness. In this paper, we introduce a novel challenging dataset from real courtrooms to predict the legal judgment in a reasonably encyclopedic manner by leveraging the genuine input of the case -- plaintiff's claims and court debate data, from which the case's facts are automatically recognized by comprehensively understanding the multi-role dialogues of the court debate, and then learnt to discriminate the claims so as to reach the final judgment through multi-task learning. An extensive set of experiments with a large civil trial data set shows that the proposed model can more accurately characterize the interactions among claims, fact and debate for legal judgment prediction, achieving significant improvements over strong state-of-the-art baselines. Moreover, the user study conducted with real judges and law school students shows the neural predictions can also be interpretable and easily observed, and thus enhancing the trial efficiency and judgment quality.
Luyao Ma, Yating Zhang, Tianyi Wang, Xiaozhong Liu, Wei Ye, Changlong Sun, Shikun Zhang
1
Python
7/21/2021 On the Difficulty of Translating Free-Order Case-Marking Languages
Identifying factors that make certain languages harder to model than others is essential to reach language equality in future Natural Language Processing technologies. Free-order case-marking languages, such as Russian, Latin or Tamil, have proved more challenging than fixed-order languages for the tasks of syntactic parsing and subject-verb agreement prediction. In this work, we investigate whether this class of languages is also more difficult to translate by state-of-the-art Neural Machine Translation models (NMT). Using a variety of synthetic languages and a newly introduced translation challenge set, we find that word order flexibility in the source language only leads to a very small loss of NMT quality, even though the core verb arguments become impossible to disambiguate in sentences without semantic cues. The latter issue is indeed solved by the addition of case marking. However, in medium- and low-resource settings, the overall NMT quality of fixed-order languages remains unmatched.
Arianna Bisazza, Ahmet Üstün, Stephan Sportel
0
Roff
7/21/2021 Can Deep Neural Networks Predict Data Correlations from Column Names?
For humans, it is often possible to predict data correlations from column names. We conduct experiments to find out whether deep neural networks can learn to do the same. If so, e.g., it would open up the possibility of tuning tools that use NLP analysis on schema elements to prioritize their efforts for correlation detection. We analyze correlations for around 120,000 column pairs, taken from around 4,000 data sets. We try to predict correlations, based on column names alone. For predictions, we exploit pre-trained language models, based on the recently proposed Transformer architecture. We consider different types of correlations, multiple prediction methods, and various prediction scenarios. We study the impact of factors such as column name length or the amount of training data on prediction accuracy. Altogether, we find that deep neural networks can predict correlations with a relatively high accuracy in many scenarios (e.g., with an accuracy of 95% for long column names).
Immanuel Trummer
0
Jupyter Notebook
7/21/2021 Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoning
Neural machine translation systems are known to be vulnerable to adversarial test inputs, however, as we show in this paper, these systems are also vulnerable to training attacks. Specifically, we propose a poisoning attack in which a malicious adversary inserts a small poisoned sample of monolingual text into the training set of a system trained using back-translation. This sample is designed to induce a specific, targeted translation behaviour, such as peddling misinformation. We present two methods for crafting poisoned examples, and show that only a tiny handful of instances, amounting to only 0.02% of the training set, is sufficient to enact a successful attack. We outline a defence method against said attacks, which partly ameliorates the problem. However, we stress that this is a blind-spot in modern NMT, demanding immediate attention.
Jun Wang, Chang Xu, Francisco Guzman, Ahmed El-Kishky, Yuqing Tang, Benjamin I. P. Rubinstein, Trevor Cohn
0
7/21/2021 Linking Health News to Research Literature
Accurately linking news articles to scientific research works is a critical component in a number of applications, such as measuring the social impact of a research work and detecting inaccuracies or distortions in science news. Although the lack of links between news and literature has been a challenge in these applications, it is a relatively unexplored research problem. In this paper we designed and evaluated a new approach that consists of (1) augmenting latest named-entity recognition techniques to extract various metadata, and (2) designing a new elastic search engine that can facilitate the use of enriched metadata queries. To evaluate our approach, we constructed two datasets of paired news articles and research papers: one is used for training models to extract metadata, and the other for evaluation. Our experiments showed that the new approach performed significantly better than a baseline approach used by this http URL (0.89 vs 0.32 in terms of top-1 accuracy). To further demonstrate the effectiveness of the approach, we also conducted a study on 37,600 health-related press releases published on EurekAlert!, which showed that our approach was able to identify the corresponding research papers with a top-1 accuracy of at least 0.97.
Jun Wang, Bei Yu
0
7/21/2021 Quantifying Explainability in NLP and Analyzing Algorithms for Performance-Explainability Tradeoff
The healthcare domain is one of the most exciting application areas for machine learning, but a lack of model transparency contributes to a lag in adoption within the industry. In this work, we explore the current art of explainability and interpretability within a case study in clinical text classification, using a task of mortality prediction within MIMIC-III clinical notes. We demonstrate various visualization techniques for fully interpretable methods as well as model-agnostic post hoc attributions, and we provide a generalized method for evaluating the quality of explanations using infidelity and local Lipschitz across model types from logistic regression to BERT variants. With these metrics, we introduce a framework through which practitioners and researchers can assess the frontier between a model's predictive performance and the quality of its available explanations. We make our code available to encourage continued refinement of these methods.
Mitchell Naylor, Christi French, Samantha Terker, Uday Kamath
0
Jupyter Notebook
7/21/2021 Enforcing Consistency in Weakly Supervised Semantic Parsing
The predominant challenge in weakly supervised semantic parsing is that of spurious programs that evaluate to correct answers for the wrong reasons. Prior work uses elaborate search strategies to mitigate the prevalence of spurious programs; however, they typically consider only one input at a time. In this work we explore the use of consistency between the output programs for related inputs to reduce the impact of spurious programs. We bias the program search (and thus the model's training signal) towards programs that map the same phrase in related inputs to the same sub-parts in their respective programs. Additionally, we study the importance of designing logical formalisms that facilitate this kind of consAistency-based training. We find that a more consistent formalism leads to improved model performance even without consistency-based training. When combined together, these two insights lead to a 10% absolute improvement over the best prior result on the Natural Language Visual Reasoning dataset.
Nitish Gupta, Sameer Singh, Matt Gardner
0
Python
7/21/2021 Fuzzy-Rough Nearest Neighbour Approaches for Emotion Detection in Tweets
Social media are an essential source of meaningful data that can be used in different tasks such as sentiment analysis and emotion recognition. Mostly, these tasks are solved with deep learning methods. Due to the fuzzy nature of textual data, we consider using classification methods based on fuzzy rough sets. Specifically, we develop an approach for the SemEval-2018 emotion detection task, based on the fuzzy rough nearest neighbour (FRNN) classifier enhanced with ordered weighted average (OWA) operators. We use tuned ensembles of FRNN--OWA models based on different text embedding methods. Our results are competitive with the best SemEval solutions based on more complicated deep learning methods.
Olha Kaminska, Chris Cornelis, Veronique Hoste
0
Jupyter Notebook
7/21/2021 Nearest neighbour approaches for Emotion Detection in Tweets
Emotion detection is an important task that can be applied to social media data to discover new knowledge. While the use of deep learning methods for this task has been prevalent, they are black-box models, making their decisions hard to interpret for a human operator. Therefore, in this paper, we propose an approach using weighted $k$ Nearest Neighbours (kNN), a simple, easy to implement, and explainable machine learning model. These qualities can help to enhance results' reliability and guide error analysis. In particular, we apply the weighted kNN model to the shared emotion detection task in tweets from SemEval-2018. Tweets are represented using different text embedding methods and emotion lexicon vocabulary scores, and classification is done by an ensemble of weighted kNN models. Our best approaches obtain results competitive with state-of-the-art solutions and open up a promising alternative path to neural network methods.
Olha Kaminska, Chris Cornelis, Veronique Hoste
0
7/21/2021 Using BERT Encoding to Tackle the Mad-lib Attack in SMS Spam Detection
One of the stratagems used to deceive spam filters is to substitute vocables with synonyms or similar words that turn the message unrecognisable by the detection algorithms. In this paper we investigate whether the recent development of language models sensitive to the semantics and context of words, such as Google's BERT, may be useful to overcome this adversarial attack (called "Mad-lib" as per the word substitution game). Using a dataset of 5572 SMS spam messages, we first established a baseline of detection performance using widely known document representation models (BoW and TFIDF) and the novel BERT model, coupled with a variety of classification algorithms (Decision Tree, kNN, SVM, Logistic Regression, Naive Bayes, Multilayer Perceptron). Then, we built a thesaurus of the vocabulary contained in these messages, and set up a Mad-lib attack experiment in which we modified each message of a held out subset of data (not used in the baseline experiment) with different rates of substitution of original words with synonyms from the thesaurus. Lastly, we evaluated the detection performance of the three representation models (BoW, TFIDF and BERT) coupled with the best classifier from the baseline experiment (SVM). We found that the classic models achieved a 94% Balanced Accuracy (BA) in the original dataset, whereas the BERT model obtained 96%. On the other hand, the Mad-lib attack experiment showed that BERT encodings manage to maintain a similar BA performance of 96% with an average substitution rate of 1.82 words per message, and 95% with 3.34 words substituted per message. In contrast, the BA performance of the BoW and TFIDF encoders dropped to chance. These results hint at the potential advantage of BERT models to combat these type of ingenious attacks, offsetting to some extent for the inappropriate use of semantic relationships in language.
Sergio Rojas-Galeano
0
Jupyter Notebook
7/21/2021 What do writing features tell us about AI papers?
As the numbers of submissions to conferences grow quickly, the task of assessing the quality of academic papers automatically, convincingly, and with high accuracy attracts increasing attention. We argue that studying interpretable dimensions of these submissions could lead to scalable solutions. We extract a collection of writing features, and construct a suite of prediction tasks to assess the usefulness of these features in predicting citation counts and the publication of AI-related papers. Depending on the venues, the writing features can predict the conference vs. workshop appearance with F1 scores up to 60-90, sometimes even outperforming the content-based tf-idf features and RoBERTa. We show that the features describe writing style more than content. To further understand the results, we estimate the causal impact of the most indicative features. Our analysis on writing features provides a perspective to assessing and refining the writing of academic articles at scale.
Zining Zhu, Bai Li, Yang Xu, Frank Rudzicz
0
Jupyter Notebook
7/21/2021 Robust Learning for Text Classification with Multi-source Noise Simulation and Hard Example Mining
Many real-world applications involve the use of Optical Character Recognition (OCR) engines to transform handwritten images into transcripts on which downstream Natural Language Processing (NLP) models are applied. In this process, OCR engines may introduce errors and inputs to downstream NLP models become noisy. Despite that pre-trained models achieve state-of-the-art performance in many NLP benchmarks, we prove that they are not robust to noisy texts generated by real OCR engines. This greatly limits the application of NLP models in real-world scenarios. In order to improve model performance on noisy OCR transcripts, it is natural to train the NLP model on labelled noisy texts. However, in most cases there are only labelled clean texts. Since there is no handwritten pictures corresponding to the text, it is impossible to directly use the recognition model to obtain noisy labelled data. Human resources can be employed to copy texts and take pictures, but it is extremely expensive considering the size of data for model training. Consequently, we are interested in making NLP models intrinsically robust to OCR errors in a low resource manner. We propose a novel robust training framework which 1) employs simple but effective methods to directly simulate natural OCR noises from clean texts and 2) iteratively mines the hard examples from a large number of simulated samples for optimal performance. 3) To make our model learn noise-invariant representations, a stability loss is employed. Experiments on three real-world datasets show that the proposed framework boosts the robustness of pre-trained models by a large margin. We believe that this work can greatly promote the application of NLP models in actual scenarios, although the algorithm we use is simple and straightforward. We make our codes and three datasets publicly available\footnote{this https URL}.
Guowei Xu, Wenbiao Ding, Weiping Fu, Zhongqin Wu, Zitao Liu
0
Python
7/21/2021 ParCourE: A Parallel Corpus Explorer for a Massively Multilingual Corpus
With more than 7000 languages worldwide, multilingual natural language processing (NLP) is essential both from an academic and commercial perspective. Researching typological properties of languages is fundamental for progress in multilingual NLP. Examples include assessing language similarity for effective transfer learning, injecting inductive biases into machine learning models or creating resources such as dictionaries and inflection tables. We provide ParCourE, an online tool that allows to browse a word-aligned parallel corpus, covering 1334 languages. We give evidence that this is useful for typological research. ParCourE can be set up for any parallel corpus and can thus be used for typological research on other corpora as well as for exploring their quality and properties.
Ayyoob Imani, Masoud Jalili Sabet, Philipp Dufter, Michael Cysouw, Hinrich Sch├╝tze
7/14/2021 Advancing CTC-CRF Based End-to-End Speech Recognition with Wordpieces and Conformers
Automatic speech recognition systems have been largely improved in the past few decades and current systems are mainly hybrid-based and end-to-end-based. The recently proposed CTC-CRF framework inherits the data-efficiency of the hybrid approach and the simplicity of the end-to-end approach. In this paper, we further advance CTC-CRF based ASR technique with explorations on modeling units and neural architectures. Specifically, we investigate techniques to enable the recently developed wordpiece modeling units and Conformer neural networks to be succesfully applied in CTC-CRFs. Experiments are conducted on two English datasets (Switchboard, Librispeech) and a German dataset from CommonVoice. Experimental results suggest that (i) Conformer can improve the recognition performance significantly; (ii) Wordpiece-based systems perform slightly worse compared with phone-based systems for the target language with a low degree of grapheme-phoneme correspondence (e.g. English), while the two systems can perform equally strong when such degree of correspondence is high for the target language (e.g. German).
Huahuan Zheng, Wenjie Peng, Zhijian Ou, Jinsong Zhang
166
Cuda
7/14/2021 DRIFT: A Toolkit for Diachronic Analysis of Scientific Literature
In this work, we present to the NLP community, and to the wider research community as a whole, an application for the diachronic analysis of research corpora. We open source an easy-to-use tool coined: DRIFT, which allows researchers to track research trends and development over the years. The analysis methods are collated from well-cited research works, with a few of our own methods added for good measure. Succinctly put, some of the analysis methods are: keyword extraction, word clouds, predicting declining/stagnant/growing trends using Productivity, tracking bi-grams using Acceleration plots, finding the Semantic Drift of words, tracking trends using similarity, etc. To demonstrate the utility and efficacy of our tool, we perform a case study on the cs.CL corpus of the arXiv repository and draw inferences from the analysis methods. The toolkit and the associated code are available here: this https URL.
Abheesht Sharma, Gunjan Chhablani, Harshit Pandey, Rajaswa Patil
82
Python
7/14/2021 VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer
Since visual perception can give rich information beyond text descriptions for world understanding, there has been increasing interest in leveraging visual grounding for language learning. Recently, vokenization has attracted attention by using the predictions of a text-to-image retrieval model as labels for language model supervision. Despite its success, the method suffers from approximation error of using finite image labels and the lack of vocabulary diversity of a small image-text dataset. To overcome these limitations, we present VidLanKD, a video-language knowledge distillation method for improving language understanding. We train a multi-modal teacher model on a video-text dataset, and then transfer its knowledge to a student language model with a text dataset. To avoid approximation error, we propose to use different knowledge distillation objectives. In addition, the use of a large-scale video-text dataset helps learn diverse and richer vocabularies. In our experiments, VidLanKD achieves consistent improvements over text-only language models and vokenization models, on several downstream language understanding tasks including GLUE, SQuAD, and SWAG. We also demonstrate the improved world knowledge, physical reasoning, and temporal reasoning capabilities of our model by evaluating on the GLUE-diagnostics, PIQA, and TRACIE datasets. Lastly, we present comprehensive ablation studies as well as visualizations of the learned text-to-video grounding results of our teacher and student language models. Our code and models are available at: this https URL
Zineng Tang, Jaemin Cho, Hao Tan, Mohit Bansal
32
Python
7/14/2021 Learned Token Pruning for Transformers
A major challenge in deploying transformer models is their prohibitive inference cost, which quadratically scales with the input sequence length. This makes it especially difficult to use transformers for processing long sequences. To address this, we present a novel Learned Token Pruning (LTP) method that reduces redundant tokens as the data passes through the different layers of the transformer. In particular, LTP prunes tokens with an attention score below a threshold value, which is learned during training. Importantly, our threshold based method avoids algorithmically expensive operations such as top-k token selection which are used in prior token pruning methods, and also leads to structured pruning. We extensively test the performance of our approach on multiple GLUE tasks and show that our learned threshold based method consistently outperforms the prior state-of-the-art top-k token based method by up to ~2% higher accuracy with the same amount of FLOPs. Furthermore, our preliminary results show up to 1.4x and 1.9x throughput improvement on Tesla T4 GPU and Intel Haswell CPU, respectively, with less than 1% of accuracy drop (and up to 2.1x FLOPs reduction). Our code has been developed in PyTorch and has been open-sourced.
