Table of Contents

• Frontmatter [doi]
• AligNART: Non-autoregressive Neural Machine Translation by Jointly Learning to Estimate Alignment and TranslateJongyoon Song, Sungwon Kim, Sungroh Yoon. 1-14 [doi]
• Zero-Shot Cross-Lingual Transfer of Neural Machine Translation with Multilingual Pretrained EncodersGuanhua Chen, Shuming Ma, Yun Chen, Li Dong 0004, Dongdong Zhang 0001, Jia Pan, Wenping Wang, Furu Wei. 15-26 [doi]
• ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual CorporaXuan Ouyang, Shuohuan Wang, Chao Pang, Yu Sun, Hao Tian, Hua Wu 0003, Haifeng Wang 0001. 27-38 [doi]
• Cross Attention Augmented Transducer Networks for Simultaneous TranslationDan Liu, Mengge Du, Xiaoxi Li, Ya Li, Enhong Chen. 39-55 [doi]
• Translating Headers of Tabular Data: A Pilot Study of Schema TranslationKunrui Zhu, Yan Gao 0002, Jiaqi Guo, Jian-Guang Lou. 56-66 [doi]
• Towards Making the Most of Dialogue Characteristics for Neural Chat TranslationYunlong Liang, Chulun Zhou, Fandong Meng, Jinan Xu, Yufeng Chen 0005, Jinsong Su, Jie Zhou 0016. 67-79 [doi]
• Low-Resource Dialogue Summarization with Domain-Agnostic Multi-Source PretrainingYicheng Zou, Bolin Zhu, Xingwu Hu, Tao Gui, Qi Zhang 0001. 80-91 [doi]
• Controllable Neural Dialogue Summarization with Personal Named Entity PlanningZhengyuan Liu, Nancy Chen. 92-106 [doi]
• Fine-grained Factual Consistency Assessment for Abstractive Summarization ModelsSen Zhang, Jianwei Niu, Chuyuan Wei. 107-116 [doi]
• Decision-Focused SummarizationChao-Chun Hsu, Chenhao Tan. 117-132 [doi]
• Multiplex Graph Neural Network for Extractive Text SummarizationBaoyu Jing, Zeyu You, Tao Yang, Wei Fan 0001, Hanghang Tong. 133-139 [doi]
• A Thorough Evaluation of Task-Specific Pretraining for SummarizationSascha Rothe, Joshua Maynez, Shashi Narayan. 140-145 [doi]
• HETFORMER: Heterogeneous Transformer with Sparse Attention for Long-Text Extractive SummarizationYe Liu 0006, Jianguo Zhang, Yao Wan, Congying Xia, Lifang He 0001, Philip S. Yu. 146-154 [doi]
• Unsupervised Keyphrase Extraction by Jointly Modeling Local and Global ContextXinnian Liang, Shuangzhi Wu, Mu Li 0001, Zhoujun Li. 155-164 [doi]
• Distantly Supervised Relation Extraction using Multi-Layer Revision Network and Confidence-based Multi-Instance LearningXiangyu Lin, Tianyi Liu, Weijia Jia 0001, Zhiguo Gong. 165-174 [doi]
• Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact VerificationQi Shi, Yu Zhang, Qingyu Yin, Ting Liu. 175-184 [doi]
• A Partition Filter Network for Joint Entity and Relation ExtractionZhiheng Yan, Chong Zhang, JinLan Fu, Qi Zhang, Zhongyu Wei. 185-197 [doi]
• TEBNER: Domain Specific Named Entity Recognition with Type Expanded Boundary-aware NetworkZheng Fang 0002, Yanan Cao, Tai Li, Ruipeng Jia, Fang Fang 0009, Yanmin Shang, Yuhai Lu. 198-207 [doi]
• Beta Distribution Guided Aspect-aware Graph for Aspect Category Sentiment Analysis with Affective KnowledgeBin Liang, Hang Su, Rongdi Yin, Lin Gui 0003, Min Yang, Qin Zhao, Xiaoqi Yu, Ruifeng Xu. 208-218 [doi]
• DILBERT: Customized Pre-Training for Domain Adaptation with Category Shift, with an Application to Aspect ExtractionEntony Lekhtman, Yftah Ziser, Roi Reichart. 219-230 [doi]
• Improving Multimodal fusion via Mutual Dependency MaximisationPierre Colombo, Emile Chapuis, Matthieu Labeau, Chloé Clavel. 231-245 [doi]
• Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-TrainingZhengyan Li, Yicheng Zou, Chong Zhang, Qi Zhang, Zhongyu Wei. 246-256 [doi]
• Progressive Self-Training with Discriminator for Aspect Term ExtractionQianlong Wang, Zhiyuan Wen, Qin Zhao, Min Yang, Ruifeng Xu. 257-268 [doi]
• Reinforced Counterfactual Data Augmentation for Dual Sentiment ClassificationHao Chen, Rui Xia, Jianfei Yu. 269-278 [doi]
• Idiosyncratic but not Arbitrary: Learning Idiolects in Online Registers Reveals Distinctive yet Consistent Individual StylesJian Zhu, David Jurgens. 279-297 [doi]
• Narrative Theory for Computational Narrative UnderstandingAndrew Piper, Richard Jean So, David Bamman. 298-311 [doi]
• (Mis)alignment Between Stance Expressed in Social Media Data and Public Opinion SurveysKenneth Joseph, Sarah Shugars, Ryan J. Gallagher, Jon Green, Alexi Quintana Mathé, Zijian An, David Lazer. 312-324 [doi]
• How Does Counterfactually Augmented Data Impact Models for Social Computing Constructs?Indira Sen, Mattia Samory, Fabian Flöck, Claudia Wagner, Isabelle Augenstein. 325-344 [doi]
• Latent Hatred: A Benchmark for Understanding Implicit Hate SpeechMai ElSherief, Caleb Ziems, David Muchlinski, Vaishnavi Anupindi, Jordyn Seybolt, Munmun De Choudhury, Diyi Yang. 345-363 [doi]
• Distilling Linguistic Context for Language Model CompressionGeondo Park, Gyeongman Kim, Eunho Yang. 364-378 [doi]
• Dynamic Knowledge Distillation for Pre-trained Language ModelsLei Li, Yankai Lin, Shuhuai Ren, Peng Li, Jie Zhou, Xu Sun 0001. 379-389 [doi]
• Few-Shot Text Generation with Natural Language InstructionsTimo Schick, Hinrich Schütze. 390-402 [doi]
• SOM-NCSCM : An Efficient Neural Chinese Sentence Compression Model Enhanced with Self-Organizing MapKangli Zi, Shi Wang, Yu Liu, Jicun Li, Yanan Cao, Cungen Cao. 403-415 [doi]
• Efficient Multi-Task Auxiliary Learning: Selecting Auxiliary Data by Feature SimilarityPo-Nien Kung, Sheng-Siang Yin, Yi-Cheng Chen, Tse-Hsuan Yang, Yun-Nung Chen. 416-428 [doi]
• GOLD: Improving Out-of-Scope Detection in Dialogues using Data AugmentationDerek Chen, Zhou Yu. 429-442 [doi]
• Graph Based Network with Contextualized Representations of Turns in DialogueBongseok Lee, Yong Suk Choi. 443-455 [doi]
• Automatically Exposing Problems with Neural Dialog ModelsDian Yu, Kenji Sagae. 456-470 [doi]
• Event Coreference Data (Almost) for Free: Mining Hyperlinks from Online NewsMichael Bugert, Iryna Gurevych. 471-491 [doi]
• Inducing Stereotypical Character Roles from Plot StructureLabiba Jahan, Rahul Mittal, Mark A. Finlayson. 492-497 [doi]
• Multitask Semi-Supervised Learning for Class-Imbalanced Discourse ClassificationAlexander Spangher, Jonathan May, Sz-Rung Shiang, Lingjia Deng. 498-517 [doi]
• Low Frequency Names Exhibit Bias and Overfitting in Contextualizing Language ModelsRobert Wolfe, Aylin Caliskan. 518-532 [doi]
• Mitigating Language-Dependent Ethnic Bias in BERTJaimeen Ahn, Alice Oh. 533-549 [doi]
• Adversarial Scrubbing of Demographic Information for Text ClassificationSomnath Basu Roy Chowdhury, Sayan Ghosh, Yiyuan Li, Junier Oliva, Shashank Srivastava, Snigdha Chaturvedi. 550-562 [doi]
• Open-domain clarification question generation without question examplesJulia White, Gabriel Poesia, Robert X. D. Hawkins, Dorsa Sadigh, Noah Goodman. 563-570 [doi]
• Improving Sequence-to-Sequence Pre-training via Sequence Span RewritingWangchunshu Zhou, Tao Ge, Canwen Xu, Ke Xu 0001, Furu Wei. 571-582 [doi]
• Coarse2Fine: Fine-grained Text Classification on Coarsely-grained Annotated DataDheeraj Mekala, Varun Gangal, Jingbo Shang. 583-594 [doi]
• Text2Mol: Cross-Modal Molecule Retrieval with Natural Language QueriesCarl Edwards, ChengXiang Zhai, Heng Ji. 595-607 [doi]
• Classification of hierarchical text using geometric deep learning: the case of clinical trials corpusSohrab Ferdowsi, Nikolay Borissov, Julien Knafou, Poorya Amini, Douglas Teodoro. 608-618 [doi]
• The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of TransformersRóbert Csordás, Kazuki Irie, Jürgen Schmidhuber. 619-634 [doi]
• Artificial Text Detection via Examining the Topology of Attention MapsLaida Kushnareva, Daniil Cherniavskii, Vladislav Mikhailov, Ekaterina Artemova, Serguei Barannikov, Alexander Bernstein, Irina Piontkovskaya, Dmitri Piontkovski, Evgeny Burnaev. 635-649 [doi]
• Active Learning by Acquiring Contrastive ExamplesKaterina Margatina, Giorgos Vernikos, Loïc Barrault, Nikolaos Aletras. 650-663 [doi]
• Conditional Poisson Stochastic BeamsClara Meister, Afra Amini, Tim Vieira, Ryan Cotterell. 664-681 [doi]
• Building Adaptive Acceptability Classifiers for Neural NLGSoumya Batra, Shashank Jain, Peyman Heidari, Ankit Arun, Catharine Youngs, Xintong Li, Pinar Donmez, Shawn Mei, Shiunzu Kuo, Vikas Bhardwaj, Anuj Kumar, Michael White 0001. 682-697 [doi]
• Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their ConsequencesDenis Emelin, Ronan Le Bras, Jena D. Hwang, Maxwell Forbes, Yejin Choi. 698-718 [doi]
• Truth-Conditional Captions for Time Series DataHarsh Jhamtani, Taylor Berg-Kirkpatrick. 719-733 [doi]
• Injecting Entity Types into Entity-Guided Text GenerationXiangyu Dong, Wenhao Yu 0002, Chenguang Zhu, Meng Jiang 0001. 734-741 [doi]
• Smelting Gold and Silver for Improved Multilingual AMR-to-Text GenerationLeonardo F. R. Ribeiro, Jonas Pfeiffer, Yue Zhang, Iryna Gurevych. 742-750 [doi]
• Learning Compact Metrics for MTAmy Pu, Hyung Won Chung, Ankur P. Parikh, Sebastian Gehrmann, Thibault Sellam. 751-762 [doi]
• The Impact of Positional Encodings on Multilingual CompressionVinit Ravishankar, Anders Søgaard. 763-777 [doi]
• Disentangling Representations of Text by Masking TransformersXiongyi Zhang, Jan-Willem van de Meent, Byron C. Wallace. 778-791 [doi]
• Exploring the Role of BERT Token Representations to Explain Sentence Probing ResultsHosein Mohebbi, Ali Modarressi, Mohammad Taher Pilehvar. 792-806 [doi]
• Do Long-Range Language Models Actually Use Long-Range Context?Simeng Sun, Kalpesh Krishna, Andrew Mattarella-Micke, Mohit Iyyer. 807-822 [doi]
• The World of an Octopus: How Reporting Bias Influences a Language Model's Perception of ColorCory Paik, Stéphane Aroca-Ouellette, Alessandro Roncone, Katharina Kann. 823-835 [doi]
• SELFEXPLAIN: A Self-Explaining Architecture for Neural Text ClassifiersDheeraj Rajagopal, Vidhisha Balachandran, Eduard H. Hovy, Yulia Tsvetkov. 836-850 [doi]
• Memory and Knowledge Augmented Language Models for Inferring Salience in Long-Form StoriesDavid Wilmot, Frank Keller. 851-865 [doi]
• Semantic Novelty Detection in Natural Language DescriptionsNianzu Ma, Alexander Politowicz, Sahisnu Mazumder, Jiahua Chen, Bing Liu 0001, Eric Robertson 0001, Scott Grigsby. 866-882 [doi]