Sehoon Kim, Sheng Shen, David Thorsley, Amir Gholami, Joseph Hassoun, Kurt Keutzer
21
Python
7/14/2021 R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling
Human language understanding operates at multiple levels of granularity (e.g., words, phrases, and sentences) with increasing levels of abstraction that can be hierarchically combined. However, existing deep models with stacked layers do not explicitly model any sort of hierarchical process. This paper proposes a recursive Transformer model based on differentiable CKY style binary trees to emulate the composition process. We extend the bidirectional language model pre-training objective to this architecture, attempting to predict each word given its left and right abstraction nodes. To scale up our approach, we also introduce an efficient pruned tree induction algorithm to enable encoding in just a linear number of composition steps. Experimental results on language modeling and unsupervised parsing show the effectiveness of our approach.
Xiang Hu, Haitao Mi, Zujie Wen, Yafang Wang, Yi Su, Jing Zheng, Gerard de Melo
12
Python
7/14/2021 Lemmatization of Historical Old Literary Finnish Texts in Modern Orthography
Texts written in Old Literary Finnish represent the first literary work ever written in Finnish starting from the 16th century. There have been several projects in Finland that have digitized old publications and made them available for research use. However, using modern NLP methods in such data poses great challenges. In this paper we propose an approach for simultaneously normalizing and lemmatizing Old Literary Finnish into modern spelling. Our best model reaches to 96.3\% accuracy in texts written by Agricola and 87.7\% accuracy in other contemporary out-of-domain text. Our method has been made freely available on Zenodo and Github.
Mika Hamalainen, Niko Partanen, Khalid Alnajjar
9
Python
7/14/2021 Deep Extrapolation for Attribute-Enhanced Generation
Attribute extrapolation in sample generation is challenging for deep neural networks operating beyond the training distribution. We formulate a new task for extrapolation in sequence generation, focusing on natural language and proteins, and propose GENhance, a generative framework that enhances attributes through a learned latent space. Trained on movie reviews and a computed protein stability dataset, GENhance can generate strongly-positive text reviews and highly stable protein sequences without being exposed to similar data during training. We release our benchmark tasks and models to contribute to the study of generative modeling extrapolation and data-driven design in biology and chemistry.
Alvin Chan, Ali Madani, Ben Krause, Nikhil Naik
11
Jupyter Notebook
7/14/2021 Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering
Active learning promises to alleviate the massive data needs of supervised machine learning: it has successfully improved sample efficiency by an order of magnitude on traditional tasks like topic classification and object recognition. However, we uncover a striking contrast to this promise: across 5 models and 4 datasets on the task of visual question answering, a wide variety of active learning approaches fail to outperform random selection. To understand this discrepancy, we profile 8 active learning methods on a per-example basis, and identify the problem as collective outliers -- groups of examples that active learning methods prefer to acquire but models fail to learn (e.g., questions that ask about text in images or require external knowledge). Through systematic ablation experiments and qualitative visualizations, we verify that collective outliers are a general phenomenon responsible for degrading pool-based active learning. Notably, we show that active learning sample efficiency increases significantly as the number of collective outliers in the active learning pool decreases. We conclude with a discussion and prescriptive recommendations for mitigating the effects of these outliers in future work.
Siddharth Karamcheti, Ranjay Krishna, Li Fei-Fei, Christopher D. Manning
9
Python
7/14/2021 CasEE: A Joint Learning Framework with Cascade Decoding for Overlapping Event Extraction
Event extraction (EE) is a crucial information extraction task that aims to extract event information in texts. Most existing methods assume that events appear in sentences without overlaps, which are not applicable to the complicated overlapping event extraction. This work systematically studies the realistic event overlapping problem, where a word may serve as triggers with several types or arguments with different roles. To tackle the above problem, we propose a novel joint learning framework with cascade decoding for overlapping event extraction, termed as CasEE. Particularly, CasEE sequentially performs type detection, trigger extraction and argument extraction, where the overlapped targets are extracted separately conditioned on the specific former prediction. All the subtasks are jointly learned in a framework to capture dependencies among the subtasks. The evaluation on a public event extraction benchmark FewFC demonstrates that CasEE achieves significant improvements on overlapping event extraction over previous competitive methods.
Jiawei Sheng, Shu Guo, Bowen Yu, Qian Li, Yiming Hei, Lihong Wang, Tingwen Liu, Hongbo Xu
6
7/14/2021 Keep it Simple: Unsupervised Simplification of Multi-Paragraph Text
This work presents Keep it Simple (KiS), a new approach to unsupervised text simplification which learns to balance a reward across three properties: fluency, salience and simplicity. We train the model with a novel algorithm to optimize the reward (k-SCST), in which the model proposes several candidate simplifications, computes each candidate's reward, and encourages candidates that outperform the mean reward. Finally, we propose a realistic text comprehension task as an evaluation method for text simplification. When tested on the English news domain, the KiS model outperforms strong supervised baselines by more than 4 SARI points, and can help people complete a comprehension task an average of 18% faster while retaining accuracy, when compared to the original text. Code available: this https URL
Philippe Laban, Tobias Schnabel, Paul Bennett, Marti A. Hearst
5
Python
7/14/2021 Inspiration through Observation: Demonstrating the Influence of Automatically Generated Text on Creative Writing
Getting machines to generate text perceived as creative is a long-pursued goal. A growing body of research directs this goal towards augmenting the creative writing abilities of human authors. In this paper, we pursue this objective by analyzing how observing examples of automatically generated text influences writing. In particular, we examine a task referred to as sentence infilling, which involves transforming a list of words into a complete sentence. We emphasize "storiability" as a desirable feature of the resulting sentences, where "storiable" sentences are those that suggest a story a reader would be curious to hear about. Both humans and an automated system (based on a neural language model) performed this sentence infilling task. In one setting, people wrote sentences on their own; in a different setting, people observed the sentences produced by the model while writing their own sentences. Readers then assigned storiability preferences to the resulting sentences in a subsequent evaluation. We find that human-authored sentences were judged as more storiable when authors observed the generated examples, and that storiability increased as authors derived more semantic content from the examples. This result gives evidence of an "inspiration through observation" paradigm for human-computer collaborative writing, through which human writing can be enhanced by text generation models without directly copying their output.
Melissa Roemmele
2
Jupyter Notebook
7/14/2021 Can Transformer Models Measure Coherence In Text? Re-Thinking the Shuffle Test
The Shuffle Test is the most common task to evaluate whether NLP models can measure coherence in text. Most recent work uses direct supervision on the task; we show that by simply finetuning a RoBERTa model, we can achieve a near perfect accuracy of 97.8%, a state-of-the-art. We argue that this outstanding performance is unlikely to lead to a good model of text coherence, and suggest that the Shuffle Test should be approached in a Zero-Shot setting: models should be evaluated without being trained on the task itself. We evaluate common models in this setting, such as Generative and Bi-directional Transformers, and find that larger architectures achieve high-performance out-of-the-box. Finally, we suggest the k-Block Shuffle Test, a modification of the original by increasing the size of blocks shuffled. Even though human reader performance remains high (around 95% accuracy), model performance drops from 94% to 78% as block size increases, creating a conceptually simple challenge to benchmark NLP models. Code available: this https URL
Philippe Laban, Luke Dai, Lucas Bandarkar, Marti A. Hearst
2
Python
7/14/2021 Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherence
Topic model evaluation, like evaluation of other unsupervised methods, can be contentious. However, the field has coalesced around automated estimates of topic coherence, which rely on the frequency of word co-occurrences in a reference corpus. Recent models relying on neural components surpass classical topic models according to these metrics. At the same time, unlike classical models, the practice of neural topic model evaluation suffers from a validation gap: automatic coherence for neural models has not been validated using human experimentation. In addition, as we show via a meta-analysis of topic modeling literature, there is a substantial standardization gap in the use of automated topic modeling benchmarks. We address both the standardization gap and the validation gap. Using two of the most widely used topic model evaluation datasets, we assess a dominant classical model and two state-of-the-art neural models in a systematic, clearly documented, reproducible way. We use automatic coherence along with the two most widely accepted human judgment tasks, namely, topic rating and word intrusion. Automated evaluation will declare one model significantly different from another when corresponding human evaluations do not, calling into question the validity of fully automatic evaluations independent of human judgments.
Alexander Hoyle, Pranav Goel, Denis Peskov, Andrew Hian-Cheong, Jordan Boyd-Graber, Philip Resnik
1
Jupyter Notebook
7/14/2021 Probabilistic Graph Reasoning for Natural Proof Generation
In this paper, we investigate the problem of reasoning over natural language statements. Prior neural based approaches do not explicitly consider the inter-dependency among answers and their proofs. In this paper, we propose PRobr, a novel approach for joint answer prediction and proof generation. PRobr defines a joint probabilistic distribution over all possible proof graphs and answers via an induced graphical model. We then optimize the model using variational approximation on top of neural textual representation. Experiments on multiple datasets under diverse settings (fully supervised, few-shot and zero-shot evaluation) verify the effectiveness of PRobr, e.g., achieving 10%-30% improvement on QA accuracy in few/zero-shot evaluation. Our codes and models can be found at this https URL.
Changzhi Sun, Xinbo Zhang, Jiangjie Chen, Chun Gan, Yuanbin Wu, Jiaze Chen, Hao Zhou, Lei Li
1
Python
7/14/2021 The DCU-EPFL Enhanced Dependency Parser at the IWPT 2021 Shared Task
We describe the DCU-EPFL submission to the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies. The task involves parsing Enhanced UD graphs, which are an extension of the basic dependency trees designed to be more facilitative towards representing semantic structure. Evaluation is carried out on 29 treebanks in 17 languages and participants are required to parse the data from each language starting from raw strings. Our approach uses the Stanza pipeline to preprocess the text files, XLMRoBERTa to obtain contextualized token representations, and an edge-scoring and labeling model to predict the enhanced graph. Finally, we run a post-processing script to ensure all of our outputs are valid Enhanced UD graphs. Our system places 6th out of 9 participants with a coarse Enhanced Labeled Attachment Score (ELAS) of 83.57. We carry out additional post-deadline experiments which include using Trankit for pre-processing, XLM-RoBERTa-LARGE, treebank concatenation, and multitask learning between a basic and an enhanced dependency parser. All of these modifications improve our initial score and our final system has a coarse ELAS of 88.04.
James Barry, Alireza Mohammadshahi, Joachim Wagner, Jennifer Foster, James Henderson
1
Python
7/14/2021 Injecting Knowledge Base Information into End-to-End Joint Entity and Relation Extraction and Coreference Resolution
We consider a joint information extraction (IE) model, solving named entity recognition, coreference resolution and relation extraction jointly over the whole document. In particular, we study how to inject information from a knowledge base (KB) in such IE model, based on unsupervised entity linking. The used KB entity representations are learned from either (i) hyperlinked text documents (Wikipedia), or (ii) a knowledge graph (Wikidata), and appear complementary in raising IE performance. Representations of corresponding entity linking (EL) candidates are added to text span representations of the input document, and we experiment with (i) taking a weighted average of the EL candidate representations based on their prior (in Wikipedia), and (ii) using an attention scheme over the EL candidate list. Results demonstrate an increase of up to 5% F1-score for the evaluated IE tasks on two datasets. Despite a strong performance of the prior-based model, our quantitative and qualitative analysis reveals the advantage of using the attention-based approach.
Severine Verlinden, Klim Zaporojets, Johannes Deleu, Thomas Demeester, Chris Develder
1
Python
7/14/2021 He Thinks He Knows Better than the Doctors: BERT for Event Factuality Fails on Pragmatics
We investigate how well BERT performs on predicting factuality in several existing English datasets, encompassing various linguistic constructions. Although BERT obtains a strong performance on most datasets, it does so by exploiting common surface patterns that correlate with certain factuality labels, and it fails on instances where pragmatic reasoning is necessary. Contrary to what the high performance suggests, we are still far from having a robust system for factuality prediction.
Nanjiang Jiang, Marie-Catherine de Marneffe
1
Python
7/14/2021 Time-Aware Ancient Chinese Text Translation and Inference
In this paper, we aim to address the challenges surrounding the translation of ancient Chinese text: (1) The linguistic gap due to the difference in eras results in translations that are poor in quality, and (2) most translations are missing the contextual information that is often very crucial to understanding the text. To this end, we improve upon past translation techniques by proposing the following: We reframe the task as a multi-label prediction task where the model predicts both the translation and its particular era. We observe that this helps to bridge the linguistic gap as chronological context is also used as auxiliary information. % As a natural step of generalization, we pivot on the modern Chinese translations to generate multilingual outputs. %We show experimentally the efficacy of our framework in producing quality translation outputs and also validate our framework on a collected task-specific parallel corpus. We validate our framework on a parallel corpus annotated with chronology information and show experimentally its efficacy in producing quality translation outputs. We release both the code and the data this https URL for future research.
Ernie Chang, Yow-Ting Shiue, Hui-Syuan Yeh, Vera Demberg
1
7/14/2021 What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition
Dialog acts can be interpreted as the atomic units of a conversation, more fine-grained than utterances, characterized by a specific communicative function. The ability to structure a conversational transcript as a sequence of dialog acts -- dialog act recognition, including the segmentation -- is critical for understanding dialog. We apply two pre-trained transformer models, XLNet and Longformer, to this task in English and achieve strong results on Switchboard Dialog Act and Meeting Recorder Dialog Act corpora with dialog act segmentation error rates (DSER) of 8.4% and 14.2%. To understand the key factors affecting dialog act recognition, we perform a comparative analysis of models trained under different conditions. We find that the inclusion of a broader conversational context helps disambiguate many dialog act classes, especially those infrequent in the training data. The presence of punctuation in the transcripts has a massive effect on the models' performance, and a detailed analysis reveals specific segmentation patterns observed in its absence. Finally, we find that the label set specificity does not affect dialog act segmentation performance. These findings have significant practical implications for spoken language understanding applications that depend heavily on a good-quality segmentation being available.
Piotr ?elasko, Raghavendra Pappagari, Najim Dehak
1
Python
7/14/2021 Question Answering over Knowledge Graphs with Neural Machine Translation and Entity Linking
The goal of Question Answering over Knowledge Graphs (KGQA) is to find answers for natural language questions over a knowledge graph. Recent KGQA approaches adopt a neural machine translation (NMT) approach, where the natural language question is translated into a structured query language. However, NMT suffers from the out-of-vocabulary problem, where terms in a question may not have been seen during training, impeding their translation. This issue is particularly problematic for the millions of entities that large knowledge graphs describe. We rather propose a KGQA approach that delegates the processing of entities to entity linking (EL) systems. NMT is then used to create a query template with placeholders that are filled by entities identified in an EL phase. Slot filling is used to decide which entity fills which placeholder. Experiments for QA over Wikidata show that our approach outperforms pure NMT: while there remains a strong dependence on having seen similar query templates during training, errors relating to entities are greatly reduced.
Daniel Diomedi, Aidan Hogan
1
Python
7/14/2021 DUKweb: Diachronic word representations from the UK Web Archive corpus
Lexical semantic change (detecting shifts in the meaning and usage of words) is an important task for social and cultural studies as well as for Natural Language Processing applications. Diachronic word embeddings (time-sensitive vector representations of words that preserve their meaning) have become the standard resource for this task. However, given the significant computational resources needed for their generation, very few resources exist that make diachronic word embeddings available to the scientific community. In this paper we present DUKweb, a set of large-scale resources designed for the diachronic analysis of contemporary English. DUKweb was created from the JISC UK Web Domain Dataset (1996-2013), a very large archive which collects resources from the Internet Archive that were hosted on domains ending in `.uk'. DUKweb consists of a series word co-occurrence matrices and two types of word embeddings for each year in the JISC UK Web Domain dataset. We show the reuse potential of DUKweb and its quality standards via a case study on word meaning change detection.
Adam Tsakalidis, Pierpaolo Basile, Marya Bazzi, Mihai Cucuringu, Barbara McGillivray
0
Python
7/14/2021 Normalizing Flow based Hidden Markov Models for Classification of Speech Phones with Explainability
In pursuit of explainability, we develop generative models for sequential data. The proposed models provide state-of-the-art classification results and robust performance for speech phone classification. We combine modern neural networks (normalizing flows) and traditional generative models (hidden Markov models - HMMs). Normalizing flow-based mixture models (NMMs) are used to model the conditional probability distribution given the hidden state in the HMMs. Model parameters are learned through judicious combinations of time-tested Bayesian learning methods and contemporary neural network learning methods. We mainly combine expectation-maximization (EM) and mini-batch gradient descent. The proposed generative models can compute likelihood of a data and hence directly suitable for maximum-likelihood (ML) classification approach. Due to structural flexibility of HMMs, we can use different normalizing flow models. This leads to different types of HMMs providing diversity in data modeling capacity. The diversity provides an opportunity for easy decision fusion from different models. For a standard speech phone classification setup involving 39 phones (classes) and the TIMIT dataset, we show that the use of standard features called mel-frequency-cepstral-coeffcients (MFCCs), the proposed generative models, and the decision fusion together can achieve $86.6\%$ accuracy by generative training only. This result is close to state-of-the-art results, for examples, $86.2\%$ accuracy of PyTorch-Kaldi toolkit [1], and $85.1\%$ accuracy using light gated recurrent units [2]. We do not use any discriminative learning approach and related sophisticated features in this article.
Anubhab Ghosh, Antoine Honore, Dong Liu, Gustav Eje Henter, Saikat Chatterjee
0
Python
7/14/2021 Power Law Graph Transformer for Machine Translation and Representation Learning
We present the Power Law Graph Transformer, a transformer model with well defined deductive and inductive tasks for prediction and representation learning. The deductive task learns the dataset level (global) and instance level (local) graph structures in terms of learnable power law distribution parameters. The inductive task outputs the prediction probabilities using the deductive task output, similar to a transductive model. We trained our model with Turkish-English and Portuguese-English datasets from TED talk transcripts for machine translation and compared the model performance and characteristics to a transformer model with scaled dot product attention trained on the same experimental setup. We report BLEU scores of $17.79$ and $28.33$ on the Turkish-English and Portuguese-English translation tasks with our model, respectively. We also show how a duality between a quantization set and N-dimensional manifold representation can be leveraged to transform between local and global deductive-inductive outputs using successive application of linear and non-linear transformations end-to-end.
Burc Gokden
1
Python
7/14/2021 Persian-WSD-Corpus: A Sense Annotated Corpus for Persian All-words Word Sense Disambiguation
Word Sense Disambiguation (WSD) is a long-standing task in Natural Language Processing(NLP) that aims to automatically identify the most relevant meaning of the words in a given context. Developing standard WSD test collections can be mentioned as an important prerequisite for developing and evaluating different WSD systems in the language of interest. Although many WSD test collections have been developed for a variety of languages, no standard All-words WSD benchmark is available for Persian. In this paper, we address this shortage for the Persian language by introducing SBU-WSD-Corpus, as the first standard test set for the Persian All-words WSD task. SBU-WSD-Corpus is manually annotated with senses from the Persian WordNet (FarsNet) sense inventory. To this end, three annotators used SAMP (a tool for sense annotation based on FarsNet lexical graph) to perform the annotation task. SBU-WSD-Corpus consists of 19 Persian documents in different domains such as Sports, Science, Arts, etc. It includes 5892 content words of Persian running text and 3371 manually sense annotated words (2073 nouns, 566 verbs, 610 adjectives, and 122 adverbs). Providing baselines for future studies on the Persian All-words WSD task, we evaluate several WSD models on SBU-WSD-Corpus. The corpus is publicly available at this https URL.
Hossein Rouhizadeh, Mehrnoush Shamsfard, Vahideh Tajalli, Masoud Rouhziadeh
0
7/14/2021 Misinformation Detection on YouTube Using Video Captions
Millions of people use platforms such as YouTube, Facebook, Twitter, and other mass media. Due to the accessibility of these platforms, they are often used to establish a narrative, conduct propaganda, and disseminate misinformation. This work proposes an approach that uses state-of-the-art NLP techniques to extract features from video captions (subtitles). To evaluate our approach, we utilize a publicly accessible and labeled dataset for classifying videos as misinformation or not. The motivation behind exploring video captions stems from our analysis of videos metadata. Attributes such as the number of views, likes, dislikes, and comments are ineffective as videos are hard to differentiate using this information. Using caption dataset, the proposed models can classify videos among three classes (Misinformation, Debunking Misinformation, and Neutral) with 0.85 to 0.90 F1-score. To emphasize the relevance of the misinformation class, we re-formulate our classification problem as a two-class classification - Misinformation vs. others (Debunking Misinformation and Neutral). In our experiments, the proposed models can classify videos with 0.92 to 0.95 F1-score and 0.78 to 0.90 AUC ROC.
Raj Jagtap, Abhinav Kumar, Rahul Goel, Shakshi Sharma, Rajesh Sharma, Clint P. George
0
Python
7/14/2021 Weakly Supervised Named Entity Tagging with Learnable Logical Rules
We study the problem of building entity tagging systems by using a few rules as weak supervision. Previous methods mostly focus on disambiguation entity types based on contexts and expert-provided rules, while assuming entity spans are given. In this work, we propose a novel method TALLOR that bootstraps high-quality logical rules to train a neural tagger in a fully automated manner. Specifically, we introduce compound rules that are composed from simple rules to increase the precision of boundary detection and generate more diverse pseudo labels. We further design a dynamic label selection strategy to ensure pseudo label quality and therefore avoid overfitting the neural tagger. Experiments on three datasets demonstrate that our method outperforms other weakly supervised methods and even rivals a state-of-the-art distantly supervised tagger with a lexicon of over 2,000 terms when starting from only 20 simple rules. Our method can serve as a tool for rapidly building taggers in emerging domains and tasks. Case studies show that learned rules can potentially explain the predicted entities.
Jiacheng Li, Haibo Ding, Jingbo Shang, Julian McAuley, Zhe Feng
0
Python
7/14/2021 An Investigation of the (In)effectiveness of Counterfactually Augmented Data
While pretrained language models achieve excellent performance on natural language understanding benchmarks, they tend to rely on spurious correlations and generalize poorly to out-of-distribution (OOD) data. Recent work has explored using counterfactually-augmented data (CAD) -- data generated by minimally perturbing examples to flip the ground-truth label -- to identify robust features that are invariant under distribution shift. However, empirical results using CAD for OOD generalization have been mixed. To explain this discrepancy, we draw insights from a linear Gaussian model and demonstrate the pitfalls of CAD. Specifically, we show that (a) while CAD is effective at identifying robust features, it may prevent the model from learning unperturbed robust features, and (b) CAD may exacerbate existing spurious correlations in the data. Our results show that the lack of perturbation diversity in current CAD datasets limits its effectiveness on OOD generalization, calling for innovative crowdsourcing procedures to elicit diverse perturbation of examples.
Nitish Joshi, He He
0
7/14/2021 MedGPT: Medical Concept Prediction from Clinical Narratives
The data available in Electronic Health Records (EHRs) provides the opportunity to transform care, and the best way to provide better care for one patient is through learning from the data available on all other patients. Temporal modelling of a patient's medical history, which takes into account the sequence of past events, can be used to predict future events such as a diagnosis of a new disorder or complication of a previous or existing disorder. While most prediction approaches use mostly the structured data in EHRs or a subset of single-domain predictions and outcomes, we present MedGPT a novel transformer-based pipeline that uses Named Entity Recognition and Linking tools (i.e. MedCAT) to structure and organize the free text portion of EHRs and anticipate a range of future medical events (initially disorders). Since a large portion of EHR data is in text form, such an approach benefits from a granular and detailed view of a patient while introducing modest additional noise. MedGPT effectively deals with the noise and the added granularity, and achieves a precision of 0.344, 0.552 and 0.640 (vs LSTM 0.329, 0.538 and 0.633) when predicting the top 1, 3 and 5 candidate future disorders on real world hospital data from King's College Hospital, London, UK (\textasciitilde600k patients). We also show that our model captures medical knowledge by testing it on an experimental medical multiple choice question answering task, and by examining the attentional focus of the model using gradient-based saliency methods.
Zeljko Kraljevic, Anthony Shek, Daniel Bean, Rebecca Bendayan, James Teo, Richard Dobson
0
Python
7/14/2021 Packing: Towards 2x NLP BERT Acceleration
We find that at sequence length 512 padding tokens represent in excess of 50% of the Wikipedia dataset used for pretraining BERT (Bidirectional Encoder Representations from Transformers). Therefore by removing all padding we achieve a 2x speed-up in terms of sequences/sec. To exploit this characteristic of the dataset, we develop and contrast two deterministic packing algorithms. Both algorithms rely on the assumption that sequences are interchangeable and therefore packing can be performed on the histogram of sequence lengths, rather than per sample. This transformation of the problem leads to algorithms which are fast and have linear complexity in dataset size. The shortest-pack-first histogram-packing (SPFHP) algorithm determines the packing order for the Wikipedia dataset of over 16M sequences in 0.02 seconds. The non-negative least-squares histogram-packing (NNLSHP) algorithm converges in 28.4 seconds but produces solutions which are more depth efficient, managing to get near optimal packing by combining a maximum of 3 sequences in one sample. Using the dataset with multiple sequences per sample requires additional masking in the attention layer and a modification of the MLM loss function. We demonstrate that both of these changes are straightforward to implement and have relatively little impact on the achievable performance gain on modern hardware. Finally, we pretrain BERT-Large using the packed dataset, demonstrating no loss of convergence and the desired 2x speed-up.
Matej Kosec, Sheng Fu, Mario Michael Krell
n/a
7/7/2021 ESPnet-ST IWSLT 2021 Offline Speech Translation System
This paper describes the ESPnet-ST group's IWSLT 2021 submission in the offline speech translation track. This year we made various efforts on training data, architecture, and audio segmentation. On the data side, we investigated sequence-level knowledge distillation (SeqKD) for end-to-end (E2E) speech translation. Specifically, we used multi-referenced SeqKD from multiple teachers trained on different amounts of bitext. On the architecture side, we adopted the Conformer encoder and the Multi-Decoder architecture, which equips dedicated decoders for speech recognition and translation tasks in a unified encoder-decoder model and enables search in both source and target language spaces during inference. We also significantly improved audio segmentation by using the pyannote.audio toolkit and merging multiple short segments for long context modeling. Experimental evaluations showed that each of them contributed to large improvements in translation performance. Our best E2E system combined all the above techniques with model ensembling and achieved 31.4 BLEU on the 2-ref of tst2021 and 21.2 BLEU and 19.3 BLEU on the two single references of tst2021.
Hirofumi Inaguma, Brian Yan, Siddharth Dalmia, Pengcheng Gu, Jiatong Shi, Kevin Duh, Shinji Watanabe
3950
Python
7/7/2021 XLM-E: Cross-lingual Language Model Pre-training via ELECTRA
In this paper, we introduce ELECTRA-style tasks to cross-lingual language model pre-training. Specifically, we present two pre-training tasks, namely multilingual replaced token detection, and translation replaced token detection. Besides, we pretrain the model, named as XLM-E, on both multilingual and parallel corpora. Our model outperforms the baseline models on various cross-lingual understanding tasks with much less computation cost. Moreover, analysis shows that XLM-E tends to obtain better cross-lingual transferability.
Zewen Chi, Shaohan Huang, Li Dong, Shuming Ma, Saksham Singhal, Payal Bajaj, Xia Song, Furu Wei
2328
Python
7/7/2021 A Survey on Neural Speech Synthesis
Text to speech (TTS), or speech synthesis, which aims to synthesize intelligible and natural speech given text, is a hot research topic in speech, language, and machine learning communities and has broad applications in the industry. As the development of deep learning and artificial intelligence, neural network-based TTS has significantly improved the quality of synthesized speech in recent years. In this paper, we conduct a comprehensive survey on neural TTS, aiming to provide a good understanding of current research and future trends. We focus on the key components in neural TTS, including text analysis, acoustic models and vocoders, and several advanced topics, including fast TTS, low-resource TTS, robust TTS, expressive TTS, and adaptive TTS, etc. We further summarize resources related to TTS (e.g., datasets, opensource implementations) and discuss future research directions. This survey can serve both academic researchers and industry practitioners working on TTS.
Xu Tan, Tao Qin, Frank Soong, Tie-Yan Liu
114
7/7/2021 XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages
Contemporary works on abstractive text summarization have focused primarily on high-resource languages like English, mostly due to the limited availability of datasets for low/mid-resource ones. In this work, we present XL-Sum, a comprehensive and diverse dataset comprising 1 million professionally annotated article-summary pairs from BBC, extracted using a set of carefully designed heuristics. The dataset covers 44 languages ranging from low to high-resource, for many of which no public dataset is currently available. XL-Sum is highly abstractive, concise, and of high quality, as indicated by human and intrinsic evaluation. We fine-tune mT5, a state-of-the-art pretrained multilingual model, with XL-Sum and experiment on multilingual and low-resource summarization tasks. XL-Sum induces competitive results compared to the ones obtained using similar monolingual datasets: we show higher than 11 ROUGE-2 scores on 10 languages we benchmark on, with some of them exceeding 15, as obtained by multilingual training. Additionally, training on low-resource languages individually also provides competitive performance. To the best of our knowledge, XL-Sum is the largest abstractive summarization dataset in terms of the number of samples collected from a single source and the number of languages covered. We are releasing our dataset and models to encourage future research on multilingual abstractive summarization. The resources can be found at \url{this https URL}.
Tahmid Hasan, Abhik Bhattacharjee, Md Saiful Islam, Kazi Samin, Yuan-Fang Li, Yong-Bin Kang, M. Sohel Rahman, Rifat Shahriyar
92
Python
7/7/2021 ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information
Recent pretraining models in Chinese neglect two important aspects specific to the Chinese language: glyph and pinyin, which carry significant syntax and semantic information for language understanding. In this work, we propose ChineseBERT, which incorporates both the {\it glyph} and {\it pinyin} information of Chinese characters into language model pretraining. The glyph embedding is obtained based on different fonts of a Chinese character, being able to capture character semantics from the visual features, and the pinyin embedding characterizes the pronunciation of Chinese characters, which handles the highly prevalent heteronym phenomenon in Chinese (the same character has different pronunciations with different meanings). Pretrained on large-scale unlabeled Chinese corpus, the proposed ChineseBERT model yields significant performance boost over baseline models with fewer training steps. The porpsoed model achieves new SOTA performances on a wide range of Chinese NLP tasks, including machine reading comprehension, natural language inference, text classification, sentence pair matching, and competitive performances in named entity recognition. Code and pretrained models are publicly available at this https URL.
Zijun Sun, Xiaoya Li, Xiaofei Sun, Yuxian Meng, Xiang Ao, Qing He, Fei Wu, Jiwei Li
79
Python
7/7/2021 A Source-Criticism Debiasing Method for GloVe Embeddings
It is well-documented that word embeddings trained on large public corpora consistently exhibit known human social biases. Although many methods for debiasing exist, almost all fixate on completely eliminating biased information from the embeddings and often diminish training set size in the process. In this paper, we present a simple yet effective method for debiasing GloVe word embeddings (Pennington et al., 2014) which works by incorporating explicit information about training set bias rather than removing biased data outright. Our method runs quickly and efficiently with the help of a fast bias gradient approximation method from Brunet et al. (2019). As our approach is akin to the notion of 'source criticism' in the humanities, we term our method Source-Critical GloVe (SC-GloVe). We show that SC-GloVe reduces the effect size on Word Embedding Association Test (WEAT) sets without sacrificing training data or TOP-1 performance.