• Jump-Starting Item Parameters for Adaptive Language TestsArya D. McCarthy, Kevin P. Yancey, Geoffrey T. LaFlair, Jesse Egbert, Manqian Liao, Burr Settles. 883-899 [doi]
• Voice Query Auto CompletionRaphael Tang, Karun Kumar, Kendra Chalkley, Ji Xin, LiMing Zhang, Wenyan Li, Gefei Yang, Yajie Mao, Junho Shin, Geoffrey Craig Murray, Jimmy Lin. 900-906 [doi]
• CoPHE: A Count-Preserving Hierarchical Evaluation Metric in Large-Scale Multi-Label Text ClassificationMatús Falis, Hang Dong, Alexandra Birch, Beatrice Alex. 907-912 [doi]
• Learning Universal Authorship RepresentationsRafael A. Rivera Soto, Olivia Elizabeth Miano, Juanita Ordonez, Barry Y. Chen, Aleem Khan, Marcus Bishop, Nicholas Andrews. 913-919 [doi]
• Predicting emergent linguistic compositions through time: Syntactic frame extension via multimodal chainingLei Yu, Yang Xu 0023. 920-931 [doi]
• Frequency Effects on Syntactic Rule Learning in TransformersJason Wei, Dan Garrette, Tal Linzen, Ellie Pavlick. 932-948 [doi]
• A surprisal-duration trade-off across and within the world's languagesTiago Pimentel, Clara Meister, Elizabeth Salesky, Simone Teufel, Damián E. Blasi, Ryan Cotterell. 949-962 [doi]
• Revisiting the Uniform Information Density HypothesisClara Meister, Tiago Pimentel, Patrick Haller, Lena Jäger, Ryan Cotterell, Roger Levy. 963-980 [doi]
• Condenser: a Pre-training Architecture for Dense RetrievalLuyu Gao, Jamie Callan. 981-993 [doi]
• Monitoring geometrical properties of word embeddings for detecting the emergence of new topicsClément Christophe, Julien Velcin, Jairo Cugliari, Manel Boumghar, Philippe Suignard. 994-1003 [doi]
• Contextualized Query Embeddings for Conversational SearchSheng-Chieh Lin, Jheng-Hong Yang, Jimmy Lin. 1004-1015 [doi]
• Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text RetrievalKyoungrok Jang, Junmo Kang, Giwon Hong, Sung-Hyon Myaeng, Joohee Park, Taewon Yoon, Hee-Cheol Seo. 1016-1029 [doi]
• IR like a SIR: Sense-enhanced Information Retrieval for Multiple LanguagesRexhina Blloshmi, Tommaso Pasini, Niccolò Campolungo, Somnath Banerjee, Roberto Navigli, Gabriella Pasi. 1030-1041 [doi]
• Neural Attention-Aware Hierarchical Topic ModelYuan Jin, He Zhao, Ming Liu, Lan Du, Wray L. Buntine. 1042-1052 [doi]
• Relational World Knowledge Representation in Contextual Language Models: A ReviewTara Safavi, Danai Koutra. 1053-1067 [doi]
• Certified Robustness to Programmable Transformations in LSTMsYuhao Zhang, Aws Albarghouthi, Loris D'Antoni. 1068-1083 [doi]
• ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language ModelsPierre L. Dognin, Inkit Padhi, Igor Melnyk, Payel Das. 1084-1099 [doi]
• Contrastive Out-of-Distribution Detection for Pretrained TransformersWenxuan Zhou, Fangyu Liu 0001, Muhao Chen. 1100-1111 [doi]
• MindCraft: Theory of Mind Modeling for Situated Dialogue in Collaborative TasksCristian-Paul Bara, Sky CH-Wang, Joyce Chai. 1112-1125 [doi]
• Detecting Speaker Personas from Conversational TextsJia-Chen Gu, Zhen-Hua Ling, Yu Wu, Quan Liu, Zhigang Chen, Xiaodan Zhu. 1126-1136 [doi]
• Cross-lingual Intermediate Fine-tuning improves Dialogue State TrackingNikita Moghe, Mark Steedman, Alexandra Birch. 1137-1150 [doi]
• ConvFiT: Conversational Fine-Tuning of Pretrained Language ModelsIvan Vulic, Pei-hao Su, Samuel Coope, Daniela Gerz, Pawel Budzianowski, Iñigo Casanueva, Nikola Mrksic, Tsung-Hsien Wen. 1151-1168 [doi]
• We've had this conversation before: A Novel Approach to Measuring Dialog SimilarityOfer Lavi, Ella Rabinovich, Segev Shlomov, David Boaz, Inbal Ronen, Ateret Anaby-Tavor. 1169-1177 [doi]
• Towards Incremental Transformers: An Empirical Analysis of Transformer Models for Incremental NLUPatrick Kahardipraja, Brielen Madureira, David Schlangen. 1178-1189 [doi]
• Feedback Attribution for Counterfactual Bandit Learning in Multi-Domain Spoken Language UnderstandingTobias Falke, Patrick Lehnen. 1190-1198 [doi]
• Label Verbalization and Entailment for Effective Zero and Few-Shot Relation ExtractionOscar Sainz, Oier Lopez de Lacalle, Gorka Labaka, Ander Barrena, Eneko Agirre. 1199-1212 [doi]
• Extend, don't rebuild: Phrasing conditional graph modification as autoregressive sequence labellingLeon Weber, Jannes Münchmeyer, Samuele Garda, Ulf Leser. 1213-1224 [doi]
• Zero-Shot Information Extraction as a Unified Text-to-Triple TranslationChenguang Wang, Xiao Liu, Zui Chen, Haoyun Hong, Jie Tang 0001, Dawn Song. 1225-1238 [doi]
• Learning Logic Rules for Document-Level Relation ExtractionDongyu Ru, Changzhi Sun, JiangTao Feng, Lin Qiu, Hao Zhou 0012, Weinan Zhang 0001, Yong Yu 0001, Lei Li 0005. 1239-1250 [doi]
• A Large-Scale Dataset for Empathetic Response GenerationAnuradha Welivita, Yubo Xie, Pearl Pu. 1251-1264 [doi]
• The Perils of Using Mechanical Turk to Evaluate Open-Ended Text GenerationMarzena Karpinska, Nader Akoury, Mohit Iyyer. 1265-1285 [doi]
• Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled CorpusJesse Dodge, Maarten Sap, Ana Marasovic, William Agnew, Gabriel Ilharco, Dirk Groeneveld, Margaret Mitchell, Matt Gardner 0001. 1286-1305 [doi]
• AfroMT: Pretraining Strategies and Reproducible Benchmarks for Translation of 8 African LanguagesMachel Reid, Junjie Hu 0001, Graham Neubig, Yutaka Matsuo. 1306-1320 [doi]
• Evaluating the Evaluation Metrics for Style Transfer: A Case Study in Multilingual Formality TransferEleftheria Briakou, Sweta Agrawal, Joel R. Tetreault, Marine Carpuat. 1321-1336 [doi]
• MS-Mentions: Consistently Annotating Entity Mentions in Materials Science Procedural TextTim O'Gorman, Zach Jensen, Sheshera Mysore, Kevin Huang 0004, Rubayyat Mahbub, Elsa Olivetti, Andrew McCallum. 1337-1352 [doi]
• Understanding Politics via Contextualized Discourse ProcessingRajkumar Pujari, Dan Goldwasser. 1353-1367 [doi]
• Conundrums in Event Coreference Resolution: Making Sense of the State of the ArtJing Lu, Vincent Ng. 1368-1380 [doi]
• Weakly supervised discourse segmentation for multiparty oral conversationsLila Gravellier, Julie Hunter, Philippe Muller, Thomas Pellegrini, Isabelle Ferrané. 1381-1392 [doi]
• Narrative Embedding: Re-Contextualization Through AttentionSean Wilner, Daniel Woolridge, Madeleine Glick. 1393-1405 [doi]
• Focus on what matters: Applying Discourse Coherence Theory to Cross Document CoreferenceWilliam Held, Dan Iter, Dan Jurafsky. 1406-1417 [doi]
• Salience-Aware Event Chain Modeling for Narrative UnderstandingXiyang Zhang, Muhao Chen, Jonathan May. 1418-1428 [doi]
• Asking It All: Generating Contextualized Questions for any Semantic RoleValentina Pyatkin, Paul Roit, Julian Michael, Yoav Goldberg, Reut Tsarfaty, Ido Dagan. 1429-1441 [doi]
• Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence EncodersFangyu Liu 0001, Ivan Vulic, Anna Korhonen, Nigel Collier. 1442-1459 [doi]
• RuleBERT: Teaching Soft Rules to Pre-Trained Language ModelsMohammed Saeed 0002, Naser Ahmadi, Preslav Nakov, Paolo Papotti. 1460-1476 [doi]
• Stepmothers are mean and academics are pretentious: What do pretrained language models learn about you?Rochelle Choenni, Ekaterina Shutova, Robert van Rooij. 1477-1491 [doi]
• ConSeC: Word Sense Disambiguation as Continuous Sense ComprehensionEdoardo Barba, Luigi Procopio, Roberto Navigli. 1492-1503 [doi]
• Shortcutted Commonsense: Data Spuriousness in Deep Learning of Commonsense ReasoningRuben Branco, António Branco, João António Rodrigues, João Ricardo Silva. 1504-1521 [doi]
• When differential privacy meets NLP: The devil is in the detailIvan Habernal. 1522-1528 [doi]
• Achieving Model Robustness through Discrete Adversarial TrainingMaor Ivgi, Jonathan Berant. 1529-1544 [doi]
• Debiasing Methods in Natural Language Understanding Make Bias More AccessibleMichael Mendelson, Yonatan Belinkov. 1545-1557 [doi]
• Evaluating the Robustness of Neural Language Models to Input PerturbationsMilad Moradi, Matthias Samwald. 1558-1570 [doi]
• How much pretraining data do language models need to learn syntax?Laura Pérez-Mayos, Miguel Ballesteros, Leo Wanner. 1571-1582 [doi]
• Sorting through the noise: Testing robustness of information processing in pre-trained language modelsLalchand Pandia, Allyson Ettinger. 1583-1596 [doi]
• Contrastive Explanations for Model InterpretabilityAlon Jacovi, Swabha Swayamdipta, Shauli Ravfogel, Yanai Elazar, Yejin Choi, Yoav Goldberg. 1597-1611 [doi]
• On the Transferability of Adversarial Attacks against Neural Text ClassifierLiping Yuan, Xiaoqing Zheng, Yi Zhou, Cho-Jui Hsieh, Kai-Wei Chang. 1612-1625 [doi]
• Conditional probing: measuring usable information beyond a baselineJohn Hewitt, Kawin Ethayarajh, Percy Liang, Christopher D. Manning. 1626-1639 [doi]
• GFST: Gender-Filtered Self-Training for More Accurate Gender in TranslationPrafulla Kumar Choubey, Anna Currey, Prashant Mathur, Georgiana Dinu. 1640-1654 [doi]
• "Wikily" Supervised Neural Translation Tailored to Cross-Lingual TasksMohammad Sadegh Rasooli, Chris Callison-Burch, Derry Tanti Wijaya. 1655-1670 [doi]
• mT6: Multilingual Pretrained Text-to-Text Transformer with Translation PairsZewen Chi, Li Dong 0004, Shuming Ma, Shaohan Huang, Saksham Singhal, Xian-Ling Mao, Heyan Huang, Xia Song, Furu Wei. 1671-1683 [doi]
• Improving Zero-Shot Cross-Lingual Transfer Learning via Robust TrainingKuan-Hao Huang, Wasi Uddin Ahmad, Nanyun Peng, Kai-Wei Chang. 1684-1697 [doi]
• Speechformer: Reducing Information Loss in Direct Speech TranslationSara Papi, Marco Gaido, Matteo Negri, Marco Turchi. 1698-1706 [doi]
• Is "moby dick" a Whale or a Bird? Named Entities and Terminology in Speech TranslationMarco Gaido, Susana Rodríguez, Matteo Negri, Luisa Bentivogli, Marco Turchi. 1707-1716 [doi]
• HintedBT: Augmenting Back-Translation with Quality and Transliteration HintsSahana Ramnath, Melvin Johnson, Abhirut Gupta, Aravindan Raghuveer. 1717-1733 [doi]
• Translation-based Supervision for Policy Generation in Simultaneous Neural Machine TranslationAshkan Alinejad, Hassan S. Shavarani, Anoop Sarkar. 1734-1744 [doi]