Hope McGovern
17
Julia
7/7/2021 A Training-free and Reference-free Summarization Evaluation Metric via Centrality-weighted Relevance and Self-referenced Redundancy
In recent years, reference-based and supervised summarization evaluation metrics have been widely explored. However, collecting human-annotated references and ratings are costly and time-consuming. To avoid these limitations, we propose a training-free and reference-free summarization evaluation metric. Our metric consists of a centrality-weighted relevance score and a self-referenced redundancy score. The relevance score is computed between the pseudo reference built from the source document and the given summary, where the pseudo reference content is weighted by the sentence centrality to provide importance guidance. Besides an $F_1$-based relevance score, we also design an $F_\beta$-based variant that pays more attention to the recall score. As for the redundancy score of the summary, we compute a self-masked similarity score with the summary itself to evaluate the redundant information in the summary. Finally, we combine the relevance and redundancy scores to produce the final evaluation score of the given summary. Extensive experiments show that our methods can significantly outperform existing methods on both multi-document and single-document summarization evaluation.
Wang Chen, Piji Li, Irwin King
10
7/7/2021 TWAG: A Topic-Guided Wikipedia Abstract Generator
Wikipedia abstract generation aims to distill a Wikipedia abstract from web sources and has met significant success by adopting multi-document summarization techniques. However, previous works generally view the abstract as plain text, ignoring the fact that it is a description of a certain entity and can be decomposed into different topics. In this paper, we propose a two-stage model TWAG that guides the abstract generation with topical information. First, we detect the topic of each input paragraph with a classifier trained on existing Wikipedia articles to divide input documents into different topics. Then, we predict the topic distribution of each abstract sentence, and decode the sentence from topic-aware representations with a Pointer-Generator network. We evaluate our model on the WikiCatSum dataset, and the results show that \modelnames outperforms various existing baselines and is capable of generating comprehensive abstracts. Our code and dataset can be accessed at \url{this https URL}
Fangwei Zhu, Shangqing Tu, Jiaxin Shi, Juanzi Li, Lei Hou, Tong Cui
9
Perl
7/7/2021 CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understanding
Despite pre-trained language models have proven useful for learning high-quality semantic representations, these models are still vulnerable to simple perturbations. Recent works aimed to improve the robustness of pre-trained models mainly focus on adversarial training from perturbed examples with similar semantics, neglecting the utilization of different or even opposite semantics. Different from the image processing field, the text is discrete and few word substitutions can cause significant semantic changes. To study the impact of semantics caused by small perturbations, we conduct a series of pilot experiments and surprisingly find that adversarial training is useless or even harmful for the model to detect these semantic changes. To address this problem, we propose Contrastive Learning with semantIc Negative Examples (CLINE), which constructs semantic negative examples unsupervised to improve the robustness under semantically adversarial attacking. By comparing with similar and opposite semantic examples, the model can effectively perceive the semantic changes caused by small perturbations. Empirical results show that our approach yields substantial improvements on a range of sentiment analysis, reasoning, and reading comprehension tasks. And CLINE also ensures the compactness within the same semantics and separability across different semantics in sentence-level.
Dong Wang, Ning Ding, Piji Li, Hai-Tao Zheng
12
Python
7/7/2021 A Span-Based Model for Joint Overlapped and Discontinuous Named Entity Recognition
Research on overlapped and discontinuous named entity recognition (NER) has received increasing attention. The majority of previous work focuses on either overlapped or discontinuous entities. In this paper, we propose a novel span-based model that can recognize both overlapped and discontinuous entities jointly. The model includes two major steps. First, entity fragments are recognized by traversing over all possible text spans, thus, overlapped entities can be recognized. Second, we perform relation classification to judge whether a given pair of entity fragments to be overlapping or succession. In this way, we can recognize not only discontinuous entities, and meanwhile doubly check the overlapped entities. As a whole, our model can be regarded as a relation extraction paradigm essentially. Experimental results on multiple benchmark datasets (i.e., CLEF, GENIA and ACE05) show that our model is highly competitive for overlapped and discontinuous NER.
Fei Li, Zhichao Lin, Meishan Zhang, Donghong Ji
8
Python
7/7/2021 Mixed Cross Entropy Loss for Neural Machine Translation
In neural machine translation, cross entropy (CE) is the standard loss function in two training methods of auto-regressive models, i.e., teacher forcing and scheduled sampling. In this paper, we propose mixed cross entropy loss (mixed CE) as a substitute for CE in both training approaches. In teacher forcing, the model trained with CE regards the translation problem as a one-to-one mapping process, while in mixed CE this process can be relaxed to one-to-many. In scheduled sampling, we show that mixed CE has the potential to encourage the training and testing behaviours to be similar to each other, more effectively mitigating the exposure bias problem. We demonstrate the superiority of mixed CE over CE on several machine translation datasets, WMT'16 Ro-En, WMT'16 Ru-En, and WMT'14 En-De in both teacher forcing and scheduled sampling setups. Furthermore, in WMT'14 En-De, we also find mixed CE consistently outperforms CE on a multi-reference set as well as a challenging paraphrased reference set. We also found the model trained with mixed CE is able to provide a better probability distribution defined over the translation output space. Our code is available at this https URL.
Haoran Li, Wei Lu
6
Python
7/7/2021 Keyphrase Generation for Scientific Document Retrieval
Sequence-to-sequence models have lead to significant progress in keyphrase generation, but it remains unknown whether they are reliable enough to be beneficial for document retrieval. This study provides empirical evidence that such models can significantly improve retrieval performance, and introduces a new extrinsic evaluation framework that allows for a better understanding of the limitations of keyphrase generation models. Using this framework, we point out and discuss the difficulties encountered with supplementing documents with -- not present in text -- keyphrases, and generalizing models across domains. Our code is available at this https URL
Florian Boudin, Ygor Gallina, Akiko Aizawa
4
Python
7/7/2021 Learning to Sample Replacements for ELECTRA Pre-Training
ELECTRA pretrains a discriminator to detect replaced tokens, where the replacements are sampled from a generator trained with masked language modeling. Despite the compelling performance, ELECTRA suffers from the following two issues. First, there is no direct feedback loop from discriminator to generator, which renders replacement sampling inefficient. Second, the generator's prediction tends to be over-confident along with training, making replacements biased to correct tokens. In this paper, we propose two methods to improve replacement sampling for ELECTRA pre-training. Specifically, we augment sampling with a hardness prediction mechanism, so that the generator can encourage the discriminator to learn what it has not acquired. We also prove that efficient sampling reduces the training variance of the discriminator. Moreover, we propose to use a focal loss for the generator in order to relieve oversampling of correct tokens as replacements. Experimental results show that our method improves ELECTRA pre-training on various downstream tasks.
Yaru Hao, Li Dong, Hangbo Bao, Ke Xu, Furu Wei
4
7/7/2021 Learning to communicate about shared procedural abstractions
Many real-world tasks require agents to coordinate their behavior to achieve shared goals. Successful collaboration requires not only adopting the same communicative conventions, but also grounding these conventions in the same task-appropriate conceptual abstractions. We investigate how humans use natural language to collaboratively solve physical assembly problems more effectively over time. Human participants were paired up in an online environment to reconstruct scenes containing two block towers. One participant could see the target towers, and sent assembly instructions for the other participant to reconstruct. Participants provided increasingly concise instructions across repeated attempts on each pair of towers, using higher-level referring expressions that captured each scene's hierarchical structure. To explain these findings, we extend recent probabilistic models of ad-hoc convention formation with an explicit perceptual learning mechanism. These results shed light on the inductive biases that enable intelligent agents to coordinate upon shared procedural abstractions.
William P. McCarthy, Robert D. Hawkins, Haoliang Wang, Cameron Holdaway, Judith E. Fan
4
Jupyter Notebook
7/7/2021 Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 Papers
This paper presents the first large-scale meta-evaluation of machine translation (MT). We annotated MT evaluations conducted in 769 research papers published from 2010 to 2020. Our study shows that practices for automatic MT evaluation have dramatically changed during the past decade and follow concerning trends. An increasing number of MT evaluations exclusively rely on differences between BLEU scores to draw conclusions, without performing any kind of statistical significance testing nor human evaluation, while at least 108 metrics claiming to be better than BLEU have been proposed. MT evaluations in recent papers tend to copy and compare automatic metric scores from previous work to claim the superiority of a method or an algorithm without confirming neither exactly the same training, validating, and testing data have been used nor the metric scores are comparable. Furthermore, tools for reporting standardized metric scores are still far from being widely adopted by the MT community. After showing how the accumulation of these pitfalls leads to dubious evaluation, we propose a guideline to encourage better automatic MT evaluation along with a simple meta-evaluation scoring method to assess its credibility.
Benjamin Marie, Atsushi Fujita, Raphael Rubino
3
7/7/2021 A Diverse Corpus for Evaluating and Developing English Math Word Problem Solvers
We present ASDiv (Academia Sinica Diverse MWP Dataset), a diverse (in terms of both language patterns and problem types) English math word problem (MWP) corpus for evaluating the capability of various MWP solvers. Existing MWP corpora for studying AI progress remain limited either in language usage patterns or in problem types. We thus present a new English MWP corpus with 2,305 MWPs that cover more text patterns and most problem types taught in elementary school. Each MWP is annotated with its problem type and grade level (for indicating the level of difficulty). Furthermore, we propose a metric to measure the lexicon usage diversity of a given MWP corpus, and demonstrate that ASDiv is more diverse than existing corpora. Experiments show that our proposed corpus reflects the true capability of MWP solvers more faithfully.
Shen-Yun Miao, Chao-Chun Liang, Keh-Yih Su
2
7/7/2021 Incorporating Domain Knowledge for Extractive Summarization of Legal Case Documents
Automatic summarization of legal case documents is an important and practical challenge. Apart from many domain-independent text summarization algorithms that can be used for this purpose, several algorithms have been developed specifically for summarizing legal case documents. However, most of the existing algorithms do not systematically incorporate domain knowledge that specifies what information should ideally be present in a legal case document summary. To address this gap, we propose an unsupervised summarization algorithm DELSumm which is designed to systematically incorporate guidelines from legal experts into an optimization setup. We conduct detailed experiments over case documents from the Indian Supreme Court. The experiments show that our proposed unsupervised method outperforms several strong baselines in terms of ROUGE scores, including both general summarization algorithms and legal-specific ones. In fact, though our proposed algorithm is unsupervised, it outperforms several supervised summarization models that are trained over thousands of document-summary pairs.
Paheli Bhattacharya, Soham Poddar, Koustav Rudra, Kripabandhu Ghosh, Saptarshi Ghosh
5
Python
7/7/2021 Benchmarking Differential Privacy and Federated Learning for BERT Models
Natural Language Processing (NLP) techniques can be applied to help with the diagnosis of medical conditions such as depression, using a collection of a person's utterances. Depression is a serious medical illness that can have adverse effects on how one feels, thinks, and acts, which can lead to emotional and physical problems. Due to the sensitive nature of such data, privacy measures need to be taken for handling and training models with such data. In this work, we study the effects that the application of Differential Privacy (DP) has, in both a centralized and a Federated Learning (FL) setup, on training contextualized language models (BERT, ALBERT, RoBERTa and DistilBERT). We offer insights on how to privately train NLP models and what architectures and setups provide more desirable privacy utility trade-offs. We envisage this work to be used in future healthcare and mental health studies to keep medical history private. Therefore, we provide an open-source implementation of this work.
Priyam Basu,�Tiasa Singha Roy,�Rakshit Naidu,�Zumrut Muftuoglu,�Sahib Singh,�Fatemehsadat Mireshghallah
3
Jupyter Notebook
7/7/2021 Key Information Extraction From Documents: Evaluation And Generator
Extracting information from documents usually relies on natural language processing methods working on one-dimensional sequences of text. In some cases, for example, for the extraction of key information from semi-structured documents, such as invoice-documents, spatial and formatting information of text are crucial to understand the contextual meaning. Convolutional neural networks are already common in computer vision models to process and extract relationships in multidimensional data. Therefore, natural language processing models have already been combined with computer vision models in the past, to benefit from e.g. positional information and to improve performance of these key information extraction models. Existing models were either trained on unpublished data sets or on an annotated collection of receipts, which did not focus on PDF-like documents. Hence, in this research project a template-based document generator was created to compare state-of-the-art models for information extraction. An existing information extraction model "Chargrid" (Katti et al., 2019) was reconstructed and the impact of a bounding box regression decoder, as well as the impact of an NLP pre-processing step was evaluated for information extraction from documents. The results have shown that NLP based pre-processing is beneficial for model performance. However, the use of a bounding box regression decoder increases the model performance only for fields that do not follow a rectangular shape.
Oliver Bensch, Mirela Popa, Constantin Spille
1
Python
7/7/2021 Effective Cascade Dual-Decoder Model for Joint Entity and Relation Extraction
Extracting relational triples from texts is a fundamental task in knowledge graph construction. The popular way of existing methods is to jointly extract entities and relations using a single model, which often suffers from the overlapping triple problem. That is, there are multiple relational triples that share the same entities within one sentence. In this work, we propose an effective cascade dual-decoder approach to extract overlapping relational triples, which includes a text-specific relation decoder and a relation-corresponded entity decoder. Our approach is straightforward: the text-specific relation decoder detects relations from a sentence according to its text semantics and treats them as extra features to guide the entity extraction; for each extracted relation, which is with trainable embedding, the relation-corresponded entity decoder detects the corresponding head and tail entities using a span-based tagging scheme. In this way, the overlapping triple problem is tackled naturally. Experiments on two public datasets demonstrate that our proposed approach outperforms state-of-the-art methods and achieves better F1 scores under the strict evaluation metric. Our implementation is available at this https URL.
Lianbo Ma, Huimin Ren, Xiliang Zhang
4
Python
7/7/2021 Automatically Select Emotion for Response via Personality-affected Emotion Transition
To provide consistent emotional interaction with users, dialog systems should be capable to automatically select appropriate emotions for responses like humans. However, most existing works focus on rendering specified emotions in responses or empathetically respond to the emotion of users, yet the individual difference in emotion expression is overlooked. This may lead to inconsistent emotional expressions and disinterest users. To tackle this issue, we propose to equip the dialog system with personality and enable it to automatically select emotions in responses by simulating the emotion transition of humans in conversation. In detail, the emotion of the dialog system is transitioned from its preceding emotion in context. The transition is triggered by the preceding dialog context and affected by the specified personality trait. To achieve this, we first model the emotion transition in the dialog system as the variation between the preceding emotion and the response emotion in the Valence-Arousal-Dominance (VAD) emotion space. Then, we design neural networks to encode the preceding dialog context and the specified personality traits to compose the variation. Finally, the emotion for response is selected from the sum of the preceding emotion and the variation. We construct a dialog dataset with emotion and personality labels and conduct emotion prediction tasks for evaluation. Experimental results validate the effectiveness of the personality-affected emotion transition.