• Nearest Neighbour Few-Shot Learning for Cross-lingual ClassificationM. Saiful Bari, Batool Haider, Saab Mansour. 1745-1753 [doi]
• Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine TranslationMozhdeh Gheini, Xiang Ren 0001, Jonathan May. 1754-1765 [doi]
• Effects of Parameter Norm Growth During Transformer Training: Inductive Bias from Gradient DescentWilliam Merrill, Vivek Ramanujan, Yoav Goldberg, Roy Schwartz 0001, Noah A. Smith. 1766-1781 [doi]
• Foreseeing the Benefits of Incidental SupervisionHangfeng He, Mingyuan Zhang, Qiang Ning, Dan Roth. 1782-1800 [doi]
• Competency Problems: On Finding and Removing Artifacts in Language DataMatt Gardner 0001, William Merrill, Jesse Dodge, Matthew E. Peters, Alexis Ross, Sameer Singh 0001, Noah A. Smith. 1801-1813 [doi]
• Knowledge-Aware Meta-learning for Low-Resource Text ClassificationHuaxiu Yao, Yingxin Wu, Maruan Al-Shedivat, Eric P. Xing. 1814-1821 [doi]
• Sentence Bottleneck Autoencoders from Transformer Language ModelsIvan Montero, Nikolaos Pappas 0002, Noah A. Smith. 1822-1831 [doi]
• Efficient Contrastive Learning via Novel Data Augmentation and Curriculum LearningSeonghyeon Ye, Jiseon Kim, Alice Oh. 1832-1838 [doi]
• CR-Walker: Tree-Structured Graph Reasoning and Dialog Acts for Conversational RecommendationWenchang Ma, Ryuichi Takanobu, Minlie Huang. 1839-1851 [doi]
• DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document ContextualizationZeqiu Wu, Bo-Ru Lu, Hannaneh Hajishirzi, Mari Ostendorf. 1852-1863 [doi]
• Iconary: A Pictionary-Based Game for Testing Multimodal Communication with Drawings and TextChristopher Clark, Jordi Salvador, Dustin Schwenk, Derrick Bonafilia, Mark Yatskar, Eric Kolve, Alvaro Herrasti, Jonghyun Choi, Sachin Mehta, Sam Skjonsberg, Carissa Schoenick, Aaron Sarnat, Hannaneh Hajishirzi, Aniruddha Kembhavi, Oren Etzioni, Ali Farhadi. 1864-1886 [doi]
• Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog SystemsFei Mi, Wanhao Zhou, Lingjing Kong 0001, Fengyu Cai, Minlie Huang, Boi Faltings. 1887-1898 [doi]
• Contextual Rephrase Detection for Reducing Friction in Dialogue SystemsZhuoyi Wang, Saurabh Gupta, Jie Hao, Xing Fan, Dingcheng Li, Alexander Hanbo Li, Chenlei Guo. 1899-1905 [doi]
• Few-Shot Intent Detection via Contrastive Pre-Training and Fine-TuningJianguo Zhang, Trung Bui, Seunghyun Yoon 0002, Xiang Chen, Zhiwei Liu, Congying Xia, Quan Hung Tran, Walter Chang, Philip S. Yu. 1906-1912 [doi]
• "It doesn't look good for a date": Transforming Critiques into Preferences for Conversational Recommendation SystemsVictor S. Bursztyn, Jennifer Healey, Nedim Lipka, Eunyee Koh, Doug Downey, Larry Birnbaum. 1913-1918 [doi]
• AttentionRank: Unsupervised Keyphrase Extraction using Self and Cross AttentionsHaoran Ding, Xiao Luo. 1919-1928 [doi]
• Unsupervised Relation Extraction: A Variational Autoencoder ApproachChenhan Yuan, Hoda Eldardiry. 1929-1938 [doi]
• Robust Retrieval Augmented Generation for Zero-shot Slot FillingMichael R. Glass, Gaetano Rossiello, Md. Faisal Mahbub Chowdhury, Alfio Gliozzo. 1939-1949 [doi]
• Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information ExtractionMahsa Yarmohammadi, Shijie Wu, Marc Marone, Haoran Xu, Seth Ebner, Guanghui Qin, Yunmo Chen, JiaLiang Guo, Craig Harman, Kenton Murray, Aaron Steven White, Mark Dredze, Benjamin Van Durme. 1950-1967 [doi]
• Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language TechnologiesSunipa Dev, Masoud Monajatipoor, Anaelia Ovalle, Arjun Subramonian, Jeff M. Phillips, Kai-Wei Chang. 1968-1994 [doi]
• Are Gender-Neutral Queries Really Gender-Neutral? Mitigating Gender Bias in Image SearchJialu Wang, Yang Liu, Xin Wang. 1995-2008 [doi]
• Style Pooling: Automatic Text Style Obfuscation for Improved Classification FairnessFatemehsadat Mireshghallah, Taylor Berg-Kirkpatrick. 2009-2022 [doi]
• Modeling Disclosive Transparency in NLP Application DescriptionsMichael Saxon, Sharon Levy, Xinyi Wang, Alon Albalak, William Yang Wang. 2023-2037 [doi]
• Reconstruction Attack on Instance Encoding for Language UnderstandingShangyu Xie, Yuan Hong. 2038-2044 [doi]
• Fairness-aware Class Imbalanced LearningShivashankar Subramanian, Afshin Rahimi 0001, Timothy Baldwin, Trevor Cohn, Lea Frermann. 2045-2051 [doi]
• CRYPTOGRU: Low Latency Privacy-Preserving Text Analysis With GRUBo Feng, Qian Lou, Lei Jiang 0001, Geoffrey C. Fox. 2052-2057 [doi]
• Local Word Discovery for Interactive TranscriptionWilliam Lane, Steven Bird. 2058-2067 [doi]
• Segment, Mask, and Predict: Augmenting Chinese Word Segmentation with Self-SupervisionMieradilijiang Maimaiti, Yang Liu, Yuanhang Zheng, Gang Chen, Kaiyu Huang, Ji Zhang, Huanbo Luan, Maosong Sun. 2068-2077 [doi]
• Minimal Supervision for Morphological InflectionOmer Goldman, Reut Tsarfaty. 2078-2088 [doi]
• Fast WordPiece TokenizationXinying Song, Alex Salcianu, Yang Song, Dave Dopson, Denny Zhou. 2089-2103 [doi]
• You should evaluate your language model on marginal likelihood over tokenisationsKris Cao, Laura Rimell. 2104-2114 [doi]
• Broaden the Vision: Geo-Diverse Visual Commonsense ReasoningDa Yin, Liunian Harold Li, Ziniu Hu, Nanyun Peng, Kai-Wei Chang. 2115-2129 [doi]
• Reference-Centric Models for Grounded Collaborative DialogueDaniel Fried, Justin T. Chiu, Dan Klein. 2130-2147 [doi]
• CrossVQA: Scalably Generating Benchmarks for Systematically Testing VQA GeneralizationArjun R. Akula, Soravit Changpinyo, Boqing Gong, Piyush Sharma, Song Chun Zhu, Radu Soricut. 2148-2166 [doi]
• Visual Goal-Step Inference using wikiHowYue Yang, Artemis Panagopoulou, Qing Lyu, Li Zhang 0039, Mark Yatskar, Chris Callison-Burch. 2167-2179 [doi]
• Systematic Generalization on gSCAN: What is Nearly Solved and What is Next?Linlu Qiu, Hexiang Hu, Bowen Zhang 0002, Peter Shaw, Fei Sha. 2180-2188 [doi]
• Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language ModelsTaichi Iki, Akiko Aizawa. 2189-2196 [doi]
• Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path GroundingNouha Dziri, Andrea Madotto, Osmar Zaïane, Avishek Joey Bose. 2197-2214 [doi]
• Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue SystemsYicheng Zou, Zhihua Liu, Xingwu Hu, Qi Zhang. 2215-2226 [doi]
• Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion CausesHyunwoo Kim, Byeongchang Kim 0002, Gunhee Kim. 2227-2240 [doi]
• Generation and Extraction Combined Dialogue State Tracking with Hierarchical Ontology IntegrationXinmeng Li, Qian Li, Wansen Wu, Quanjun Yin. 2241-2249 [doi]
• CoLV: A Collaborative Latent Variable Model for Knowledge-Grounded Dialogue GenerationHaolan Zhan, Lei Shen, Hongshen Chen, Hainan Zhang. 2250-2261 [doi]
• A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue GenerationShilei Liu, Xiaofeng Zhao, Bochao Li, Feiliang Ren, Longhui Zhang, Shujuan Yin. 2262-2272 [doi]
• Intention Reasoning Network for Multi-Domain End-to-end Task-Oriented DialogueZhiyuan Ma, Jianjun Li, Zezheng Zhang, Guohui Li, Yongjing Cheng. 2273-2285 [doi]
• More is Better: Enhancing Open-Domain Dialogue Generation via Multi-Source Heterogeneous KnowledgeSixing Wu, Ying Li, Minghui Wang, Dawei Zhang, Yang Zhou 0001, Zhonghai Wu. 2286-2300 [doi]
• Domain-Lifelong Learning for Dialogue State Tracking via Knowledge Preservation NetworksQingbin Liu, Pengfei Cao, Cao Liu, Jiansong Chen, Xunliang Cai, Fan Yang, Shizhu He, Kang Liu 0001, Jun Zhao 0001. 2301-2311 [doi]
• CSAGN: Conversational Structure Aware Graph Network for Conversational Semantic Role LabelingHan Wu, Kun Xu, Linqi Song. 2312-2317 [doi]
• Different Strokes for Different Folks: Investigating Appropriate Further Pre-training Approaches for Diverse Dialogue TasksYao Qiu, Jinchao Zhang, Jie Zhou. 2318-2327 [doi]
• Knowledge Enhanced Fine-Tuning for Better Handling Unseen Entities in Dialogue GenerationLeyang Cui, Yu Wu 0012, Shujie Liu 0001, Yue Zhang 0004. 2328-2337 [doi]
• An Evaluation Dataset and Strategy for Building Robust Multi-turn Response Selection ModelKijong Han, Seojin Lee, Dong-Hun Lee. 2338-2344 [doi]
• Unsupervised Conversation Disentanglement through Co-TrainingHui Liu 0033, Zhan Shi, Xiaodan Zhu. 2345-2356 [doi]
• Don't be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue SystemLibo Qin, Tianbao Xie, Shijue Huang, Qiguang Chen, Xiao Xu, Wanxiang Che. 2357-2367 [doi]
• Transferable Persona-Grounded Dialogues via Grounded Minimal EditsChen Henry Wu, Yinhe Zheng, Xiaoxi Mao, Minlie Huang. 2368-2382 [doi]
• EARL: Informative Knowledge-Grounded Conversation Generation with Entity-Agnostic Representation LearningHao Zhou, Minlie Huang, Yong Liu, Wei Chen, Xiaoyan Zhu 0001. 2383-2395 [doi]
• DialogueCSE: Dialogue-based Contrastive Learning of Sentence EmbeddingsChe Liu, Rui Wang, Jinghua Liu, Jian Sun, Fei Huang, Luo Si. 2396-2406 [doi]
• Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise OrderingsShaopeng Lai, Ante Wang, Fandong Meng, Jie Zhou, Yubin Ge, Jiali Zeng, Junfeng Yao, Degen Huang, Jinsong Su. 2407-2417 [doi]
• Not Just Classification: Recognizing Implicit Discourse Relation on Joint Modeling of Classification and GenerationFeng Jiang, Yaxin Fan, Xiaomin Chu, Peifeng Li, Qiaoming Zhu. 2418-2431 [doi]
• A Language Model-based Generative Classifier for Sentence-level Discourse ParsingYing Zhang, Hidetaka Kamigaito, Manabu Okumura. 2432-2446 [doi]
• Multimodal Phased Transformer for Sentiment AnalysisJunyan Cheng, Iordanis Fostiropoulos, Barry W. Boehm, Mohammad Soleymani 0001. 2447-2458 [doi]
• Hierarchical Multi-label Text Classification with Horizontal and Vertical Category CorrelationsLinli Xu, Sijie Teng, Ruoyu Zhao, Junliang Guo, Chi Xiao, Deqiang Jiang, Bo Ren. 2459-2468 [doi]
• RankNAS: Efficient Neural Architecture Search by Pairwise RankingChi Hu, Chenglong Wang, Xiangnan Ma, Xia Meng, Yinqiao Li, Tong Xiao, Jingbo Zhu, Changliang Li. 2469-2480 [doi]
• FLiText: A Faster and Lighter Semi-Supervised Text Classification with Convolution NetworksChen Liu, Mengchao Zhang, Zhibing Fu, Panpan Hou, Yu Li. 2481-2491 [doi]
• Evaluating Debiasing Techniques for Intersectional BiasesShivashankar Subramanian, Xudong Han, Timothy Baldwin, Trevor Cohn, Lea Frermann. 2492-2498 [doi]
• Definition Modelling for Appropriate SpecificityHan Huang, Tomoyuki Kajiwara, Yuki Arase. 2499-2509 [doi]
• Transductive Learning for Unsupervised Text Style TransferFei Xiao, Liang Pang, Yanyan Lan, Yan Wang, Huawei Shen, Xueqi Cheng. 2510-2521 [doi]
• Integrating Semantic Scenario and Word Relations for Abstractive Sentence SummarizationYong Guan, Shaoru Guo, Ru Li, Xiaoli Li, Hu Zhang. 2522-2529 [doi]
• Coupling Context Modeling with Zero Pronoun Recovering for Document-Level Natural Language GenerationXin Tan, Longyin Zhang, Guodong Zhou. 2530-2540 [doi]
• Adaptive Bridge between Training and Inference for Dialogue GenerationHaoran Xu, Hainan Zhang, Yanyan Zou, Hongshen Chen, Zhuoye Ding, Yanyan Lan. 2541-2550 [doi]
• ConRPG: Paraphrase Generation using Contexts as RegularizerYuxian Meng, Xiang Ao 0001, Qing He 0003, Xiaofei Sun, Qinghong Han, Fei Wu, Chun Fan, Jiwei Li. 2551-2562 [doi]
• Building the Directed Semantic Graph for Coherent Long Text GenerationZiao Wang, Xiaofeng Zhang, Hongwei Du. 2563-2572 [doi]
• Iterative GNN-based Decoder for Question GenerationZichu Fei, Qi Zhang, Yaqian Zhou. 2573-2582 [doi]
• Asking Questions Like Educational Experts: Automatically Generating Question-Answer Pairs on Real-World Examination DataFanyi Qu, Xin Jia, Yunfang Wu. 2583-2593 [doi]
• Syntactically-Informed Unsupervised Paraphrasing with Non-Parallel DataErguang Yang, Mingtong Liu, Deyi Xiong, Yujie Zhang, Yao Meng, Changjian Hu, Jinan Xu, Yufeng Chen 0005. 2594-2604 [doi]
• Exploring Task Difficulty for Few-Shot Relation ExtractionJiale Han, Bo Cheng 0001, Wei Lu. 2605-2616 [doi]
• MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity RepresentationsXinyin Ma, Yong Jiang, Nguyen Bach, Tao Wang, Zhongqiang Huang, Fei Huang, Weiming Lu 0001. 2617-2624 [doi]
• Treasures Outside Contexts: Improving Event Detection via Global StatisticsRui Li 0044, Wenlin Zhao, Cheng Yang, Sen Su. 2625-2635 [doi]
• Uncertain Local-to-Global Networks for Document-Level Event Factuality IdentificationPengfei Cao, Yubo Chen 0001, YuQing Yang, Kang Liu 0001, Jun Zhao 0001. 2636-2645 [doi]
• A Novel Global Feature-Oriented Relational Triple Extraction Model based on Table FillingFeiliang Ren, Longhui Zhang, Shujuan Yin, Xiaofeng Zhao, Shilei Liu, Bochao Li, Yaduo Liu. 2646-2656 [doi]
• Structure-Augmented Keyphrase GenerationJihyuk Kim, Myeongho Jeong, Seungtaek Choi, Seung-won Hwang. 2657-2667 [doi]
• An Empirical Study on Multiple Information Sources for Zero-Shot Fine-Grained Entity TypingYi Chen 0019, Haiyun Jiang, Lemao Liu, Shuming Shi 0001, Chuang Fan, Min Yang, Ruifeng Xu. 2668-2678 [doi]
• DyLex: Incorporating Dynamic Lexicons into BERT for Sequence LabelingBaojun Wang, Zhao Zhang, Kun Xu, Guang-Yuan Hao, Yuyang Zhang, Lifeng Shang, Linlin Li, Xiao Chen, Xin Jiang, Qun Liu 0001. 2679-2693 [doi]
• MapRE: An Effective Semantic Mapping Approach for Low-resource Relation ExtractionManqing Dong, Chunguang Pan, Zhipeng Luo. 2694-2704 [doi]
• Heterogeneous Graph Neural Networks for Keyphrase GenerationJiacheng Ye, Ruijian Cai, Tao Gui, Qi Zhang. 2705-2715 [doi]
• Machine Reading Comprehension as Data Augmentation: A Case Study on Implicit Event Argument ExtractionJian Liu, Yufeng Chen 0005, Jinan Xu. 2716-2725 [doi]
• Importance Estimation from Multiple Perspectives for Keyphrase ExtractionMingYang Song, Liping Jing, Lin Xiao. 2726-2736 [doi]
• Gradient Imitation Reinforcement Learning for Low Resource Relation ExtractionXuming Hu, Chenwei Zhang, YaWen Yang, Xiaohe Li, Li Lin, Lijie Wen, Philip S. Yu. 2737-2746 [doi]
• Low-resource Taxonomy Enrichment with Pretrained Language ModelsKunihiro Takeoka, Kosuke Akimoto, Masafumi Oyamada. 2747-2758 [doi]
• Entity Relation Extraction as Dependency Parsing in Visually Rich DocumentsYue Zhang 0004, Bo Zhang, Rui Wang, Junjie Cao, Chen Li, Zuyi Bao. 2759-2768 [doi]
• Synchronous Dual Network with Cross-Type Attention for Joint Entity and Relation ExtractionHui Wu, Xiaodong Shi. 2769-2779 [doi]
• Less is More: Pretrain a Strong Siamese Encoder for Dense Text Retrieval Using a Weak DecoderShuqi Lu, Di He, Chenyan Xiong, Guolin Ke, Waleed Malik, Zhicheng Dou, Paul Bennett, Tie-Yan Liu, Arnold Overwijk. 2780-2791 [doi]
• TransPrompt: Towards an Automatic Transferable Prompting Framework for Few-shot Text ClassificationChengyu Wang 0001, Jianing Wang, Minghui Qiu, Jun Huang, Ming Gao 0001. 2792-2802 [doi]
• Weakly-supervised Text Classification Based on Keyword GraphLu Zhang, Jiandong Ding, Yi Xu, Yingyao Liu, Shuigeng Zhou. 2803-2813 [doi]
• Efficient-FedRec: Efficient Federated Learning Framework for Privacy-Preserving News RecommendationJingwei Yi, Fangzhao Wu, Chuhan Wu, Ruixuan Liu, Guangzhong Sun, Xing Xie 0001. 2814-2824 [doi]
• RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-rankingRuiyang Ren, Yingqi Qu, Jing Liu, Wayne Xin Zhao, Qiaoqiao She, Hua Wu, Haifeng Wang, Ji-Rong Wen. 2825-2835 [doi]
• Dealing with Typos for BERT-based Passage Retrieval and RankingShengyao Zhuang, Guido Zuccon. 2836-2842 [doi]
• From Alignment to Assignment: Frustratingly Simple Unsupervised Entity AlignmentXin Mao, Wenting Wang, Yuanbin Wu, Man Lan. 2843-2853 [doi]
• Simple and Effective Unsupervised Redundancy Elimination to Compress Dense Vectors for Passage RetrievalXueguang Ma, Minghan Li, Kai Sun, Ji Xin, Jimmy Lin. 2854-2859 [doi]
• Relation Extraction with Word Graphs from N-gramsHan Qin, Yuanhe Tian, Yan Song. 2860-2868 [doi]
• A Bayesian Framework for Information-Theoretic ProbingTiago Pimentel, Ryan Cotterell. 2869-2887 [doi]
• Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for LittleKoustuv Sinha, Robin Jia, Dieuwke Hupkes, Joelle Pineau, Adina Williams, Douwe Kiela. 2888-2913 [doi]
• What's Hidden in a One-layer Randomly Weighted Transformer?Sheng Shen, Zhewei Yao, Douwe Kiela, Kurt Keutzer, Michael W. Mahoney. 2914-2921 [doi]
• Rethinking Denoised Auto-Encoding in Language Pre-TrainingFuli Luo, Pengcheng Yang, Shicheng Li, Xuancheng Ren, Xu Sun, Songfang Huang, Fei Huang. 2922-2932 [doi]
• Lifelong Explainer for Lifelong LearnersXuelin Situ, Sameen Maruf, Ingrid Zukerman, Cécile Paris, Gholamreza Haffari. 2933-2940 [doi]
• Linguistic Dependencies and Statistical DependenceJacob Louis Hoover, Wenyu Du, Alessandro Sordoni, Timothy J. O'Donnell. 2941-2963 [doi]
• Modeling Human Sentence Processing with Left-Corner Recurrent Neural Network GrammarsRyo Yoshida, Hiroshi Noji, Yohei Oseki. 2964-2973 [doi]
• A Simple and Effective Positional Encoding for TransformersPu-Chin Chen, Henry Tsai, Srinadh Bhojanapalli, Hyung Won Chung, Yin-Wen Chang, Chun-Sung Ferng. 2974-2988 [doi]
• Explore Better Relative Position Embeddings from Encoding Perspective for Transformer ModelsAnlin Qu, Jianwei Niu 0002, Shasha Mo. 2989-2997 [doi]
• Adversarial Mixing Policy for Relaxing Locally Linear Constraints in MixupGuang Liu 0007, Yuzhao Mao, Hailong Huang, Weiguo Gao, Xuan Li. 2998-3008 [doi]
• Is this the end of the gold standard? A straightforward reference-less grammatical error correction metricMd Asadul Islam, Enrico Magnani. 3009-3015 [doi]
• Augmenting BERT-style Models with Predictive Coding to Improve Discourse-level RepresentationsVladimir Araujo, Andrés Villa, Marcelo Mendoza, Marie-Francine Moens, Alvaro Soto. 3016-3022 [doi]
• Backdoor Attacks on Pre-trained Models by Layerwise Weight PoisoningLinyang Li, Demin Song, Xiaonan Li, Jiehang Zeng, Ruotian Ma, Xipeng Qiu. 3023-3032 [doi]
• GAML-BERT: Improving BERT Early Exiting by Gradient Aligned Mutual LearningWei Zhu, Xiaoling Wang, Yuan Ni, Guotong Xie. 3033-3044 [doi]
• The Power of Scale for Parameter-Efficient Prompt TuningBrian Lester, Rami Al-Rfou, Noah Constant. 3045-3059 [doi]
• Scalable Font Reconstruction with Dual Latent ManifoldsNikita Srivatsan, Si Wu, Jonathan T. Barron, Taylor Berg-Kirkpatrick. 3060-3072 [doi]
• Neuro-Symbolic Approaches for Text-Based Policy LearningSubhajit Chaudhury, Prithviraj Sen, Masaki Ono, Daiki Kimura, Michiaki Tatsubori, Asim Munawar. 3073-3078 [doi]
• Layer-wise Model Pruning based on Mutual InformationChun Fan, Jiwei Li, Tianwei Zhang 0004, Xiang Ao 0001, Fei Wu, Yuxian Meng, Xiaofei Sun. 3079-3090 [doi]
• Hierarchical Heterogeneous Graph Representation Learning for Short Text ClassificationYaqing Wang, Song Wang, Quanming Yao, Dejing Dou. 3091-3101 [doi]
• kFolden: k-Fold Ensemble for Out-Of-Distribution DetectionXiaoya Li, Jiwei Li, Xiaofei Sun, Chun Fan, Tianwei Zhang 0004, Fei Wu, Yuxian Meng, Jun Zhang. 3102-3115 [doi]
• Frustratingly Simple Pretraining Alternatives to Masked Language ModelingAtsuki Yamaguchi, George Chrysostomou, Katerina Margatina, Nikolaos Aletras. 3116-3125 [doi]
• HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model CompressionChenhe Dong, Yaliang Li, Ying Shen, Minghui Qiu. 3126-3136 [doi]
• Searching for an Effective Defender: Benchmarking Defense against Adversarial Word SubstitutionZongyi Li, Jianhan Xu, Jiehang Zeng, Linyang Li, Xiaoqing Zheng, Qi Zhang, Kai-Wei Chang, Cho-Jui Hsieh. 3137-3147 [doi]
• Re-embedding Difficult Samples via Mutual Information Constrained Semantically Oversampling for Imbalanced Text ClassificationJiachen Tian, Shizhan Chen, Xiaowang Zhang, Zhiyong Feng 0002, Deyi Xiong, Shaojuan Wu, Chunliu Dou. 3148-3161 [doi]
• Beyond Text: Incorporating Metadata and Label Structure for Multi-Label Document Classification using Heterogeneous GraphsChenchen Ye, Linhai Zhang, Yulan He, Deyu Zhou, Jie Wu. 3162-3171 [doi]
• Natural Language Processing Meets Quantum Physics: A Survey and CategorizationSixuan Wu, Jian Li, Peng Zhang, Yue Zhang 0022. 3172-3182 [doi]
• MetaTS: Meta Teacher-Student Network for Multilingual Sequence Labeling with Minimal SupervisionZheng Li, Danqing Zhang, Tianyu Cao, Ying Wei 0001, Yiwei Song, Bing Yin. 3183-3196 [doi]
• Neural Machine Translation with Heterogeneous Topic Knowledge EmbeddingsWeixuan Wang, Wei Peng, Meng Zhang, Qun Liu. 3197-3202 [doi]