Wen Zhiyuan, Cao Jiannong, Yang Ruosong, Liu Shuaiqi, Shen Jiaxing
2
Jupyter Notebook
7/7/2021 Reinforcement Learning for Abstractive Question Summarization with Question-aware Semantic Rewards
The growth of online consumer health questions has led to the necessity for reliable and accurate question answering systems. A recent study showed that manual summarization of consumer health questions brings significant improvement in retrieving relevant answers. However, the automatic summarization of long questions is a challenging task due to the lack of training data and the complexity of the related subtasks, such as the question focus and type recognition. In this paper, we introduce a reinforcement learning-based framework for abstractive question summarization. We propose two novel rewards obtained from the downstream tasks of (i) question-type identification and (ii) question-focus recognition to regularize the question generation model. These rewards ensure the generation of semantically valid questions and encourage the inclusion of key medical entities/foci in the question summary. We evaluated our proposed method on two benchmark datasets and achieved higher performance over state-of-the-art models. The manual evaluation of the summaries reveals that the generated questions are more diverse and have fewer factual inconsistencies than the baseline summaries
Shweta Yadav, Deepak Gupta, Asma Ben Abacha, Dina Demner-Fushman
1
Python
7/7/2021 Few-Shot Electronic Health Record Coding through Graph Contrastive Learning
Electronic health record (EHR) coding is the task of assigning ICD codes to each EHR. Most previous studies either only focus on the frequent ICD codes or treat rare and frequent ICD codes in the same way. These methods perform well on frequent ICD codes but due to the extremely unbalanced distribution of ICD codes, the performance on rare ones is far from satisfactory. We seek to improve the performance for both frequent and rare ICD codes by using a contrastive graph-based EHR coding framework, CoGraph, which re-casts EHR coding as a few-shot learning task. First, we construct a heterogeneous EHR word-entity (HEWE) graph for each EHR, where the words and entities extracted from an EHR serve as nodes and the relations between them serve as edges. Then, CoGraph learns similarities and dissimilarities between HEWE graphs from different ICD codes so that information can be transferred among them. In a few-shot learning scenario, the model only has access to frequent ICD codes during training, which might force it to encode features that are useful for frequent ICD codes only. To mitigate this risk, CoGraph devises two graph contrastive learning schemes, GSCL and GECL, that exploit the HEWE graph structures so as to encode transferable features. GSCL utilizes the intra-correlation of different sub-graphs sampled from HEWE graphs while GECL exploits the inter-correlation among HEWE graphs at different clinical stages. Experiments on the MIMIC-III benchmark dataset show that CoGraph significantly outperforms state-of-the-art methods on EHR coding, not only on frequent ICD codes, but also on rare codes, in terms of several evaluation indicators. On frequent ICD codes, GSCL and GECL improve the classification accuracy and F1 by 1.31% and 0.61%, respectively, and on rare ICD codes CoGraph has more obvious improvements by 2.12% and 2.95%.
Shanshan Wang, Pengjie Ren, Zhumin Chen, Zhaochun Ren, Huasheng Liang, Qiang Yan, Evangelos Kanoulas, Maarten de Rijke
2
Python
7/7/2021 Manually Annotated Spelling Error Corpus for Amharic
This paper presents a manually annotated spelling error corpus for Amharic, lingua franca in Ethiopia. The corpus is designed to be used for the evaluation of spelling error detection and correction. The misspellings are tagged as non-word and real-word errors. In addition, the contextual information available in the corpus makes it useful in dealing with both types of spelling errors.
Andargachew Mekonnen Gezmu, Tirufat Tesifaye Lema, Binyam Ephrem Seyoum, Andreas Nürnberger
0
7/7/2021 Representation based meta-learning for few-shot spoken intent recognition
Spoken intent detection has become a popular approach to interface with various smart devices with ease. However, such systems are limited to the preset list of intents-terms or commands, which restricts the quick customization of personal devices to new intents. This paper presents a few-shot spoken intent classification approach with task-agnostic representations via meta-learning paradigm. Specifically, we leverage the popular representation-based meta-learning learning to build a task-agnostic representation of utterances, that then use a linear classifier for prediction. We evaluate three such approaches on our novel experimental protocol developed on two popular spoken intent classification datasets: Google Commands and the Fluent Speech Commands dataset. For a 5-shot (1-shot) classification of novel classes, the proposed framework provides an average classification accuracy of 88.6% (76.3%) on the Google Commands dataset, and 78.5% (64.2%) on the Fluent Speech Commands dataset. The performance is comparable to traditionally supervised classification models with abundant training samples.
Ashish Mittal, Samarth Bharadwaj, Shreya Khare, Saneem Chemmengath, Karthik Sankaranarayanan, Brian Kingsbury
0
7/7/2021 AMU-EURANOVA at CASE 2021 Task 1: Assessing the stability of multilingual BERT
This paper explains our participation in task 1 of the CASE 2021 shared task. This task is about multilingual event extraction from news. We focused on sub-task 4, event information extraction. This sub-task has a small training dataset and we fine-tuned a multilingual BERT to solve this sub-task. We studied the instability problem on the dataset and tried to mitigate it.
Leo Bouscarrat (LIS, TALEP, QARMA), Antoine Bonnefoy, Cecile Capponi (LIS, QARMA), Carlos Ramisch (LIS, TALEP)
0
Python
7/7/2021 Exploring the Representation of Word Meanings in Context: A Case Study on Homonymy and Synonymy
This paper presents a multilingual study of word meaning representations in context. We assess the ability of both static and contextualized models to adequately represent different lexical-semantic relations, such as homonymy and synonymy. To do so, we created a new multilingual dataset that allows us to perform a controlled evaluation of several factors such as the impact of the surrounding context or the overlap between words, conveying the same or different senses. A systematic assessment on four scenarios shows that the best monolingual models based on Transformers can adequately disambiguate homonyms in context. However, as they rely heavily on context, these models fail at representing words with different senses when occurring in similar sentences. Experiments are performed in Galician, Portuguese, English, and Spanish, and both the dataset (with more than 3,000 evaluation items) and new models are freely released with this study.
Marcos Garcia
0
Python
7/7/2021 News Article Retrieval in Context for Event-centric Narrative Creation
Writers such as journalists often use automatic tools to find relevant content to include in their narratives. In this paper, we focus on supporting writers in the news domain to develop event-centric narratives. Given an incomplete narrative that specifies a main event and a context, we aim to retrieve news articles that discuss relevant events that would enable the continuation of the narrative. We formally define this task and propose a retrieval dataset construction procedure that relies on existing news articles to simulate incomplete narratives and relevant articles. Experiments on two datasets derived from this procedure show that state-of-the-art lexical and semantic rankers are not sufficient for this task. We show that combining those with a ranker that ranks articles by reverse chronological order outperforms those rankers alone. We also perform an in-depth quantitative and qualitative analysis of the results that sheds light on the characteristics of this task.
Nikos Voskarides, Edgar Meij, Sabrina Sauer, Maarten de Rijke
0
7/7/2021 Modeling Target-side Inflection in Placeholder Translation
Placeholder translation systems enable the users to specify how a specific phrase is translated in the output sentence. The system is trained to output special placeholder tokens, and the user-specified term is injected into the output through the context-free replacement of the placeholder token. However, this approach could result in ungrammatical sentences because it is often the case that the specified term needs to be inflected according to the context of the output, which is unknown before the translation. To address this problem, we propose a novel method of placeholder translation that can inflect specified terms according to the grammatical construction of the output sentence. We extend the sequence-to-sequence architecture with a character-level decoder that takes the lemma of a user-specified term and the words generated from the word-level decoder to output the correct inflected form of the lemma. We evaluate our approach with a Japanese-to-English translation task in the scientific writing domain, and show that our model can incorporate specified terms in the correct form more successfully than other comparable models.
Ryokan Ri, Toshiaki Nakazawa, Yoshimasa Tsuruoka
0
Python
7/7/2021 KGRefiner: Knowledge Graph Refinement for Improving Accuracy of Translational Link Prediction Methods
Link prediction is the task of predicting missing relations between entities of the knowledge graph by inferring from the facts contained in it. Recent work in link prediction has attempted to provide a model for increasing link prediction accuracy by using more layers in neural network architecture or methods that add to the computational complexity of models. This paper we proposed a method for refining the knowledge graph, which makes the knowledge graph more informative, and link prediction operations can be performed more accurately using relatively fast translational models. Translational link prediction models, such as TransE, TransH, TransD, etc., have much less complexity than deep learning approaches. This method uses the hierarchy of relationships and also the hierarchy of entities in the knowledge graph to add the entity information as a new entity to the graph and connect it to the nodes which contain this information in their hierarchy. Our experiments show that our method can significantly increase the performance of translational link prediction methods in H@10, MR, MRR.
Mohammad Javad Saeedizade, Najmeh Torabian, Behrouz Minaei-Bidgoli
0
Python
7/7/2021 SymbolicGPT: A Generative Transformer Model for Symbolic Regression
Symbolic regression is the task of identifying a mathematical expression that best fits a provided dataset of input and output values. Due to the richness of the space of mathematical expressions, symbolic regression is generally a challenging problem. While conventional approaches based on genetic evolution algorithms have been used for decades, deep learning-based methods are relatively new and an active research area. In this work, we present SymbolicGPT, a novel transformer-based language model for symbolic regression. This model exploits the advantages of probabilistic language models like GPT, including strength in performance and flexibility. Through comprehensive experiments, we show that our model performs strongly compared to competing models with respect to the accuracy, running time, and data efficiency.
Mojtaba Valipour, Bowen You, Maysum Panju, Ali Ghodsi
7/7/2021 The MultiBERTs: BERT Reproductions for Robustness Analysis
Experiments with pretrained models such as BERT are often based on a single checkpoint. While the conclusions drawn apply to the artifact (i.e., the particular instance of the model), it is not always clear whether they hold for the more general procedure (which includes the model architecture, training data, initialization scheme, and loss function). Recent work has shown that re-running pretraining can lead to substantially different conclusions about performance, suggesting that alternative evaluations are needed to make principled statements about procedures. To address this question, we introduce MultiBERTs: a set of 25 BERT-base checkpoints, trained with similar hyper-parameters as the original BERT model but differing in random initialization and data shuffling. The aim is to enable researchers to draw robust and statistically justified conclusions about pretraining procedures. The full release includes 25 fully trained checkpoints, as well as statistical guidelines and a code library implementing our recommended hypothesis testing methods. Finally, for five of these models we release a set of 28 intermediate checkpoints in order to support research on learning dynamics.
Thibault Sellam, Steve Yadlowsky, Jason Wei, Naomi Saphra, Alexander D'Amour, Tal Linzen, Jasmijn Bastings, Iulia Turc, Jacob Eisenstein, Dipanjan Das, Ian Tenney, Ellie Pavlick
n/a
7/7/2021 Learning from Miscellaneous Other-Class Words for Few-shot Named Entity Recognition
Few-shot Named Entity Recognition (NER) exploits only a handful of annotations to identify and classify named entity mentions. Prototypical network shows superior performance on few-shot NER. However, existing prototypical methods fail to differentiate rich semantics in other-class words, which will aggravate overfitting under few shot scenario. To address the issue, we propose a novel model, Mining Undefined Classes from Other-class (MUCO), that can automatically induce different undefined classes from the other class to improve few-shot NER. With these extra-labeled undefined classes, our method will improve the discriminative ability of NER classifier and enhance the understanding of predefined classes with stand-by semantic knowledge. Experimental results demonstrate that our model outperforms five state-of-the-art models in both 1-shot and 5-shots settings on four NER benchmarks. We will release the code upon acceptance. The source code is released on https: //github.com/shuaiwa16/OtherClassNER.git.
Meihan Tong, Shuai Wang, Bin Xu, Yixin Cao, Minghui Liu, Lei Hou, Juanzi Li
n/a
6/29/2021 Charformer: Fast Character Transformers via Gradient-based Subword Tokenization
State-of-the-art models in natural language processing rely on separate rigid subword tokenization algorithms, which limit their generalization ability and adaptation to new settings. In this paper, we propose a new model inductive bias that learns a subword tokenization end-to-end as part of the model. To this end, we introduce a soft gradient-based subword tokenization module (GBST) that automatically learns latent subword representations from characters in a data-driven fashion. Concretely, GBST enumerates candidate subword blocks and learns to score them in a position-wise fashion using a block scoring network. We additionally introduce Charformer, a deep Transformer model that integrates GBST and operates on the byte level. Via extensive experiments on English GLUE, multilingual, and noisy text datasets, we show that Charformer outperforms a series of competitive byte-level baselines while generally performing on par and sometimes outperforming subword-based models. Additionally, Charformer is fast, improving the speed of both vanilla byte-level and subword-level Transformers by 28%-100% while maintaining competitive quality. We believe this work paves the way for highly performant token-free models that are trained completely end-to-end.
Yi Tay, Vinh Q. Tran, Sebastian Ruder, Jai Gupta, Hyung Won Chung, Dara Bahri, Zhen Qin, Simon Baumgartner, Cong Yu, Donald Metzler
18503
Jupyter Notebook
6/29/2021 Dive into Deep Learning
This open-source book represents our attempt to make deep learning approachable, teaching readers the concepts, the context, and the code. The entire book is drafted in Jupyter notebooks, seamlessly integrating exposition figures, math, and interactive examples with self-contained code. Our goal is to offer a resource that could (i) be freely available for everyone; (ii) offer sufficient technical depth to provide a starting point on the path to actually becoming an applied machine learning scientist; (iii) include runnable code, showing readers how to solve problems in practice; (iv) allow for rapid updates, both by us and also by the community at large; (v) be complemented by a forum for interactive discussion of technical details and to answer questions.
Aston Zhang, Zachary C. Lipton, Mu Li, Alexander J. Smola
10472
Python
6/29/2021 GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio
This paper introduces GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10,000 hours of high quality labeled audio suitable for supervised training, and 40,000 hours of total audio suitable for semi-supervised and unsupervised training. Around 40,000 hours of transcribed audio is first collected from audiobooks, podcasts and YouTube, covering both read and spontaneous speaking styles, and a variety of topics, such as arts, science, sports, etc. A new forced alignment and segmentation pipeline is proposed to create sentence segments suitable for speech recognition training, and to filter out segments with low-quality transcription. For system training, GigaSpeech provides five subsets of different sizes, 10h, 250h, 1000h, 2500h, and 10000h. For our 10,000-hour XL training subset, we cap the word error rate at 4% during the filtering/validation stage, and for all our other smaller training subsets, we cap it at 0%. The DEV and TEST evaluation sets, on the other hand, are re-processed by professional human transcribers to ensure high transcription quality. Baseline systems are provided for popular speech recognition toolkits, namely Athena, ESPnet, Kaldi and Pika.
Guoguo Chen, Shuzhou Chai, Guanbo Wang, Jiayu Du, Wei-Qiang Zhang, Chao Weng, Dan Su, Daniel Povey, Jan Trmal, Junbo Zhang, Mingjie Jin, Sanjeev Khudanpur, Shinji Watanabe, Shuaijiang Zhao, Wei Zou, Xiangang Li, Xuchen Yao, Yongqing Wang, Yujun Wang, Zhao You, Zhiyong Yan
261
Shell
6/29/2021 pysentimiento: A Python Toolkit for Sentiment Analysis and SocialNLP tasks
Extracting opinions from texts has gathered a lot of interest in the last years, as we are experiencing an unprecedented volume of user-generated content in social networks and other places. A problem that social researchers find in using opinion mining tools is that they are usually behind commercial APIs and unavailable for other languages than English. To address these issues, we present pysentimiento, a multilingual Python toolkit for Sentiment Analysis and other Social NLP tasks. This open-source library brings state-of-the-art models for Spanish and English in a black-box fashion, allowing researchers to easily access these techniques.
Juan Manuel Perez, Juan Carlos Giudici, Franco Luque
76
Jupyter Notebook
6/29/2021 Calliar: An Online Handwritten Dataset for Arabic Calligraphy
Calligraphy is an essential part of the Arabic heritage and culture. It has been used in the past for the decoration of houses and mosques. Usually, such calligraphy is designed manually by experts with aesthetic insights. In the past few years, there has been a considerable effort to digitize such type of art by either taking a photo of decorated buildings or drawing them using digital devices. The latter is considered an online form where the drawing is tracked by recording the apparatus movement, an electronic pen for instance, on a screen. In the literature, there are many offline datasets collected with a diversity of Arabic styles for calligraphy. However, there is no available online dataset for Arabic calligraphy. In this paper, we illustrate our approach for the collection and annotation of an online dataset for Arabic calligraphy called Calliar that consists of 2,500 sentences. Calliar is annotated for stroke, character, word and sentence level prediction.
Zaid Alyafeai, Maged S. Al-shaibani, Mustafa Ghaleb, Yousif Ahmed Al-Wajih
69
Jupyter Notebook
6/29/2021 Thinking Like Transformers
What is the computational model behind a Transformer? Where recurrent neural networks have direct parallels in finite state machines, allowing clear discussion and thought around architecture variants or trained models, Transformers have no such familiar parallel. In this paper we aim to change that, proposing a computational model for the transformer-encoder in the form of a programming language. We map the basic components of a transformer-encoder -- attention and feed-forward computation -- into simple primitives, around which we form a programming language: the Restricted Access Sequence Processing Language (RASP). We show how RASP can be used to program solutions to tasks that could conceivably be learned by a Transformer, and how a Transformer can be trained to mimic a RASP solution. In particular, we provide RASP programs for histograms, sorting, and Dyck-languages. We further use our model to relate their difficulty in terms of the number of required layers and attention heads: analyzing a RASP program implies a maximum number of heads and layers necessary to encode a task in a transformer. Finally, we see how insights gained from our abstraction might be used to explain phenomena seen in recent works.