• Allocating Large Vocabulary Capacity for Cross-Lingual Language Model Pre-TrainingBo Zheng, Li Dong 0004, Shaohan Huang, Saksham Singhal, Wanxiang Che, Ting Liu 0001, Xia Song, Furu Wei. 3203-3215 [doi]
• Recurrent Attention for Neural Machine TranslationJiali Zeng, Shuangzhi Wu, Yongjing Yin, Yufan Jiang, Mu Li 0001. 3216-3225 [doi]
• Learning from Multiple Noisy Augmented Data Sets for Better Cross-Lingual Spoken Language UnderstandingYingmei Guo, Linjun Shou, Jian Pei, Ming Gong, Mingxing Xu, Zhiyong Wu 0001, Daxin Jiang. 3226-3237 [doi]
• Enlivening Redundant Heads in Multi-head Self-attention for Machine TranslationTianfu Zhang, Heyan Huang, Chong Feng, Longbing Cao. 3238-3248 [doi]
• Unsupervised Neural Machine Translation with Universal GrammarZuchao Li, Masao Utiyama, Eiichiro Sumita, Hai Zhao. 3249-3264 [doi]
• Encouraging Lexical Translation Consistency for Document-Level Neural Machine TranslationXinglin Lyu, Junhui Li, Zhengxian Gong, Min Zhang. 3265-3277 [doi]
• Improving Neural Machine Translation by Bidirectional TrainingLiang Ding, Di Wu, Dacheng Tao. 3278-3284 [doi]
• Scheduled Sampling Based on Decoding Steps for Neural Machine TranslationYijin Liu, Fandong Meng, Yufeng Chen 0005, Jinan Xu, Jie Zhou. 3285-3296 [doi]
• Learning to Rewrite for Non-Autoregressive Neural Machine TranslationXinwei Geng, Xiaocheng Feng, Bing Qin 0001. 3297-3308 [doi]
• SHAPE : Shifted Absolute Position Embedding for TransformersShun Kiyono, Sosuke Kobayashi, Jun Suzuki, Kentaro Inui. 3309-3321 [doi]
• Self-Supervised Quality Estimation for Machine TranslationYuanhang Zheng, Zhixing Tan, Meng Zhang, Mieradilijiang Maimaiti, Huanbo Luan, Maosong Sun, Qun Liu, Yang Liu. 3322-3334 [doi]
• Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data SelectionThuy-Trang Vu, Xuanli He, Dinh Q. Phung, Gholamreza Haffari. 3335-3346 [doi]
• STANKER: Stacking Network based on Level-grained Attention-masked BERT for Rumor Detection on Social MediaDongning Rao, Xin Miao, Zhihua Jiang, Ran Li. 3347-3363 [doi]
• ActiveEA: Active Learning for Neural Entity AlignmentBing Liu, Harrisen Scells, Guido Zuccon, Wen-hua, Genghong Zhao. 3364-3374 [doi]
• Cost-effective End-to-end Information Extraction for Semi-structured Document ImagesWonseok Hwang, Hyunji Lee, Jinyeong Yim, Geewook Kim, Minjoon Seo. 3375-3383 [doi]
• Improving Math Word Problems with Pre-trained Knowledge and Hierarchical ReasoningWeijiang Yu, Yingpeng Wen, Fudan Zheng, Nong Xiao. 3384-3394 [doi]
• GraphMR: Graph Neural Network for Mathematical ReasoningWeijie Feng, Binbin Liu, Dongpeng Xu 0001, Qilong Zheng, Yun Xu. 3395-3404 [doi]
• What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained TransformersBoseop Kim, Hyoungseok Kim, Sang-Woo Lee, Gichang Lee, Dong-Hyun Kwak, Dong Hyeon Jeon, Sunghyun Park 0005, Sungju Kim, Seonhoon Kim, Dongpil Seo, Heungsub Lee, Minyoung Jeong, Sungjae Lee, Minsub Kim, SukHyun Ko, Seokhun Kim, Taeyong Park, Jinuk Kim, Soyoung Kang, Na-Hyeon Ryu, Kang Min Yoo, Minsuk Chang, Soobin Suh, Sookyo In, Jinseong Park, Kyungduk Kim, Hiun Kim, Jisu Jeong, Yong Goo Yeo, DongHoon Ham, Dongju Park, Min-Young Lee, Jaewook Kang, Inho Kang, Jung-Woo Ha, Woo-Myoung Park, Nako Sung. 3405-3424 [doi]
• APIRecX: Cross-Library API Recommendation via Pre-Trained Language ModelYuning Kang, Zan Wang, Hongyu Zhang 0002, Junjie Chen 0003, Hanmo You. 3425-3436 [doi]
• GMH: A General Multi-hop Reasoning Model for KG CompletionYao Zhang, Hongru Liang, Adam Jatowt, Wenqiang Lei, Xin Wei, Ning Jiang, Zhenglu Yang. 3437-3446 [doi]
• BPM_MT: Enhanced Backchannel Prediction Model using Multi-Task LearningJin Yea Jang, San Kim, Minyoung Jung, Saim Shin, Gahgene Gweon. 3447-3452 [doi]
• Graphine: A Dataset for Graph-aware Terminology Definition GenerationZequn Liu, Shukai Wang, Yiyang Gu, Ruiyi Zhang, Ming Zhang 0004, Sheng Wang. 3453-3463 [doi]
• Leveraging Order-Free Tag Relations for Context-Aware RecommendationJunmo Kang, Jeonghwan Kim, Suwon Shin, Sung-Hyon Myaeng. 3464-3476 [doi]
• End-to-End Conversational Search for Online Shopping with Utterance TransferLiqiang Xiao, Jun Ma, Xin Luna Dong, Pascual Martínez-Gómez, Nasser Zalmout, Wei Chen, Tong Zhao, Hao He 0007, Yaohui Jin. 3477-3486 [doi]
• Self-Supervised Curriculum Learning for Spelling Error CorrectionZifa Gan, Hongfei Xu, Hongying Zan. 3487-3494 [doi]
• Fix-Filter-Fix: Intuitively Connect Any Models for Effective Bug FixingHaiwen Hong, Jingfeng Zhang, Yin Zhang, Yao Wan, Yulei Sui. 3495-3504 [doi]
• Neuro-Symbolic Reinforcement Learning with First-Order LogicDaiki Kimura, Masaki Ono, Subhajit Chaudhury, Ryosuke Kohita, Akifumi Wachi, Don Joven Agravante, Michiaki Tatsubori, Asim Munawar, Alexander Gray. 3505-3511 [doi]
• Biomedical Concept Normalization by Leveraging HypernymsCheng Yan, Yuanzhe Zhang, Kang Liu 0001, Jun Zhao 0001, Yafei Shi, Shengping Liu. 3512-3517 [doi]
• Leveraging Capsule Routing to Associate Knowledge with Medical Literature HierarchicallyXin Liu, Qingcai Chen, Junying Chen, Wenxiu Zhou, Tingyu Liu, Xinlan Yang, Weihua Peng. 3518-3532 [doi]
• Label-Enhanced Hierarchical Contextualized Representation for Sequential Metaphor IdentificationShuqun Li, Liang Yang, Weidong He, ShiQi Zhang, Jingjie Zeng, Hongfei Lin. 3533-3543 [doi]
• SpellBERT: A Lightweight Pretrained Model for Chinese Spelling CheckTuo Ji, Hang Yan, Xipeng Qiu. 3544-3551 [doi]
• Automated Generation of Accurate & Fluent Medical X-ray ReportsHoang T. N. Nguyen, Dong Nie, Taivanbat Badamdorj, Yujie Liu, Yingying Zhu, Jason Truong, Li Cheng. 3552-3569 [doi]
• Enhancing Document Ranking with Task-adaptive Training and Segmented Token Recovery MechanismXingwu Sun, Yanling Cui, Hongyin Tang, Fuzheng Zhang, Beihong Jin, Shi Wang. 3570-3579 [doi]
• Abstract, Rationale, Stance: A Joint Model for Scientific Claim VerificationZhiwei Zhang, Jiyi Li, Fumiyo Fukumoto, Yanming Ye. 3580-3586 [doi]
• A Fine-Grained Domain Adaption Model for Joint Word Segmentation and POS TaggingPeijie Jiang, Dingkun Long, Yueheng Sun, Meishan Zhang, Guangwei Xu, Pengjun Xie. 3587-3598 [doi]
• Answering Open-Domain Questions of Varying Reasoning Steps from TextPeng Qi 0003, Haejun Lee, Tg Sido, Christopher D. Manning. 3599-3614 [doi]
• Adaptive Information Seeking for Open-Domain Question AnsweringYunchang Zhu, Liang Pang, Yanyan Lan, Huawei Shen, Xueqi Cheng. 3615-3626 [doi]
• Mapping probability word problems to executable representationsSimon Suster, Pieter Fivez, Pietro Totis, Angelika Kimmig, Jesse Davis, Luc De Raedt, Walter Daelemans. 3627-3640 [doi]
• Enhancing Multiple-choice Machine Reading Comprehension by Punishing Illogical InterpretationsYiming Ju, Yuanzhe Zhang, Zhixing Tian, Kang Liu 0001, Xiaohuan Cao, Wenting Zhao, Jinlong Li, Jun Zhao. 3641-3652 [doi]
• Large-Scale Relation Learning for Question Answering over Knowledge Bases with Pre-trained Language ModelsYuanmeng Yan, Rumei Li, Sirui Wang, Hongzhi Zhang, Zan Daoguang, Fuzheng Zhang, Wei Wu, Weiran Xu. 3653-3660 [doi]
• Phrase Retrieval Learns Passage Retrieval, TooJinhyuk Lee, Alexander Wettig, Danqi Chen. 3661-3672 [doi]
• Neural Natural Logic Inference for Interpretable Question AnsweringJihao Shi, Xiao Ding, Li Du, Ting Liu 0001, Bing Qin 0001. 3673-3684 [doi]
• Smoothing Dialogue States for Open Conversational Machine ReadingZhuosheng Zhang 0001, Siru Ouyang, Hai Zhao, Masao Utiyama, Eiichiro Sumita. 3685-3696 [doi]
• FinQA: A Dataset of Numerical Reasoning over Financial DataZhiYu Chen, Wenhu Chen, Charese Smiley, Sameena Shah, Iana Borova, Dylan Langdon, Reema Moussa, Matt Beane, Ting-Hao Huang, Bryan R. Routledge, William Yang Wang. 3697-3711 [doi]
• FiD-Ex: Improving Sequence-to-Sequence Models for Extractive Rationale GenerationKushal Lakhotia, Bhargavi Paranjape, Asish Ghoshal, Scott Yih, Yashar Mehdad, Srini Iyer. 3712-3727 [doi]
• RockNER: A Simple Method to Create Adversarial Examples for Evaluating the Robustness of Named Entity Recognition ModelsBill Yuchen Lin, Wenyang Gao, Jun Yan 0012, Ryan Moreno, Xiang Ren 0001. 3728-3737 [doi]
• Diagnosing the First-Order Logical Reasoning Ability Through LogicNLIJidong Tian, Yitian Li, Wenqing Chen, Liqiang Xiao, Hao He 0007, Yaohui Jin. 3738-3747 [doi]
• Constructing a Psychometric Testbed for Fair Natural Language ProcessingAhmed Abbasi, David G. Dobolyi, John P. Lalor, Richard G. Netemeyer, Kendall Smith, Yi Yang. 3748-3758 [doi]
• COUGH: A Challenge Dataset and Models for COVID-19 FAQ RetrievalXinliang Frederick Zhang, Heming Sun, Xiang Yue, Simon M. Lin, Huan Sun. 3759-3769 [doi]
• Chinese WPLC: A Chinese Dataset for Evaluating Pretrained Language Models on Word Prediction Given Long-Range ContextHuibin Ge, Chenxi Sun, Deyi Xiong, Qun Liu 0001. 3770-3778 [doi]
• WinoLogic: A Zero-Shot Logic-based Diagnostic Dataset for Winograd Schema ChallengeWeinan He, Canming Huang, Yongmei Liu, Xiaodan Zhu. 3779-3789 [doi]
• Pseudo Zero Pronoun Resolution Improves Zero Anaphora ResolutionRyuto Konno, Shun Kiyono, Yuichiroh Matsubayashi, Hiroki Ouchi, Kentaro Inui. 3790-3806 [doi]
• Aligning Cross-lingual Sentence Representations with Dual Momentum ContrastLiang Wang 0046, Wei Zhao, Jingming Liu. 3807-3815 [doi]
• Total Recall: a Customized Continual Learning Method for Neural Semantic ParsersZhuang Li, Lizhen Qu, Gholamreza Haffari. 3816-3831 [doi]
• Exophoric Pronoun Resolution in Dialogues with Topic RegularizationXintong Yu, Hongming Zhang, Yangqiu Song, Changshui Zhang, Kun Xu, Dong Yu 0001. 3832-3845 [doi]
• Context-Aware Interaction Network for Question MatchingZhe Hu, Zuohui Fu, Yu Yin, Gerard de Melo. 3846-3853 [doi]
• TEMP: Taxonomy Expansion with Dynamic Margin Loss through Taxonomy-PathsZichen Liu, Hongyuan Xu, Yanlong Wen, Ning Jiang, Haiying Wu, Xiaojie Yuan. 3854-3863 [doi]
• A Graph-Based Neural Model for End-to-End Frame Semantic ParsingZhichao Lin, Yueheng Sun, Meishan Zhang. 3864-3874 [doi]
• Virtual Data Augmentation: A Robust and General Framework for Fine-tuning Pre-trained ModelsKun Zhou, Wayne Xin Zhao, Sirui Wang, Fuzheng Zhang, Wei Wu, Ji-Rong Wen. 3875-3887 [doi]