Gail Weiss, Yoav Goldberg, Eran Yahav
68
Python
6/29/2021 CPM-2: Large-scale Cost-effective Pre-trained Language Models
In recent years, the size of pre-trained language models (PLMs) has grown by leaps and bounds. However, efficiency issues of these large-scale PLMs limit their utilization in real-world scenarios. We present a suite of cost-effective techniques for the use of PLMs to deal with the efficiency issues of pre-training, fine-tuning, and inference. (1) We introduce knowledge inheritance to accelerate the pre-training process by exploiting existing PLMs instead of training models from scratch. (2) We explore the best practice of prompt tuning with large-scale PLMs. Compared with conventional fine-tuning, prompt tuning significantly reduces the number of task-specific parameters. (3) We implement a new inference toolkit, namely InfMoE, for using large-scale PLMs with limited computational resources. Based on our cost-effective pipeline, we pre-train two models: an encoder-decoder bilingual model with 11 billion parameters (CPM-2) and its corresponding MoE version with 198 billion parameters. In our experiments, we compare CPM-2 with mT5 on downstream tasks. Experimental results show that CPM-2 has excellent general language intelligence. Moreover, we validate the efficiency of InfMoE when conducting inference of large-scale models having tens of billions of parameters on a single GPU. All source code and model parameters are available at this https URL.
Zhengyan Zhang, Yuxian Gu, Xu Han, Shengqi Chen, Chaojun Xiao, Zhenbo Sun, Yuan Yao, Fanchao Qi, Jian Guan, Pei Ke, Yanzheng Cai, Guoyang Zeng, Zhixing Tan, Zhiyuan Liu, Minlie Huang, Wentao Han, Yang Liu, Xiaoyan Zhu, Maosong Sun
45
6/29/2021 BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data
Maintaining consistent personas is essential for dialogue agents. Although tremendous advancements have been brought, the limited-scale of annotated persona-dense data are still barriers towards training robust and consistent persona-based dialogue models. In this work, we show how the challenges can be addressed by disentangling persona-based dialogue generation into two sub-tasks with a novel BERT-over-BERT (BoB) model. Specifically, the model consists of a BERT-based encoder and two BERT-based decoders, where one decoder is for response generation, and another is for consistency understanding. In particular, to learn the ability of consistency understanding from large-scale non-dialogue inference data, we train the second decoder in an unlikelihood manner. Under different limited data settings, both automatic and human evaluations demonstrate that the proposed model outperforms strong baselines in response quality and persona consistency.
Haoyu Song, Yan Wang, Kaiyan Zhang, Wei-Nan Zhang, Ting Liu
38
Python
6/29/2021 NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs
Conventional representation learning algorithms for knowledge graphs (KG) map each entity to a unique embedding vector. Such a shallow lookup results in a linear growth of memory consumption for storing the embedding matrix and incurs high computational costs when working with real-world KGs. Drawing parallels with subword tokenization commonly used in NLP, we explore the landscape of more parameter-efficient node embedding strategies with possibly sublinear memory requirements. To this end, we propose NodePiece, an anchor-based approach to learn a fixed-size entity vocabulary. In NodePiece, a vocabulary of subword/sub-entity units is constructed from anchor nodes in a graph with known relation types. Given such a fixed-size vocabulary, it is possible to bootstrap an encoding and embedding for any entity, including those unseen during training. Experiments show that NodePiece performs competitively in node classification, link prediction, and relation prediction tasks while retaining less than 10% of explicit nodes in a graph as anchors and often having 10x fewer parameters.
Mikhail Galkin, Jiapeng Wu, Etienne Denis, William L. Hamilton
35
Python
6/29/2021 DocNLI: A Large-scale Dataset for Document-level Natural Language Inference
Natural language inference (NLI) is formulated as a unified framework for solving various NLP problems such as relation extraction, question answering, summarization, etc. It has been studied intensively in the past few years thanks to the availability of large-scale labeled datasets. However, most existing studies focus on merely sentence-level inference, which limits the scope of NLI's application in downstream NLP problems. This work presents DocNLI -- a newly-constructed large-scale dataset for document-level NLI. DocNLI is transformed from a broad range of NLP problems and covers multiple genres of text. The premises always stay in the document granularity, whereas the hypotheses vary in length from single sentences to passages with hundreds of words. Additionally, DocNLI has pretty limited artifacts which unfortunately widely exist in some popular sentence-level NLI datasets. Our experiments demonstrate that, even without fine-tuning, a model pretrained on DocNLI shows promising performance on popular sentence-level benchmarks, and generalizes well to out-of-domain NLP tasks that rely on inference at document granularity. Task-specific fine-tuning can bring further improvements. Data, code, and pretrained models can be found at this https URL.
Wenpeng Yin, Dragomir Radev, Caiming Xiong
25
Python
6/29/2021 Towards Knowledge-Grounded Counter Narrative Generation for Hate Speech
Tackling online hatred using informed textual responses - called counter narratives - has been brought under the spotlight recently. Accordingly, a research line has emerged to automatically generate counter narratives in order to facilitate the direct intervention in the hate discussion and to prevent hate content from further spreading. Still, current neural approaches tend to produce generic/repetitive responses and lack grounded and up-to-date evidence such as facts, statistics, or examples. Moreover, these models can create plausible but not necessarily true arguments. In this paper we present the first complete knowledge-bound counter narrative generation pipeline, grounded in an external knowledge repository that can provide more informative content to fight online hatred. Together with our approach, we present a series of experiments that show its feasibility to produce suitable and informative counter narratives in in-domain and cross-domain settings.
Yi-Ling Chung, Serra Sinem Tekiroglu, Marco Guerini
23
6/29/2021 Scientific Language Models for Biomedical Knowledge Base Completion: An Empirical Study
Biomedical knowledge graphs (KGs) hold rich information on entities such as diseases, drugs, and genes. Predicting missing links in these graphs can boost many important applications, such as drug design and repurposing. Recent work has shown that general-domain language models (LMs) can serve as "soft" KGs, and that they can be fine-tuned for the task of KG completion. In this work, we study scientific LMs for KG completion, exploring whether we can tap into their latent knowledge to enhance biomedical link prediction. We evaluate several domain-specific LMs, fine-tuning them on datasets centered on drugs and diseases that we represent as KGs and enrich with textual entity descriptions. We integrate the LM-based models with KG embedding models, using a router method that learns to assign each input example to either type of model and provides a substantial boost in performance. Finally, we demonstrate the advantage of LM models in the inductive setting with novel scientific entities. Our datasets and code are made publicly available.
Rahul Nadkarni, David Wadden, Iz Beltagy, Noah A. Smith, Hannaneh Hajishirzi, Tom Hope
17
Python
6/29/2021 TagRuler: Interactive Tool for Span-Level Data Programming by Demonstration
Despite rapid developments in the field of machine learning research, collecting high-quality labels for supervised learning remains a bottleneck for many applications. This difficulty is exacerbated by the fact that state-of-the-art models for NLP tasks are becoming deeper and more complex, often increasing the amount of training data required even for fine-tuning. Weak supervision methods, including data programming, address this problem and reduce the cost of label collection by using noisy label sources for supervision. However, until recently, data programming was only accessible to users who knew how to program. To bridge this gap, the Data Programming by Demonstration framework was proposed to facilitate the automatic creation of labeling functions based on a few examples labeled by a domain expert. This framework has proven successful for generating high-accuracy labeling models for document classification. In this work, we extend the DPBD framework to span-level annotation tasks, arguably one of the most time-consuming NLP labeling tasks. We built a novel tool, TagRuler, that makes it easy for annotators to build span-level labeling functions without programming and encourages them to explore trade-offs between different labeling models and active learning strategies. We empirically demonstrated that an annotator could achieve a higher F1 score using the proposed tool compared to manual labeling for different span-level annotation tasks.
Dongjin Choi, Sara Evensen, Cagatay Demiralp, Estevam Hruschka
22
JavaScript
6/29/2021 LV-BERT: Exploiting Layer Variety for BERT
Modern pre-trained language models are mostly built upon backbones stacking self-attention and feed-forward layers in an interleaved order. In this paper, beyond this stereotyped layer pattern, we aim to improve pre-trained models by exploiting layer variety from two aspects: the layer type set and the layer order. Specifically, besides the original self-attention and feed-forward layers, we introduce convolution into the layer type set, which is experimentally found beneficial to pre-trained models. Furthermore, beyond the original interleaved order, we explore more layer orders to discover more powerful architectures. However, the introduced layer variety leads to a large architecture space of more than billions of candidates, while training a single candidate model from scratch already requires huge computation cost, making it not affordable to search such a space by directly training large amounts of candidate models. To solve this problem, we first pre-train a supernet from which the weights of all candidate models can be inherited, and then adopt an evolutionary algorithm guided by pre-training accuracy to find the optimal architecture. Extensive experiments show that LV-BERT model obtained by our method outperforms BERT and its variants on various downstream tasks. For example, LV-BERT-small achieves 79.8 on the GLUE testing set, 1.8 higher than the strong baseline ELECTRA-small.
Weihao Yu, Zihang Jiang, Fei Chen, Qibin Hou, Jiashi Feng
13
Python
6/29/2021 N-Best ASR Transformer: Enhancing SLU Performance using Multiple ASR Hypotheses
Spoken Language Understanding (SLU) systems parse speech into semantic structures like dialog acts and slots. This involves the use of an Automatic Speech Recognizer (ASR) to transcribe speech into multiple text alternatives (hypotheses). Transcription errors, common in ASRs, impact downstream SLU performance negatively. Approaches to mitigate such errors involve using richer information from the ASR, either in form of N-best hypotheses or word-lattices. We hypothesize that transformer models learn better with a simpler utterance representation using the concatenation of the N-best ASR alternatives, where each alternative is separated by a special delimiter [SEP]. In our work, we test our hypothesis by using concatenated N-best ASR alternatives as the input to transformer encoder models, namely BERT and XLM-RoBERTa, and achieve performance equivalent to the prior state-of-the-art model on DSTC2 dataset. We also show that our approach significantly outperforms the prior state-of-the-art when subjected to the low data regime. Additionally, this methodology is accessible to users of third-party ASR APIs which do not provide word-lattice information.
Karthik Ganesan, Pakhi Bamdev, Jaivarsan B, Amresh Venugopal, Abhinav Tushar
12
Python
6/29/2021 GEM: A General Evaluation Benchmark for Multimodal Tasks
In this paper, we present GEM as a General Evaluation benchmark for Multimodal tasks. Different from existing datasets such as GLUE, SuperGLUE, XGLUE and XTREME that mainly focus on natural language tasks, GEM is a large-scale vision-language benchmark, which consists of GEM-I for image-language tasks and GEM-V for video-language tasks. Comparing with existing multimodal datasets such as MSCOCO and Flicker30K for image-language tasks, YouCook2 and MSR-VTT for video-language tasks, GEM is not only the largest vision-language dataset covering image-language tasks and video-language tasks at the same time, but also labeled in multiple languages. We also provide two baseline models for this benchmark. We will release the dataset, code and baseline models, aiming to advance the development of multilingual multimodal research.
Lin Su, Nan Duan, Edward Cui, Lei Ji, Chenfei Wu, Huaishao Luo, Yongfei Liu, Ming Zhong, Taroon Bharti, Arun Sacheti
12
JavaScript
6/29/2021 Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translation
Policy gradient algorithms have found wide adoption in NLP, but have recently become subject to criticism, doubting their suitability for NMT. Choshen et al. (2020) identify multiple weaknesses and suspect that their success is determined by the shape of output distributions rather than the reward. In this paper, we revisit these claims and study them under a wider range of configurations. Our experiments on in-domain and cross-domain adaptation reveal the importance of exploration and reward scaling, and provide empirical counter-evidence to these claims.
Samuel Kiegeland, Julia Kreutzer
10
Python
6/29/2021 QuaPy: A Python-Based Framework for Quantification
QuaPy is an open-source framework for performing quantification (a.k.a. supervised prevalence estimation), written in Python. Quantification is the task of training quantifiers via supervised learning, where a quantifier is a predictor that estimates the relative frequencies (a.k.a. prevalence values) of the classes of interest in a sample of unlabelled data. While quantification can be trivially performed by applying a standard classifier to each unlabelled data item and counting how many data items have been assigned to each class, it has been shown that this "classify and count" method is outperformed by methods specifically designed for quantification. QuaPy provides implementations of a number of baseline methods and advanced quantification methods, of routines for quantification-oriented model selection, of several broadly accepted evaluation measures, and of robust evaluation protocols routinely used in the field. QuaPy also makes available datasets commonly used for testing quantifiers, and offers visualization tools for facilitating the analysis and interpretation of the results. The software is open-source and publicly available under a BSD-3 licence via this https URL, and can be installed via pip (this https URL)
Alejandro Moreo, Andrea Esuli, Fabrizio Sebastiani
7
Python
6/29/2021 BARTScore: Evaluating Generated Text as Text Generation
A wide variety of NLP applications, such as machine translation, summarization, and dialog, involve text generation. One major challenge for these applications is how to evaluate whether such generated texts are actually fluent, accurate, or effective. In this work, we conceptualize the evaluation of generated text as a text generation problem, modeled using pre-trained sequence-to-sequence models. The general idea is that models trained to convert the generated text to/from a reference output or the source text will achieve higher scores when the generated text is better. We operationalize this idea using BART, an encoder-decoder based pre-trained model, and propose a metric BARTScore with a number of variants that can be flexibly applied in an unsupervised fashion to evaluation of text from different perspectives (e.g. informativeness, fluency, or factuality). BARTScore is conceptually simple and empirically effective. It can outperform existing top-scoring metrics in 16 of 22 test settings, covering evaluation of 16 datasets (e.g., machine translation, text summarization) and 7 different perspectives (e.g., informativeness, factuality). Code to calculate BARTScore is available at this https URL, and we have released an interactive leaderboard for meta-evaluation at this http URL on the ExplainaBoard platform, which allows us to interactively understand the strengths, weaknesses, and complementarity of each metric.
Weizhe Yuan, Graham Neubig, Pengfei Liu
28
6/29/2021 CodemixedNLP: An Extensible and Open NLP Toolkit for Code-Mixing
The NLP community has witnessed steep progress in a variety of tasks across the realms of monolingual and multilingual language processing recently. These successes, in conjunction with the proliferating mixed language interactions on social media have boosted interest in modeling code-mixed texts. In this work, we present CodemixedNLP, an open-source library with the goals of bringing together the advances in code-mixed NLP and opening it up to a wider machine learning community. The library consists of tools to develop and benchmark versatile model architectures that are tailored for mixed texts, methods to expand training sets, techniques to quantify mixing styles, and fine-tuned state-of-the-art models for 7 tasks in Hinglish. We believe this work has a potential to foster a distributed yet collaborative and sustainable ecosystem in an otherwise dispersed space of code-mixing research. The toolkit is designed to be simple, easily extensible, and resourceful to both researchers as well as practitioners.