• CATE: A Contrastive Pre-trained Model for Metaphor Detection with Semi-supervised LearningZhenxi Lin, Qianli Ma, Jiangyue Yan, Jieyu Chen. 3888-3898 [doi]
• To be Closer: Learning to Link up Aspects with OpinionsYuxiang Zhou, Lejian Liao, Yang Gao 0016, Zhanming Jie, Wei Lu 0011. 3899-3909 [doi]
• Seeking Common but Distinguishing Difference, A Joint Aspect-based Sentiment Analysis ModelHongjiang Jing, Zuchao Li, Hai Zhao, Shu Jiang. 3910-3922 [doi]
• Argument Pair Extraction with Mutual Guidance and Inter-sentence Relation GraphJianzhu Bao, Bin Liang, Jingyi Sun, Yice Zhang, Min Yang, Ruifeng Xu. 3923-3934 [doi]
• Emotion Inference in Multi-Turn Conversations with Addressee-Aware Module and Ensemble StrategyDayu Li, Xiaodan Zhu, Yang Li, Suge Wang, Deyu Li, Jian Liao, Jianxing Zheng. 3935-3941 [doi]
• Improving Federated Learning for Aspect-based Sentiment Analysis via Topic MemoriesHan Qin, Guimin Chen, Yuanhe Tian, Yan Song. 3942-3954 [doi]
• Comparative Opinion Quintuple Extraction from Product ReviewsZiheng Liu, Rui Xia, Jianfei Yu. 3955-3965 [doi]
• CTAL: Pre-training Cross-modal Transformer for Audio-and-Language RepresentationsHang Li, Wenbiao Ding, Yu Kang, Tianqiao Liu, Zhongqin Wu, Zitao Liu. 3966-3977 [doi]
• Relation-aware Video Reading Comprehension for Temporal Language GroundingJialin Gao, Xin Sun, Mengmeng Xu, Xi Zhou, Bernard Ghanem. 3978-3988 [doi]
• Mutual-Learning Improves End-to-End Speech TranslationJiawei Zhao, Wei Luo, Boxing Chen, Andrew Gilman. 3989-3994 [doi]
• Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive SummarizationTiezheng Yu, Wenliang Dai, Zihan Liu, Pascale Fung. 3995-4007 [doi]
• Natural Language Video Localization with Learnable Moment ProposalsShaoning Xiao, Long Chen, Jian Shao, Yueting Zhuang, Jun Xiao 0001. 4008-4017 [doi]
• Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous EnvironmentsSonia Raychaudhuri, Saim Wani, Shivansh Patel, Unnat Jain, Angel X. Chang. 4018-4028 [doi]
• How to leverage the multimodal EHR data for better medical prediction?Bo Yang, Lijun Wu. 4029-4038 [doi]
• Considering Nested Tree Structure in Sentence Extractive Summarization with Pre-trained TransformerJingun Kwon, Naoki Kobayashi, Hidetaka Kamigaito, Manabu Okumura. 4039-4044 [doi]
• Frame Semantic-Enhanced Sentence Modeling for Sentence-level Extractive Text SummarizationYong Guan, Shaoru Guo, Ru Li, Xiaoli Li, Hongye Tan. 4045-4052 [doi]
• CAST: Enhancing Code Summarization with Hierarchical Splitting and Reconstruction of Abstract Syntax TreesEnsheng Shi, Yanlin Wang 0001, Lun Du, Hongyu Zhang 0002, Shi Han, Dongmei Zhang, Hongbin Sun. 4053-4062 [doi]
• SgSum: Transforming Multi-document Summarization into Sub-graph SelectionMoye Chen, Wei Li, Jiachen Liu, Xinyan Xiao, Hua Wu 0003, Haifeng Wang 0001. 4063-4074 [doi]
• Event Graph based Sentence FusionRuifeng Yuan, Zili Wang, Wenjie Li. 4075-4084 [doi]
• Transformer-based Lexically Constrained Headline GenerationKosuke Yamada, Yuta Hitomi, Hideaki Tamori, Ryohei Sasano, Naoaki Okazaki, Kentaro Inui, Koichi Takeda. 4085-4090 [doi]
• Learn to Copy from the Copying History: Correlational Copy Network for Abstractive SummarizationHaoran Li 0001, Song Xu 0002, Peng Yuan 0002, Yujia Wang, Youzheng Wu, Xiaodong He 0002, Bowen Zhou. 4091-4101 [doi]
• Gradient-Based Adversarial Factual Consistency Evaluation for Abstractive SummarizationZhiyuan Zeng, Jiaze Chen, Weiran Xu, Lei Li 0005. 4102-4108 [doi]
• Word Reordering for Zero-shot Cross-lingual Structured PredictionTao Ji, Yong Jiang, Tao Wang, Zhongqiang Huang, Fei Huang, Yuanbin Wu, Xiaoling Wang. 4109-4120 [doi]
• A Unified Encoding of Structures in Transition SystemsTao Ji, Yong Jiang, Tao Wang, Zhongqiang Huang, Fei Huang, Yuanbin Wu, Xiaoling Wang. 4121-4133 [doi]
• Improving Unsupervised Question Answering via Summarization-Informed Question GenerationChenyang Lyu, Lifeng Shang, Yvette Graham, Jennifer Foster, Xin Jiang 0002, Qun Liu 0001. 4134-4148 [doi]
• TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation GraphJiaxin Shi, Shulin Cao, Lei Hou 0001, Juanzi Li, Hanwang Zhang. 4149-4158 [doi]
• Topic Transferable Table Question AnsweringSaneem A. Chemmengath, Vishwajeet Kumar, Samarth Bharadwaj, Jaydeep Sen, Mustafa Canim, Soumen Chakrabarti, Alfio Gliozzo, Karthik Sankaranarayanan. 4159-4172 [doi]
• WebSRC: A Dataset for Web-Based Structural Reading ComprehensionXingyu Chen, Zihan Zhao, Lu Chen, Jiabao Ji, Danyang Zhang, Ao Luo, Yuxuan Xiong, Kai Yu 0004. 4173-4185 [doi]
• Cryptonite: A Cryptic Crossword Benchmark for Extreme Ambiguity in LanguageAvia Efrat, Uri Shaham, Dan Kilman, Omer Levy. 4186-4192 [doi]
• End-to-End Entity Resolution and Question Answering Using Differentiable Knowledge GraphsAmir Saffari, Armin Oliya, Priyanka Sen, Tom Ayoola. 4193-4200 [doi]
• Improving Query Graph Generation for Complex Question Answering over Knowledge BaseKechen Qin, Cheng Li, Virgil Pavlu, Javed A. Aslam. 4201-4207 [doi]
• DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational TransformerHaozhe Ji, Minlie Huang. 4208-4224 [doi]
• Mathematical Word Problem Generation from Commonsense Knowledge Graph and EquationsTianqiao Liu, Qiang Fang, Wenbiao Ding, Hang Li, Zhongqin Wu, Zitao Liu. 4225-4240 [doi]
• Generic resources are what you need: Style transfer tasks without task-specific parallel training dataHuiyuan Lai, Antonio Toral, Malvina Nissim. 4241-4254 [doi]
• Revisiting Pivot-Based Paraphrase Generation: Language Is Not the Only Optional PivotYitao Cai, Yue Cao 0006, Xiaojun Wan 0001. 4255-4268 [doi]
• Structural Adapters in Pretrained Language Models for AMR-to-Text GenerationLeonardo F. R. Ribeiro, Yue Zhang, Iryna Gurevych. 4269-4282 [doi]
• Data-to-text Generation by Splicing Together Nearest NeighborsSam Wiseman, Arturs Backurs, Karl Stratos. 4283-4299 [doi]
• Contextualize Knowledge Bases with Transformer for End-to-end Task-Oriented Dialogue SystemsYanjie Gou, Yinjie Lei, Lingqiao Liu, Yong Dai, Chunxu Shen. 4300-4310 [doi]
• Efficient Dialogue Complementary Policy Learning via Deep Q-network Policy and Episodic Memory PolicyYangyang Zhao, Zhenyu Wang, Changxi Zhu, Shihan Wang. 4311-4323 [doi]
• CRFR: Improving Conversational Recommender Systems via Flexible Fragments Reasoning on Knowledge GraphsJinfeng Zhou, Bo Wang, Ruifang He, Yuexian Hou. 4324-4334 [doi]
• DuRecDial 2.0: A Bilingual Parallel Corpus for Conversational RecommendationZeming Liu, Haifeng Wang 0001, Zhengyu Niu, Hua Wu 0003, Wanxiang Che. 4335-4347 [doi]
• End-to-End Learning of Flowchart Grounded Task-Oriented DialogsShantanu Agarwal Dinesh Raghu, Mausam Sachindra Joshi. 4348-4366 [doi]
• Dimensional Emotion Detection from Categorical EmotionSungjoon Park, Jiseon Kim, Seonghyeon Ye, Jaeyeol Jeon, Heeyoung Park, Alice Oh. 4367-4380 [doi]
• Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text ClassificationVarsha Suresh, Desmond C. Ong. 4381-4394 [doi]
• Joint Multi-modal Aspect-Sentiment Analysis with Auxiliary Cross-modal Relation DetectionXincheng Ju, Dong Zhang, Rong Xiao, Junhui Li, Shoushan Li, Min Zhang, Guodong Zhou. 4395-4405 [doi]
• Solving Aspect Category Sentiment Analysis as a Text Generation TaskJian Liu 0030, Zhiyang Teng, Leyang Cui, Hanmeng Liu, Yue Zhang 0004. 4406-4416 [doi]
• Semantics-Preserved Data Augmentation for Aspect-Based Sentiment AnalysisTing-Wei Hsu, Chung-Chi Chen, Hen-Hsen Huang, Hsin-Hsi Chen. 4417-4422 [doi]
• The Effect of Round-Trip Translation on Fairness in Sentiment AnalysisJonathan Christiansen, Mathias Gammelgaard, Anders Søgaard. 4423-4428 [doi]
• CHoRaL: Collecting Humor Reaction Labels from Millions of Social Media UsersZixiaofan Yang, Shayan Hooshmand, Julia Hirschberg. 4429-4435 [doi]
• CSDS: A Fine-Grained Chinese Dataset for Customer Service Dialogue SummarizationHaitao Lin, Liqun Ma, Junnan Zhu, Lu Xiang, Yu Zhou 0001, Jiajun Zhang, Chengqing Zong. 4436-4451 [doi]
• CodRED: A Cross-Document Relation Extraction Dataset for Acquiring Knowledge in the WildYuan Yao, Jiaju Du, Yankai Lin, Peng Li, Zhiyuan Liu, Jie Zhou, Maosong Sun. 4452-4472 [doi]
• Building and Evaluating Open-Domain Dialogue Corpora with Clarifying QuestionsMohammad Aliannejadi, Julia Kiseleva, Aleksandr Chuklin, Jeff Dalton 0001, Mikhail S. Burtsev. 4473-4484 [doi]
• We Need to Talk About train-dev-test SplitsRob van der Goot. 4485-4494 [doi]
• PhoMT: A High-Quality and Large-Scale Benchmark Dataset for Vietnamese-English Machine TranslationLong Doan, Linh The Nguyen, Nguyen Luong Tran, Thai-Hoang, Dat Quoc Nguyen. 4495-4503 [doi]
• Lying Through One's Teeth: A Study on Verbal Leakage CuesMin-Hsuan Yeh, Lun-Wei Ku. 4504-4510 [doi]
• Multi-granularity Textual Adversarial Attack with Behavior CloningYangyi Chen, Jin Su, Wei Wei. 4511-4526 [doi]
• All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational QualityWilliam Timkey, Marten Van Schijndel. 4527-4546 [doi]
• Incorporating Residual and Normalization Layers into Analysis of Masked Language ModelsGoro Kobayashi, Tatsuki Kuribayashi, Sho Yokoi, Kentaro Inui. 4547-4568 [doi]
• Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style TransferFanchao Qi, Yangyi Chen, Xurui Zhang, Mukai Li, Zhiyuan Liu, Maosong Sun. 4569-4580 [doi]
• Sociolectal Analysis of Pretrained Language ModelsSheng Zhang 0022, Xin Zhang, Weiming Zhang, Anders Søgaard. 4581-4588 [doi]
• Examining Cross-lingual Contextual Embeddings with Orthogonal Structural ProbesTomasz Limisiewicz, David Marecek. 4589-4598 [doi]
• Are Transformers a Modern Version of ELIZA? Observations on French Object Verb AgreementBingzhi Li, Guillaume Wisniewski, Benoît Crabbé. 4599-4610 [doi]
• Fine-grained Entity Typing via Label ReasoningQing Liu, Hongyu Lin, Xinyan Xiao, Xianpei Han, Le Sun 0001, Hua Wu. 4611-4622 [doi]
• Enhanced Language Representation with Label Knowledge for Span ExtractionPan Yang 0022, Xin Cong, Zhenyun Sun, Xingwu Liu. 4623-4635 [doi]
• PRIDE: Predicting Relationships in ConversationsAnna Tigunova, Paramita Mirza, Andrew Yates, Gerhard Weikum. 4636-4650 [doi]
• Extracting Fine-Grained Knowledge Graphs of Scientific Claims: Dataset and Transformer-Based ResultsIan H. Magnusson, Scott E. Friedman. 4651-4658 [doi]
• Sequential Cross-Document Coreference ResolutionEmily Allaway, Shuai Wang, Miguel Ballesteros. 4659-4671 [doi]
• Mixture-of-Partitions: Infusing Large Biomedical Knowledge Graphs into BERTZaiqiao Meng, Fangyu Liu 0001, Thomas Hikaru Clark, Ehsan Shareghi, Nigel Collier. 4672-4681 [doi]
• Filling the Gaps in Ancient Akkadian Texts: A Masked Language Modelling ApproachKoren Lazar, Benny Saret, Asaf Yehudai, Wayne Horowitz, Nathan Wasserman, Gabriel Stanovsky. 4682-4691 [doi]
• AVocaDo: Strategy for Adapting Vocabulary to Downstream DomainJimin Hong, Taehee Kim, Hyesu Lim, Jaegul Choo. 4692-4700 [doi]
• Can We Improve Model Robustness through Secondary Attribute Counterfactuals?Ananth Balashankar, Xuezhi Wang 0002, Ben Packer, Nithum Thain, Ed H. Chi, Alex Beutel. 4701-4712 [doi]
• Long-Range Modeling of Source Code Files with eWASH: Extended Window Access by Syntax HierarchyColin B. Clement, Shuai Lu, Xiaoyu Liu, Michele Tufano, Dawn Drain, Nan Duan, Neel Sundaresan, Alexey Svyatkovskiy. 4713-4722 [doi]
• Can Language Models be Biomedical Knowledge Bases?Mujeen Sung, Jinhyuk Lee, Sean S. Yi, Minji Jeon, Sungdong Kim, Jaewoo Kang. 4723-4734 [doi]
• LayoutReader: Pre-training of Text and Layout for Reading Order DetectionZilong Wang, Yiheng Xu, Lei Cui 0001, Jingbo Shang, Furu Wei. 4735-4744 [doi]
• Region under Discussion for visual dialogMauricio Mazuecos, Franco M. Luque, Jorge Sánchez, Hernán Maina, Thomas Vadora, Luciana Benotti. 4745-4759 [doi]
• Learning grounded word meaning representations on similarity graphsMariella Dimiccoli, Herwig Wendt, Pau Batlle Franch. 4760-4769 [doi]
• WhyAct: Identifying Action Reasons in Lifestyle VlogsOana Ignat, Santiago Castro, Hanwen Miao, Weiji Li, Rada Mihalcea. 4770-4785 [doi]
• Genre as Weak Supervision for Cross-lingual Dependency ParsingMax Müller-Eberstein, Rob van der Goot, Barbara Plank. 4786-4802 [doi]
• On the Relation between Syntactic Divergence and Zero-Shot PerformanceOfir Arviv, Dmitry Nikolaev 0002, Taelin Karidi, Omri Abend. 4803-4817 [doi]
• Improved Latent Tree Induction with Distant Supervision via Span ConstraintsZhiyang Xu, Andrew Drozdov, Jay Yoon Lee, Tim O'Gorman, Subendhu Rongali, Dylan Finkbeiner, Shilpa Suresh, Mohit Iyyer, Andrew McCallum. 4818-4831 [doi]
• Aligning Multidimensional Worldviews and Discovering Ideological DifferencesJeremiah Milbauer, Adarsh Mathew, James Evans. 4832-4845 [doi]
• Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive ContextsAshutosh Baheti, Maarten Sap, Alan Ritter, Mark Riedl. 4846-4862 [doi]
• Multi-Modal Open-Domain DialogueKurt Shuster 0001, Eric Michael Smith, Da Ju, Jason Weston. 4863-4883 [doi]
• A Label-Aware BERT Attention Network for Zero-Shot Multi-Intent Detection in Spoken Language UnderstandingTing-Wei Wu, Ruolin Su, Biing-Hwang Juang. 4884-4896 [doi]
• Zero-Shot Dialogue Disentanglement by Self-Supervised Entangled Response SelectionTa-Chung Chi, Alexander I. Rudnicky. 4897-4902 [doi]
• SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal ConversationsSatwik Kottur, Seungwhan Moon, Alborz Geramifard, Babak Damavandi. 4903-4912 [doi]
• RAST: Domain-Robust Dialogue Rewriting as Sequence TaggingJie Hao, Linfeng Song, Liwei Wang 0009, Kun Xu, Zhaopeng Tu, Dong Yu 0001. 4913-4924 [doi]
• MRF-Chat: Improving Dialogue with Markov Random FieldsIshaan Grover, Matthew Huggins, Cynthia Breazeal, Hae Won Park. 4925-4936 [doi]
• Dialogue State Tracking with a Language Model using Schema-Driven PromptingChia-Hsuan Lee 0001, Hao Cheng 0002, Mari Ostendorf. 4937-4949 [doi]
• Signed Coreference ResolutionKayo Yin, Kenneth DeHaan, Malihe Alikhani. 4950-4961 [doi]
• Consistent Accelerated Inference via Confident Adaptive TransformersTal Schuster, Adam Fisch, Tommi S. Jaakkola, Regina Barzilay. 4962-4979 [doi]
• Improving and Simplifying Pattern Exploiting TrainingDerek Tam, Rakesh R. Menon, Mohit Bansal, Shashank Srivastava, Colin Raffel. 4980-4991 [doi]
• Unsupervised Data Augmentation with Naive Augmentation and without Unlabeled DataDavid Lowell, Brian E. Howard, Zachary C. Lipton, Byron C. Wallace. 4992-5001 [doi]
• Pre-train or Annotate? Domain Adaptation with a Constrained BudgetFan Bai, Alan Ritter, Wei Xu. 5002-5015 [doi]
• Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge ResourcesNinareh Mehrabi, Pei Zhou, Fred Morstatter, Jay Pujara, Xiang Ren, Aram Galstyan. 5016-5033 [doi]
• OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word EmbeddingsSunipa Dev, Tao Li 0039, Jeff M. Phillips, Vivek Srikumar. 5034-5050 [doi]
• Sentence-Permuted Paragraph GenerationWenhao Yu, Chenguang Zhu, Tong Zhao 0003, Zhichun Guo, Meng Jiang 0001. 5051-5062 [doi]
• Extract, Denoise and Enforce: Evaluating and Improving Concept Preservation for Text-to-Text GenerationYuning Mao, Wenchang Ma, Deren Lei, Jiawei Han 0001, Xiang Ren 0001. 5063-5074 [doi]
• Paraphrase Generation: A Survey of the State of the ArtJianing Zhou, Suma Bhat. 5075-5086 [doi]
• Exposure Bias versus Self-Recovery: Are Distortions Really Incremental for Autoregressive Text Generation?Tianxing He, Jingzhao Zhang, Zhiming Zhou, James R. Glass. 5087-5102 [doi]
• Generating Self-Contained and Summary-Centric Question Answer Pairs via Differentiable Reward Imitation LearningLi Zhou 0006, Kevin Small, Yong Zhang, Sandeep Atluri. 5103-5135 [doi]
• Unsupervised Paraphrasing with Pretrained Language ModelsTong Niu, Semih Yavuz, Yingbo Zhou, Nitish Shirish Keskar, Huan Wang, Caiming Xiong. 5136-5150 [doi]
• Profanity-Avoiding Training Framework for Seq2seq Models with Certified RobustnessHengtong Zhang, Tianhang Zheng, Yaliang Li, Jing Gao 0004, Lu Su, Bo Li. 5151-5161 [doi]
• Journalistic Guidelines Aware News Image CaptioningXuewen Yang, Svebor Karaman, Joel R. Tetreault, Alejandro Jaimes. 5162-5175 [doi]
• AESOP: Paraphrase Generation with Adaptive Syntactic ControlJiao Sun, Xuezhe Ma, Nanyun Peng. 5176-5189 [doi]
• Refocusing on Relevance: Personalization in NLGShiran Dudy, Steven Bedrick, Bonnie Webber. 5190-5202 [doi]
• The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event PredictionManling Li, Sha Li, Zhenhailong Wang, Lifu Huang, KyungHyun Cho, Heng Ji, Jiawei Han 0001, Clare R. Voss. 5203-5215 [doi]
• Learning Constraints and Descriptive Segmentation for Subevent DetectionHaoyu Wang, Hongming Zhang, Muhao Chen, Dan Roth. 5216-5226 [doi]
• ChemNER: Fine-Grained Chemistry Named Entity Recognition with Ontology-Guided Distant SupervisionXuan Wang, Vivian Hu, Xiangchen Song, Shweta Garg 0004, Jinfeng Xiao, Jiawei Han 0001. 5227-5240 [doi]
• Moving on from OntoNotes: Coreference Resolution Model TransferPatrick Xia, Benjamin Van Durme. 5241-5256 [doi]
• Document-level Entity-based Extraction as Template GenerationKung-Hsiang Huang, Sam Tang, Nanyun Peng. 5257-5269 [doi]
• Learning Prototype Representations Across Few-Shot Tasks for Event DetectionViet Lai, Franck Dernoncourt, Thien Huu Nguyen. 5270-5277 [doi]
• Lifelong Event Detection with Knowledge TransferPengfei Yu, Heng Ji, Prem Natarajan. 5278-5290 [doi]
• Modular Self-Supervision for Document-Level Relation ExtractionSheng Zhang, Cliff Wong, Naoto Usuyama, Sarthak Jain, Tristan Naumann, Hoifung Poon. 5291-5302 [doi]
• Unsupervised Paraphrasing Consistency Training for Low Resource Named Entity RecognitionRui Wang, Ricardo Henao. 5303-5308 [doi]
• Fine-grained Entity Typing without Knowledge BaseJing Qian, Yibin Liu, Lemao Liu, Yangming Li, Haiyun Jiang, Haisong Zhang, Shuming Shi 0001. 5309-5319 [doi]
• Adversarial Attack against Cross-lingual Knowledge Graph AlignmentZeru Zhang, Zijie Zhang, Yang Zhou 0001, Lingfei Wu, Sixing Wu, Xiaoying Han, Dejing Dou, Tianshi Che, Da Yan 0001. 5320-5337 [doi]
• Towards Realistic Few-Shot Relation ExtractionSam Brody, Sichao Wu, Adrian Benton. 5338-5345 [doi]
• Data Augmentation for Cross-Domain Named Entity RecognitionShuguang Chen, Gustavo Aguilar, Leonardo Neves, Thamar Solorio. 5346-5356 [doi]
• Incorporating medical knowledge in BERT for clinical relation extractionArpita Roy, Shimei Pan. 5357-5366 [doi]
• ECONET: Effective Continual Pretraining of Language Models for Event Temporal ReasoningRujun Han, Xiang Ren 0001, Nanyun Peng. 5367-5380 [doi]
• Learning from Noisy Labels for Entity-Centric Information ExtractionWenxuan Zhou, Muhao Chen. 5381-5392 [doi]
• Extracting Material Property Measurement Data from Scientific ArticlesGihan Panapitiya, Fred Parks, Jonathan Sepulveda, Emily Saldanha. 5393-5402 [doi]
• Modeling Document-Level Context for Event Detection via Important Context SelectionAmir Pouran Ben Veyseh, Minh Van Nguyen, Nghia Trung Ngo, Bonan Min, Thien Huu Nguyen. 5403-5413 [doi]
• Crosslingual Transfer Learning for Relation and Event Extraction via Word Category and Class AlignmentsMinh Van Nguyen, Tuan Ngo Nguyen, Bonan Min, Thien Huu Nguyen. 5414-5426 [doi]
• Corpus-based Open-Domain Event Type InductionJiaming Shen, Yunyi Zhang, Heng Ji, Jiawei Han 0001. 5427-5440 [doi]
• PDALN: Progressive Domain Adaptation over a Pre-trained Model for Low-Resource Cross-Domain Named Entity RecognitionTao Zhang, Congying Xia, Philip S. Yu, Zhiwei Liu, Shu Zhao. 5441-5451 [doi]
• Multi-Vector Attention Models for Deep Re-rankingGiulio Zhou, Jacob Devlin. 5452-5456 [doi]
• Toward Deconfounding the Effect of Entity Demographics for Question Answering AccuracyMaharshi Gor, Kellie Webster, Jordan L. Boyd-Graber. 5457-5473 [doi]
• Exploring Strategies for Generalizable Commonsense Reasoning with Pre-trained ModelsKaixin Ma, Filip Ilievski, Jonathan Francis, Satoru Ozaki, Eric Nyberg, Alessandro Oltramari. 5474-5483 [doi]
• Transformer Feed-Forward Layers Are Key-Value MemoriesMor Geva, Roei Schuster, Jonathan Berant, Omer Levy. 5484-5495 [doi]
• Connecting Attributions and QA Model Behavior on Realistic CounterfactualsXi Ye, Rohan Nair, Greg Durrett. 5496-5512 [doi]
• How Do Neural Sequence Models Generalize? Local and Global Cues for Out-of-Distribution PredictionD. Anthony Bau, Jacob Andreas. 5513-5526 [doi]