Sai Muralidhar Jayanthi, Kavya Nerella, Khyathi Raghavi Chandu, Alan W Black
9
Python
6/29/2021 AIT-QA: Question Answering Dataset over Complex Tables in the Airline Industry
Recent advances in transformers have enabled Table Question Answering (Table QA) systems to achieve high accuracy and SOTA results on open domain datasets like WikiTableQuestions and WikiSQL. Such transformers are frequently pre-trained on open-domain content such as Wikipedia, where they effectively encode questions and corresponding tables from Wikipedia as seen in Table QA dataset. However, web tables in Wikipedia are notably flat in their layout, with the first row as the sole column header. The layout lends to a relational view of tables where each row is a tuple. Whereas, tables in domain-specific business or scientific documents often have a much more complex layout, including hierarchical row and column headers, in addition to having specialized vocabulary terms from that domain. To address this problem, we introduce the domain-specific Table QA dataset AIT-QA (Airline Industry Table QA). The dataset consists of 515 questions authored by human annotators on 116 tables extracted from public U.S. SEC filings (publicly available at: this https URL) of major airline companies for the fiscal years 2017-2019. We also provide annotations pertaining to the nature of questions, marking those that require hierarchical headers, domain-specific terminology, and paraphrased forms. Our zero-shot baseline evaluation of three transformer-based SOTA Table QA methods - TaPAS (end-to-end), TaBERT (semantic parsing-based), and RCI (row-column encoding-based) - clearly exposes the limitation of these methods in this practical setting, with the best accuracy at just 51.8\% (RCI). We also present pragmatic table preprocessing steps used to pivot and project these complex tables into a layout suitable for the SOTA Table QA models.
Yannis Katsis, Saneem Chemmengath, Vishwajeet Kumar, Samarth Bharadwaj, Mustafa Canim, Michael Glass, Alfio Gliozzo, Feifei Pan, Jaydeep Sen, Karthik Sankaranarayanan, Soumen Chakrabarti
7
6/29/2021 Do Encoder Representations of Generative Dialogue Models Encode Sufficient Information about the Task ?
Predicting the next utterance in dialogue is contingent on encoding of users' input text to generate appropriate and relevant response in data-driven approaches. Although the semantic and syntactic quality of the language generated is evaluated, more often than not, the encoded representation of input is not evaluated. As the representation of the encoder is essential for predicting the appropriate response, evaluation of encoder representation is a challenging yet important problem. In this work, we showcase evaluating the text generated through human or automatic metrics is not sufficient to appropriately evaluate soundness of the language understanding of dialogue models and, to that end, propose a set of probe tasks to evaluate encoder representation of different language encoders commonly used in dialogue models. From experiments, we observe that some of the probe tasks are easier and some are harder for even sophisticated model architectures to learn. And, through experiments we observe that RNN based architectures have lower performance on automatic metrics on text generation than transformer model but perform better than the transformer model on the probe tasks indicating that RNNs might preserve task information better than the Transformers.
Prasanna Parthasarathi, Joelle Pineau, Sarath Chandar
4
Python
6/29/2021 Weakly Supervised Pre-Training for Multi-Hop Retriever
In multi-hop QA, answering complex questions entails iterative document retrieval for finding the missing entity of the question. The main steps of this process are sub-question detection, document retrieval for the sub-question, and generation of a new query for the final document retrieval. However, building a dataset that contains complex questions with sub-questions and their corresponding documents requires costly human annotation. To address the issue, we propose a new method for weakly supervised multi-hop retriever pre-training without human efforts. Our method includes 1) a pre-training task for generating vector representations of complex questions, 2) a scalable data generation method that produces the nested structure of question and sub-question as weak supervision for pre-training, and 3) a pre-training model structure based on dense encoders. We conduct experiments to compare the performance of our pre-trained retriever with several state-of-the-art models on end-to-end multi-hop QA as well as document retrieval. The experimental results show that our pre-trained retriever is effective and also robust on limited data and computational resources.
Yeon Seonwoo, Sang-Woo Lee, Ji-Hoon Kim, Jung-Woo Ha, Alice Oh
5
Python
6/29/2021 PRASEMap: A Probabilistic Reasoning and Semantic Embedding based Knowledge Graph Alignment System
Knowledge Graph (KG) alignment aims at finding equivalent entities and relations (i.e., mappings) between two KGs. The existing approaches utilize either reasoning-based or semantic embedding-based techniques, but few studies explore their combination. In this demonstration, we present PRASEMap, an unsupervised KG alignment system that iteratively computes the Mappings with both Probabilistic Reasoning (PR) And Semantic Embedding (SE) techniques. PRASEMap can support various embedding-based KG alignment approaches as the SE module, and enables easy human computer interaction that additionally provides an option for users to feed the mapping annotations back to the system for better results. The demonstration showcases these features via a stand-alone Web application with user friendly interfaces.
Zhiyuan Qi, Ziheng Zhang, Jiaoyan Chen, Xi Chen, Yefeng Zheng
5
Python
6/29/2021 Neural Combinatory Constituency Parsing
We propose two fast neural combinatory models for constituency parsing: binary and multi-branching. Our models decompose the bottom-up parsing process into 1) classification of tags, labels, and binary orientations or chunks and 2) vector composition based on the computed orientations or chunks. These models have theoretical sub-quadratic complexity and empirical linear complexity. The binary model achieves an F1 score of 92.54 on Penn Treebank, speeding at 1327.2 sents/sec. Both the models with XLNet provide near state-of-the-art accuracies for English. Syntactic branching tendency and headedness of a language are observed during the training and inference processes for Penn Treebank, Chinese Treebank, and Keyaki Treebank (Japanese).
Zhousi Chen, Longtu Zhang, Aizhan Imankulova, Mamoru Komachi
5
Python
6/29/2021 Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment Classification
Lifelong learning capabilities are crucial for sentiment classifiers to process continuous streams of opinioned information on the Web. However, performing lifelong learning is non-trivial for deep neural networks as continually training of incrementally available information inevitably results in catastrophic forgetting or interference. In this paper, we propose a novel iterative network pruning with uncertainty regularization method for lifelong sentiment classification (IPRLS), which leverages the principles of network pruning and weight regularization. By performing network pruning with uncertainty regularization in an iterative manner, IPRLS can adapta single BERT model to work with continuously arriving data from multiple domains while avoiding catastrophic forgetting and interference. Specifically, we leverage an iterative pruning method to remove redundant parameters in large deep networks so that the freed-up space can then be employed to learn new tasks, tackling the catastrophic forgetting problem. Instead of keeping the old-tasks fixed when learning new tasks, we also use an uncertainty regularization based on the Bayesian online learning framework to constrain the update of old tasks weights in BERT, which enables positive backward transfer, i.e. learning new tasks improves performance on past tasks while protecting old knowledge from being lost. In addition, we propose a task-specific low-dimensional residual function in parallel to each layer of BERT, which makes IPRLS less prone to losing the knowledge saved in the base BERT network when learning a new task. Extensive experiments on 16 popular review corpora demonstrate that the proposed IPRLS method sig-nificantly outperforms the strong baselines for lifelong sentiment classification. For reproducibility, we submit the code and data at:this https URL.
Binzong Geng, Min Yang, Fajie Yuan, Shupeng Wang, Xiang Ao, Ruifeng Xu
3
6/29/2021 From Discourse to Narrative: Knowledge Projection for Event Relation Extraction
Current event-centric knowledge graphs highly rely on explicit connectives to mine relations between events. Unfortunately, due to the sparsity of connectives, these methods severely undermine the coverage of EventKGs. The lack of high-quality labelled corpora further exacerbates that problem. In this paper, we propose a knowledge projection paradigm for event relation extraction: projecting discourse knowledge to narratives by exploiting the commonalities between them. Specifically, we propose Multi-tier Knowledge Projection Network (MKPNet), which can leverage multi-tier discourse knowledge effectively for event relation extraction. In this way, the labelled data requirement is significantly reduced, and implicit event relations can be effectively extracted. Intrinsic experimental results show that MKPNet achieves the new state-of-the-art performance, and extrinsic experimental results verify the value of the extracted event relations.
Jialong Tang, Hongyu Lin, Meng Liao, Yaojie Lu, Xianpei Han, Le Sun, Weijian Xie, Jin Xu
3
Python
6/29/2021 A Self-supervised Method for Entity Alignment
Entity alignment, aiming to identify equivalent entities across different knowledge graphs (KGs), is a fundamental problem for constructing large-scale KGs. Over the course of its development, supervision has been considered necessary for accurate alignments. Inspired by the recent progress of self-supervised learning, we explore the extent to which we can get rid of supervision for entity alignment. Existing supervised methods for this task focus on pulling each pair of positive (labeled) entities close to each other. However, our analysis suggests that the learning of entity alignment can actually benefit more from pushing sampled (unlabeled) negatives far away than pulling positive aligned pairs close. We present SelfKG by leveraging this discovery to design a contrastive learning strategy across two KGs. Extensive experiments on benchmark datasets demonstrate that SelfKG without supervision can match or achieve comparable results with state-of-the-art supervised baselines. The performance of SelfKG demonstrates self-supervised learning offers great potential for entity alignment in KGs.
Xiao Liu, Haoyun Hong, Xinghao Wang, Zeyi Chen, Evgeny Kharlamov, Yuxiao Dong, Jie Tang
6
Python
6/29/2021 Biomedical Entity Linking with Contrastive Context Matching
We introduce BioCoM, a contrastive learning framework for biomedical entity linking that uses only two resources: a small-sized dictionary and a large number of raw biomedical articles. Specifically, we build the training instances from raw PubMed articles by dictionary matching and use them to train a context-aware entity linking model with contrastive learning. We predict the normalized biomedical entity at inference time through a nearest-neighbor search. Results found that BioCoM substantially outperforms state-of-the-art models, especially in low-resource settings, by effectively using the context of the entities.
Shogo Ujiie, Hayate Iso, Eiji Aramaki
3
Python
6/29/2021 Learn to Resolve Conversational Dependency: A Consistency Training Framework for Conversational Question Answering
One of the main challenges in conversational question answering (CQA) is to resolve the conversational dependency, such as anaphora and ellipsis. However, existing approaches do not explicitly train QA models on how to resolve the dependency, and thus these models are limited in understanding human dialogues. In this paper, we propose a novel framework, ExCorD (Explicit guidance on how to resolve Conversational Dependency) to enhance the abilities of QA models in comprehending conversational context. ExCorD first generates self-contained questions that can be understood without the conversation history, then trains a QA model with the pairs of original and self-contained questions using a consistency-based regularizer. In our experiments, we demonstrate that ExCorD significantly improves the QA models' performance by up to 1.2 F1 on QuAC, and 5.2 F1 on CANARD, while addressing the limitations of the existing approaches.
Gangwoo Kim, Hyunjae Kim, Jungsoo Park, Jaewoo Kang
5
6/29/2021 Continuity of Topic, Interaction, and Query: Learning to Quote in Online Conversations
Quotations are crucial for successful explanations and persuasions in interpersonal communications. However, finding what to quote in a conversation is challenging for both humans and machines. This work studies automatic quotation generation in an online conversation and explores how language consistency affects whether a quotation fits the given context. Here, we capture the contextual consistency of a quotation in terms of latent topics, interactions with the dialogue history, and coherence to the query turn's existing content. Further, an encoder-decoder neural framework is employed to continue the context with a quotation via language generation. Experiment results on two large-scale datasets in English and Chinese demonstrate that our quotation generation model outperforms the state-of-the-art models. Further analysis shows that topic, interaction, and query consistency are all helpful to learn how to quote in online conversations.
Lingzhi Wang, Jing Li, Xingshan Zeng, Haisong Zhang, Kam-Fai Wong
2
6/29/2021 A Neural Edge-Editing Approach for Document-Level Relation Graph Extraction
In this paper, we propose a novel edge-editing approach to extract relation information from a document. We treat the relations in a document as a relation graph among entities in this approach. The relation graph is iteratively constructed by editing edges of an initial graph, which might be a graph extracted by another system or an empty graph. The way to edit edges is to classify them in a close-first manner using the document and temporally-constructed graph information; each edge is represented with a document context information by a pretrained transformer model and a graph context information by a graph convolutional neural network model. We evaluate our approach on the task to extract material synthesis procedures from materials science texts. The experimental results show the effectiveness of our approach in editing the graphs initialized by our in-house rule-based system and empty graphs.
Kohei Makino, Makoto Miwa, Yutaka Sasaki
3
Python
6/29/2021 Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument Relations
Event extraction is a fundamental task for natural language processing. Finding the roles of event arguments like event participants is essential for event extraction. However, doing so for real-life event descriptions is challenging because an argument's role often varies in different contexts. While the relationship and interactions between multiple arguments are useful for settling the argument roles, such information is largely ignored by existing approaches. This paper presents a better approach for event extraction by explicitly utilizing the relationships of event arguments. We achieve this through a carefully designed task-oriented dialogue system. To model the argument relation, we employ reinforcement learning and incremental learning to extract multiple arguments via a multi-turned, iterative process. Our approach leverages knowledge of the already extracted arguments of the same sentence to determine the role of arguments that would be difficult to decide individually. It then uses the newly obtained information to improve the decisions of previously extracted arguments. This two-way feedback process allows us to exploit the argument relations to effectively settle argument roles, leading to better sentence understanding and event extraction. Experimental results show that our approach consistently outperforms seven state-of-the-art event extraction methods for the classification of events and argument role and argument identification.
Qian Li, Hao Peng, Jianxin Li, Yuanxing Ning, Lihong Wang, Philip S. Yu, Zheng Wang
2
Python
6/29/2021 Sample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology Problems
Neural models excel at extracting statistical patterns from large amounts of data, but struggle to learn patterns or reason about language from only a few examples. In this paper, we ask: Can we learn explicit rules that generalize well from only a few examples? We explore this question using program synthesis. We develop a synthesis model to learn phonology rules as programs in a domain-specific language. We test the ability of our models to generalize from few training examples using our new dataset of problems from the Linguistics Olympiad, a challenging set of tasks that require strong linguistic reasoning ability. In addition to being highly sample-efficient, our approach generates human-readable programs, and allows control over the generalizability of the learnt programs.
Saujas Vaduguru, Aalok Sathe, Monojit Choudhury, Dipti Misra Sharma
2
Python
6/29/2021 Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generation
Advanced large-scale neural language models have led to significant success in many language generation tasks. However, the most commonly used training objective, Maximum Likelihood Estimation (MLE), has been shown problematic, where the trained model prefers using dull and repetitive phrases. In this work, we introduce ScaleGrad, a modification straight to the gradient of the loss function, to remedy the degeneration issue of the standard MLE objective. By directly maneuvering the gradient information, ScaleGrad makes the model learn to use novel tokens. Empirical results show the effectiveness of our method not only in open-ended generation, but also in directed generation tasks. With the simplicity in architecture, our method can serve as a general training objective that is applicable to most of the neural text generation tasks.
Xiang Lin, Simeng Han, Shafiq Joty
2
6/29/2021 GenSF: Simultaneous Adaptation of Generative Pre-trained Models and Slot Filling
In transfer learning, it is imperative to achieve strong alignment between a pre-trained model and a downstream task. Prior work has done this by proposing task-specific pre-training objectives, which sacrifices the inherent scalability of the transfer learning paradigm. We instead achieve strong alignment by simultaneously modifying both the pre-trained model and the formulation of the downstream task, which is more efficient and preserves the scalability of transfer learning. We present GenSF (Generative Slot Filling), which leverages a generative pre-trained open-domain dialog model for slot filling. GenSF (1) adapts the pre-trained model by incorporating inductive biases about the task and (2) adapts the downstream task by reformulating slot filling to better leverage the pre-trained model's capabilities. GenSF achieves state-of-the-art results on two slot filling datasets with strong gains in few-shot and zero-shot settings. We achieve a 9 F1 score improvement in zero-shot slot filling. This highlights the value of strong alignment between the pre-trained model and the downstream task.
Shikib Mehri, Maxine Eskenazi
2
Python
6/29/2021 Incorporating External POS Tagger for Punctuation Restoration
Punctuation restoration is an important post-processing step in automatic speech recognition. Among other kinds of external information, part-of-speech (POS) taggers provide informative tags, suggesting each input token's syntactic role, which has been shown to be beneficial for the punctuation restoration task. In this work, we incorporate an external POS tagger and fuse its predicted labels into the existing language model to provide syntactic information. Besides, we propose sequence boundary sampling (SBS) to learn punctuation positions more efficiently as a sequence tagging task. Experimental results show that our methods can consistently obtain performance gains and achieve a new state-of-the-art on the common IWSLT benchmark. Further ablation studies illustrate that both large pre-trained language models and the external POS tagger take essential parts to improve the model's performance.
Ning Shi, Wei Wang, Boxin Wang, Jinfeng Li, Xiangyu Liu, Zhouhan Lin
2
Python
6/29/2021 Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution
Recent studies show that neural natural language processing (NLP) models are vulnerable to backdoor attacks. Injected with backdoors, models perform normally on benign examples but produce attacker-specified predictions when the backdoor is activated, presenting serious security threats to real-world applications. Since existing textual backdoor attacks pay little attention to the invisibility of backdoors, they can be easily detected and blocked. In this work, we present invisible backdoors that are activated by a learnable combination of word substitution. We show that NLP models can be injected with backdoors that lead to a nearly 100% attack success rate, whereas being highly invisible to existing defense strategies and even human inspections. The results raise a serious alarm to the security of NLP models, which requires further research to be resolved. All the data and code of this paper are released at this https URL.
Fanchao Qi, Yuan Yao, Sophia Xu, Zhiyuan Liu, Maosong Sun
4
Python
6/29/2021 How Should Agents Ask Questions For Situated Learning? An Annotated Dialogue Corpus
Intelligent agents that are confronted with novel concepts in situated environments will need to ask their human teammates questions to learn about the physical world. To better understand this problem, we need data about asking questions in situated task-based interactions. To this end, we present the Human-Robot Dialogue Learning (HuRDL) Corpus - a novel dialogue corpus collected in an online interactive virtual environment in which human participants play the role of a robot performing a collaborative tool-organization task. We describe the corpus data and a corresponding annotation scheme to offer insight into the form and content of questions that humans ask to facilitate learning in a situated environment. We provide the corpus as an empirically-grounded resource for improving question generation in situated intelligent agents.
Felix Gervits, Antonio Roque, Gordon Briggs, Matthias Scheutz, Matthew Marge
2
6/29/2021 Mitigating Biases in Toxic Language Detection through Invariant Rationalization
Automatic detection of toxic language plays an essential role in protecting social media users, especially minority groups, from verbal abuse. However, biases toward some attributes, including gender, race, and dialect, exist in most training datasets for toxicity detection. The biases make the learned models unfair and can even exacerbate the marginalization of people. Considering that current debiasing methods for general natural language understanding tasks cannot effectively mitigate the biases in the toxicity detectors, we propose to use invariant rationalization (InvRat), a game-theoretic framework consisting of a rationale generator and a predictor, to rule out the spurious correlation of certain syntactic patterns (e.g., identity mentions, dialect) to toxicity labels. We empirically show that our method yields lower false positive rate in both lexical and dialectal attributes than previous debiasing methods.
Yung-Sung Chuang, Mingye Gao, Hongyin Luo, James Glass, Hung-yi Lee, Yun-Nung Chen, Shang-Wen Li
2
Python
6/29/2021 Unsupervised Topic Segmentation of Meetings with BERT Embeddings
Topic segmentation of meetings is the task of dividing multi-person meeting transcripts into topic blocks. Supervised approaches to the problem have proven intractable due to the difficulties in collecting and accurately annotating large datasets. In this paper we show how previous unsupervised topic segmentation methods can be improved using pre-trained neural architectures. We introduce an unsupervised approach based on BERT embeddings that achieves a 15.5% reduction in error rate over existing unsupervised approaches applied to two popular datasets for meeting transcripts.
Alessandro Solbiati, Kevin Heffernan, Georgios Damaskinos, Shivani Poddar, Shubham Modi, Jacques Cali
3
Python
6/29/2021 How well do you know your summarization datasets?
State-of-the-art summarization systems are trained and evaluated on massive datasets scraped from the web. Despite their prevalence, we know very little about the underlying characteristics (data noise, summarization complexity, etc.) of these datasets, and how these affect system performance and the reliability of automatic metrics like ROUGE. In this study, we manually analyze 600 samples from three popular summarization datasets. Our study is driven by a six-class typology which captures different noise types (missing facts, entities) and degrees of summarization difficulty (extractive, abstractive). We follow with a thorough analysis of 27 state-of-the-art summarization models and 5 popular metrics, and report our key insights: (1) Datasets have distinct data quality and complexity distributions, which can be traced back to their collection process. (2) The performance of models and reliability of metrics is dependent on sample complexity. (3) Faithful summaries often receive low scores because of the poor diversity of references. We release the code, annotated data and model outputs.
Priyam Tejaswin, Dhruv Naik, Pengfei Liu
1
Jupyter Notebook
6/29/2021 Transformers for Headline Selection for Russian News Clusters
In this paper, we explore various multilingual and Russian pre-trained transformer-based models for the Dialogue Evaluation 2021 shared task on headline selection. Our experiments show that the combined approach is superior to individual multilingual and monolingual models. We present an analysis of a number of ways to obtain sentence embeddings and learn a ranking model on top of them. We achieve the result of 87.28% and 86.60% accuracy for the public and private test sets respectively.
Pavel Voropaev, Olga Sopilnyak
1
Python
6/29/2021 Context-Aware Legal Citation Recommendation using Deep Learning
Lawyers and judges spend a large amount of time researching the proper legal authority to cite while drafting decisions. In this paper, we develop a citation recommendation tool that can help improve efficiency in the process of opinion drafting. We train four types of machine learning models, including a citation-list based method (collaborative filtering) and three context-based methods (text similarity, BiLSTM and RoBERTa classifiers). Our experiments show that leveraging local textual context improves recommendation, and that deep neural models achieve decent performance. We show that non-deep text-based methods benefit from access to structured case metadata, but deep models only benefit from such access when predicting from context of insufficient length. We also find that, even after extensive training, RoBERTa does not outperform a recurrent neural model, despite its benefits of pretraining. Our behavior analysis of the RoBERTa model further shows that predictive performance is stable across time and citation classes.
Zihan Huang, Charles Low, Mengqiu Teng, Hongyi Zhang, Daniel E. Ho, Mark S. Krass, Matthias Grabmair
2
6/29/2021 Direction is what you need: Improving Word Embedding Compression in Large Language Models
The adoption of Transformer-based models in natural language processing (NLP) has led to great success using a massive number of parameters. However, due to deployment constraints in edge devices, there has been a rising interest in the compression of these models to improve their inference time and memory footprint. This paper presents a novel loss objective to compress token embeddings in the Transformer-based models by leveraging an AutoEncoder architecture. More specifically, we emphasize the importance of the direction of compressed embeddings with respect to original uncompressed embeddings. The proposed method is task-agnostic and does not require further language modeling pre-training. Our method significantly outperforms the commonly used SVD-based matrix-factorization approach in terms of initial language model Perplexity. Moreover, we evaluate our proposed approach over SQuAD v1.1 dataset and several downstream tasks from the GLUE benchmark, where we also outperform the baseline in most scenarios. Our code is public.
Klaudia Balazy, Mohammadreza Banaei, Remi Lebret, Jacek Tabor, Karl Aberer
1
Python
6/29/2021 Cascaded Span Extraction and Response Generation for Document-Grounded Dialog
This paper summarizes our entries to both subtasks of the first DialDoc shared task which focuses on the agent response prediction task in goal-oriented document-grounded dialogs. The task is split into two subtasks: predicting a span in a document that grounds an agent turn and generating an agent response based on a dialog and grounding document. In the first subtask, we restrict the set of valid spans to the ones defined in the dataset, use a biaffine classifier to model spans, and finally use an ensemble of different models. For the second subtask, we use a cascaded model which grounds the response prediction on the predicted span instead of the full document. With these approaches, we obtain significant improvements in both subtasks compared to the baseline.
Nico Daheim, David Thulke, Christian Dugast, Hermann Ney
1
6/29/2021 MathBERT: A Pre-trained Language Model for General NLP Tasks in Mathematics Education
Due to the transfer learning nature of BERT model, researchers have achieved better performance than base BERT by further pre-training the original BERT on a huge domain-specific corpus. Due to the special nature of mathematical texts which often contain math equations and symbols, the original BERT model pre-trained on general English context will not fit Natural Language Processing (NLP) tasks in mathematical education well. Therefore, we propose MathBERT, a BERT pre-trained on large mathematical corpus including pre-k to graduate level mathematical content to tackle math-specific tasks. In addition, We generate a customized mathematical vocabulary to pre-train with MathBERT and compare the performance to the MathBERT pre-trained with the original BERT vocabulary. We select three important tasks in mathematical education such as knowledge component, auto-grading, and knowledge tracing prediction to evaluate the performance of MathBERT. Our experiments show that MathBERT outperforms the base BERT by 2-9\% margin. In some cases, MathBERT pre-trained with mathematical vocabulary is better than MathBERT trained with original this http URL our best knowledge, MathBERT is the first pre-trained model for general purpose mathematics education tasks.
Jia Tracy Shen, Michiharu Yamashita, Ethan Prihar, Neil Heffernan, Xintao Wu, Dongwon Lee
1
Python
6/29/2021 Do Acoustic Word Embeddings Capture Phonological Similarity? An Empirical Study
Several variants of deep neural networks have been successfully employed for building parametric models that project variable-duration spoken word segments onto fixed-size vector representations, or acoustic word embeddings (AWEs). However, it remains unclear to what degree we can rely on the distance in the emerging AWE space as an estimate of word-form similarity. In this paper, we ask: does the distance in the acoustic embedding space correlate with phonological dissimilarity? To answer this question, we empirically investigate the performance of supervised approaches for AWEs with different neural architectures and learning objectives. We train AWE models in controlled settings for two languages (German and Czech) and evaluate the embeddings on two tasks: word discrimination and phonological similarity. Our experiments show that (1) the distance in the embedding space in the best cases only moderately correlates with phonological distance, and (2) improving the performance on the word discrimination task does not necessarily yield models that better reflect word phonological similarity. Our findings highlight the necessity to rethink the current intrinsic evaluations for AWEs.
Badr M. Abdullah, Marius Mosbach, Iuliia Zaitova, Bernd Mobius, Dietrich Klakow
1
Python
6/29/2021 Modeling Profanity and Hate Speech in Social Media with Semantic Subspaces
Hate speech and profanity detection suffer from data sparsity, especially for languages other than English, due to the subjective nature of the tasks and the resulting annotation incompatibility of existing corpora. In this study, we identify profane subspaces in word and sentence representations and explore their generalization capability on a variety of similar and distant target tasks in a zero-shot setting. This is done monolingually (German) and cross-lingually to closely-related (English), distantly-related (French) and non-related (Arabic) tasks. We observe that, on both similar and distant target tasks and across all languages, the subspace-based representations transfer more effectively than standard BERT representations in the zero-shot setting, with improvements between F1 +10.9 and F1 +42.9 over the baselines across all tested monolingual and cross-lingual scenarios.
Vanessa Hahn, Dana Ruiter, Thomas Kleinbauer, Dietrich Klakow
1
Python
6/29/2021 X-FACT: A New Benchmark Dataset for Multilingual Fact Checking
In this work, we introduce X-FACT: the largest publicly available multilingual dataset for factual verification of naturally existing real-world claims. The dataset contains short statements in 25 languages and is labeled for veracity by expert fact-checkers. The dataset includes a multilingual evaluation benchmark that measures both out-of-domain generalization, and zero-shot capabilities of the multilingual models. Using state-of-the-art multilingual transformer-based models, we develop several automated fact-checking models that, along with textual claims, make use of additional metadata and evidence from news stories retrieved using a search engine. Empirically, our best model attains an F-score of around 40%, suggesting that our dataset is a challenging benchmark for evaluation of multilingual fact-checking models.
Ashim Gupta, Vivek Srikumar
2
Python
6/29/2021 OKGIT: Open Knowledge Graph Link Prediction with Implicit Types
Open Knowledge Graphs (OpenKG) refer to a set of (head noun phrase, relation phrase, tail noun phrase) triples such as (tesla, return to, new york) extracted from a corpus using OpenIE tools. While OpenKGs are easy to bootstrap for a domain, they are very sparse and far from being directly usable in an end task. Therefore, the task of predicting new facts, i.e., link prediction, becomes an important step while using these graphs in downstream tasks such as text comprehension, question answering, and web search query recommendation. Learning embeddings for OpenKGs is one approach for link prediction that has received some attention lately. However, on careful examination, we found that current OpenKG link prediction algorithms often predict noun phrases (NPs) with incompatible types for given noun and relation phrases. We address this problem in this work and propose OKGIT that improves OpenKG link prediction using novel type compatibility score and type regularization. With extensive experiments on multiple datasets, we show that the proposed method achieves state-of-the-art performance while producing type compatible NPs in the link prediction task.
Chandrahas, Partha Pratim Talukdar
0
6/29/2021 Understanding the Dynamics between Vaping and Cannabis Legalization Using Twitter Opinions
Cannabis legalization has been welcomed by many U.S. states but its role in escalation from tobacco e-cigarette use to cannabis vaping is unclear. Meanwhile, cannabis vaping has been associated with new lung diseases and rising adolescent use. To understand the impact of cannabis legalization on escalation, we design an observational study to estimate the causal effect of recreational cannabis legalization on the development of pro-cannabis attitude for e-cigarette users. We collect and analyze Twitter data which contains opinions about cannabis and JUUL, a very popular e-cigarette brand. We use weakly supervised learning for personal tweet filtering and classification for stance detection. We discover that recreational cannabis legalization policy has an effect on increased development of pro-cannabis attitudes for users already in favor of e-cigarettes.
Shishir Adhikari, Akshay Uppal, Robin Mermelstein, Tanya Berger-Wolf, Elena Zheleva
0
6/29/2021 A Condense-then-Select Strategy for Text Summarization
Select-then-compress is a popular hybrid, framework for text summarization due to its high efficiency. This framework first selects salient sentences and then independently condenses each of the selected sentences into a concise version. However, compressing sentences separately ignores the context information of the document, and is therefore prone to delete salient information. To address this limitation, we propose a novel condense-then-select framework for text summarization. Our framework first concurrently condenses each document sentence. Original document sentences and their compressed versions then become the candidates for extraction. Finally, an extractor utilizes the context information of the document to select candidates and assembles them into a summary. If salient information is deleted during condensing, the extractor can select an original sentence to retain the information. Thus, our framework helps to avoid the loss of salient information, while preserving the high efficiency of sentence-level compression. Experiment results on the CNN/DailyMail, DUC-2002, and Pubmed datasets demonstrate that our framework outperforms the select-then-compress framework and other strong baselines.
Hou Pong Chan, Irwin King
0
Python
6/29/2021 Towards Understanding and Mitigating Social Biases in Language Models
As machine learning methods are deployed in real-world settings such as healthcare, legal systems, and social science, it is crucial to recognize how they shape social biases and stereotypes in these sensitive decision-making processes. Among such real-world deployments are large-scale pretrained language models (LMs) that can be potentially dangerous in manifesting undesirable representational biases - harmful biases resulting from stereotyping that propagate negative generalizations involving gender, race, religion, and other social constructs. As a step towards improving the fairness of LMs, we carefully define several sources of representational biases before proposing new benchmarks and metrics to measure them. With these tools, we propose steps towards mitigating social biases during text generation. Our empirical results and human evaluation demonstrate effectiveness in mitigating bias while retaining crucial contextual information for high-fidelity text generation, thereby pushing forward the performance-fairness Pareto frontier.
Paul Pu Liang, Chiyu Wu, Louis-Philippe Morency, Ruslan Salakhutdinov
13
6/29/2021 A Brief Study on the Effects of Training Generative Dialogue Models with a Semantic loss
Neural models trained for next utterance generation in dialogue task learn to mimic the n-gram sequences in the training set with training objectives like negative log-likelihood (NLL) or cross-entropy. Such commonly used training objectives do not foster generating alternate responses to a context. But, the effects of minimizing an alternate training objective that fosters a model to generate alternate response and score it on semantic similarity has not been well studied. We hypothesize that a language generation model can improve on its diversity by learning to generate alternate text during training and minimizing a semantic loss as an auxiliary objective. We explore this idea on two different sized data sets on the task of next utterance generation in goal oriented dialogues. We make two observations (1) minimizing a semantic objective improved diversity in responses in the smaller data set (Frames) but only as-good-as minimizing the NLL in the larger data set (MultiWoZ) (2) large language model embeddings can be more useful as a semantic loss objective than as initialization for token embeddings.
Prasanna Parthasarathi, Mohamed Abdelsalam, Joelle Pineau, Sarath Chandar
0
Python