• Comparing Text Representations: A Theory-Driven ApproachGregory Yauney, David Mimno. 5527-5539 [doi]
• Human Rationales as Attribution Priors for Explainable Stance DetectionSahil Jayaram, Emily Allaway. 5540-5554 [doi]
• The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer EncodersHan He, Jinho D. Choi. 5555-5577 [doi]
• Text Counterfactuals via Latent Optimization and Shapley-Guided SearchXiaoli Z. Fern, Quintin Pope. 5578-5593 [doi]
• "Average" Approximates "First Principal Component"? An Empirical Analysis on Representations from Neural Language ModelsZihan Wang, Chengyu Dong, Jingbo Shang. 5594-5603 [doi]
• Controlled Evaluation of Grammatical Knowledge in Mandarin Chinese Language ModelsYiwen Wang, Jennifer Hu, Roger Levy, Peng Qian. 5604-5620 [doi]
• GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer NetworksWeicheng Ma, Renze Lou, Kai Zhang, Lili Wang, Soroush Vosoughi. 5621-5632 [doi]
• NegatER: Unsupervised Discovery of Negatives in Commonsense Knowledge BasesTara Safavi, Jing Zhu, Danai Koutra. 5633-5646 [doi]
• Instance-adaptive training with noise-robust losses against noisy labelsLifeng Jin, Linfeng Song, Kun Xu, Dong Yu. 5647-5663 [doi]
• Distributionally Robust Multilingual Machine TranslationChunting Zhou, Daniel Levy, Xian Li, Marjan Ghazvininejad, Graham Neubig. 5664-5674 [doi]
• Model Selection for Cross-lingual TransferYang Chen, Alan Ritter. 5675-5687 [doi]
• Continual Few-Shot Learning for Text ClassificationRamakanth Pasunuru, Veselin Stoyanov, Mohit Bansal. 5688-5702 [doi]
• Efficient Nearest Neighbor Language ModelsJunxian He, Graham Neubig, Taylor Berg-Kirkpatrick. 5703-5714 [doi]
• STraTA: Self-Training with Task Augmentation for Better Few-shot LearningTu Vu, Minh-Thang Luong, Quoc V. Le, Grady Simon, Mohit Iyyer. 5715-5731 [doi]
• TADPOLE: Task ADapted Pre-Training via AnOmaLy DEtectionVivek Madan, Ashish Khetan, Zohar Karnin. 5732-5746 [doi]
• Gradient-based Adversarial Attacks against Text TransformersChuan Guo, Alexandre Sablayrolles, Hervé Jégou, Douwe Kiela. 5747-5757 [doi]
• Do Transformer Modifications Transfer Across Implementations and Applications?Sharan Narang, Hyung Won Chung, Yi Tay, Liam Fedus, Thibault Févry, Michael Matena, Karishma Malkan, Noah Fiedel, Noam Shazeer, Zhenzhong Lan, Yanqi Zhou, Wei Li 0133, Nan Ding, Jake Marcus, Adam Roberts, Colin Raffel. 5758-5773 [doi]
• Paired Examples as Indirect Supervision in Latent Decision ModelsNitish Gupta, Sameer Singh 0001, Matt Gardner 0001, Dan Roth. 5774-5785 [doi]
• Pairwise Supervised Contrastive Learning of Sentence RepresentationsDejiao Zhang, Shang-wen Li 0001, Wei Xiao, Henghui Zhu, Ramesh Nallapati, Andrew O. Arnold, Bing Xiang. 5786-5798 [doi]
• Muppet: Massive Multi-task Representations with Pre-FinetuningArmen Aghajanyan, Anchit Gupta, Akshat Shrivastava, Xilun Chen, Luke Zettlemoyer, Sonal Gupta. 5799-5811 [doi]
• Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLPTrapit Bansal, Karthick Prasad Gunasekaran, Tong Wang, Tsendsuren Munkhdalai, Andrew McCallum. 5812-5824 [doi]
• A Simple and Effective Method To Eliminate the Self Language Bias in Multilingual RepresentationsZiyi Yang, Yinfei Yang, Daniel Cer, Eric Darve. 5825-5832 [doi]
• A Massively Multilingual Analysis of Cross-linguality in Shared Embedding SpaceAlexander Jones, William Yang Wang, Kyle Mahowald. 5833-5847 [doi]
• Frustratingly Simple but Surprisingly Strong: Using Language-Independent Features for Zero-shot Cross-lingual Semantic ParsingJingfeng Yang, Federico Fancellu, Bonnie Webber, Diyi Yang. 5848-5856 [doi]
• Improving Simultaneous Translation by Incorporating Pseudo-References with Fewer ReorderingsJunkun Chen, Renjie Zheng, Atsuhito Kita, Mingbo Ma, Liang Huang 0001. 5857-5864 [doi]
• Classification-based Quality Estimation: Small and Efficient Models for Real-world ApplicationsShuo Sun, Ahmed El-Kishky, Vishrav Chaudhary, James Cross, Lucia Specia, Francisco Guzmán. 5865-5875 [doi]
• A Large-Scale Study of Machine Translation in Turkic LanguagesJamshidbek Mirzakhalov, Anoop Babu, Duygu Ataman, Sherzod Kariev, Francis Tyers, Otabek Abduraufov, Mammad Hajili, Sardana Ivanova, Abror Khaytbaev, Antonio Laverghetta Jr., Behzodbek Moydinboyev, Esra Onal, Shaxnoza Pulatova, Ahsan Wahab, Orhan Firat, Sriram Chellappan. 5876-5890 [doi]
• Analyzing the Surprising Variability in Word Embedding Stability Across LanguagesLaura Burdick, Jonathan K. Kummerfeld, Rada Mihalcea. 5891-5901 [doi]
• Rule-based Morphological Inflection Improves Neural Terminology TranslationWeijia Xu, Marine Carpuat. 5902-5914 [doi]
• Data and Parameter Scaling Laws for Neural Machine TranslationMitchell A. Gordon, Kevin Duh, Jared Kaplan. 5915-5922 [doi]
• Good-Enough Example ExtrapolationJason Wei. 5923-5929 [doi]
• Learning to Selectively Learn for Weakly-supervised Paraphrase GenerationKaize Ding, Dingcheng Li, Alexander Hanbo Li, Xing Fan, Chenlei Guo, Yang Liu, Huan Liu 0001. 5930-5940 [doi]
• Effective Convolutional Attention Network for Multi-label Clinical Document ClassificationYang Liu, Hua Cheng, Russell Klopfer, Matthew R. Gormley, Thomas Schaaf. 5941-5953 [doi]
• Contrastive Code Representation LearningParas Jain 0001, Ajay Jain, Tianjun Zhang, Pieter Abbeel, Joseph Gonzalez 0001, Ion Stoica. 5954-5971 [doi]
• IGA: An Intent-Guided Authoring AssistantSimeng Sun, Wenlong Zhao, Varun Manjunatha, Rajiv Jain, Vlad I. Morariu, Franck Dernoncourt, Balaji Vasan Srinivasan, Mohit Iyyer. 5972-5985 [doi]
• Math Word Problem Generation with Mathematical Consistency and Problem Context ConstraintsZichao Wang 0001, Andrew S. Lan, Richard G. Baraniuk. 5986-5999 [doi]
• Navigating the Kaleidoscope of COVID-19 Misinformation Using Deep LearningYuanzhi Chen, Mohammad Hasan. 6000-6017 [doi]
• Detecting Health Advice in Medical Research LiteratureYingya Li, Jun Wang, Bei Yu 0002. 6018-6029 [doi]
• A Semantic Feature-Wise Transformation Relation Network for Automatic Short Answer GradingZhaohui Li, Yajur Tomar, Rebecca J. Passonneau. 6030-6040 [doi]
• Evaluating Scholarly Impact: Towards Content-Aware BibliometricsSaurav Manchanda, George Karypis. 6041-6053 [doi]
• A Scalable Framework for Learning From Implicit User Feedback to Improve Natural Language Understanding in Large-Scale Conversational AI SystemsSunghyun Park, Han Li, Ameen Patel, Sidharth Mudgal, Sungjin Lee, Young-Bum Kim, Spyros Matsoukas, Ruhi Sarikaya. 6054-6063 [doi]
• Summarize-then-Answer: Generating Concise Explanations for Multi-hop Reading ComprehensionNaoya Inoue, Harsh Trivedi, Steven Sinha, Niranjan Balasubramanian, Kentaro Inui. 6064-6080 [doi]
• FewshotQA: A simple framework for few-shot learning of question answering tasks using pre-trained text-to-text modelsRakesh Chada, Pradeep Natarajan. 6081-6090 [doi]
• Multi-stage Training with Improved Negative Contrast for Neural Passage RetrievalJing Lu, Gustavo Hernández Ábrego, Ji Ma, Jianmo Ni, Yinfei Yang. 6091-6103 [doi]
• Perhaps PTLMs Should Go to School - A Task to Assess Open Book and Closed Book QAManuel R. Ciosici, Joe Cecil 0002, Dong-Ho Lee, Alex Hedges, Marjorie Freedman, Ralph M. Weischedel. 6104-6111 [doi]
• ReasonBERT: Pre-trained to Reason with Distant SupervisionXiang Deng, Yu Su 0001, Alyssa Lees, You Wu 0001, Cong Yu 0001, Huan Sun. 6112-6127 [doi]
• Single-dataset Experts for Multi-dataset Question AnsweringDan Friedman, Ben Dodge, Danqi Chen. 6128-6137 [doi]
• Simple Entity-Centric Questions Challenge Dense RetrieversChristopher Sciavolino, Zexuan Zhong, Jinhyuk Lee, Danqi Chen. 6138-6148 [doi]
• Mitigating False-Negative Contexts in Multi-document Question Answering with Retrieval MarginalizationAnsong Ni, Matt Gardner 0001, Pradeep Dasigi. 6149-6161 [doi]
• MultiDoc2Dial: Modeling Dialogues Grounded in Multiple DocumentsSong Feng, Siva Sankalp Patel, Hui Wan 0001, Sachindra Joshi. 6162-6176 [doi]
• GupShup: Summarizing Open-Domain Code-Switched ConversationsLaiba Mehnaz, Debanjan Mahata, Rakesh Gosangi, Uma Sushmitha Gunturi, Riya Jain, Gauri Gupta, Amardeep Kumar, Isabelle G. Lee, Anish Acharya, Rajiv Ratn Shah. 6177-6192 [doi]
• BiSECT: Learning to Split and Rephrase Sentences with BitextsJoongwon Kim, Mounica Maddela, Reno Kriz, Wei Xu, Chris Callison-Burch. 6193-6209 [doi]
• Data Collection vs. Knowledge Graph Completion: What is Needed to Improve Coverage?Kenneth Church 0001, Yuchen Bian. 6210-6215 [doi]
• Universal Sentence Representation Learning with Conditional Masked Language ModelZiyi Yang, Yinfei Yang, Daniel Cer, Jax Law, Eric Darve. 6216-6228 [doi]
• On the Benefit of Syntactic Supervision for Cross-lingual Transfer in Semantic Role LabelingZhisong Zhang, Emma Strubell, Eduard H. Hovy. 6229-6246 [doi]
• Implicit Premise Generation with Discourse-aware Commonsense Knowledge ModelsTuhin Chakrabarty, Aadit Trivedi, Smaranda Muresan. 6247-6252 [doi]
• Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction TasksYichen Jiang, Mohit Bansal. 6253-6265 [doi]
• Flexible Generation of Natural Language DeductionsKaj Bostrom, Xinyu Zhao, Swarat Chaudhuri, Greg Durrett. 6266-6278 [doi]
• Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR ParsingJiawei Zhou, Tahira Naseem, Ramón Fernandez Astudillo, Young-Suk Lee, Radu Florian, Salim Roukos. 6279-6290 [doi]
• Think about it! Improving defeasible reasoning by first modeling the question scenarioAman Madaan, Niket Tandon, Dheeraj Rajagopal, Peter Clark, Yiming Yang, Eduard H. Hovy. 6291-6310 [doi]
• Open Aspect Target Sentiment Classification with Natural Language PromptsRonald Seoh, Ian Birle, Mrinal Tak, Haw-Shiuan Chang, Brian Pinette, Alfred Hough. 6311-6322 [doi]
• Does BERT Learn as Humans Perceive? Understanding Linguistic Styles through LexicaShirley Anugrah Hayati, Dongyeop Kang, Lyle Ungar. 6323-6331 [doi]
• Improving Stance Detection with Multi-Dataset Learning and Knowledge DistillationYingjie Li, Chenye Zhao, Cornelia Caragea. 6332-6345 [doi]
• Discovering the Unknown Knowns: Turning Implicit Knowledge in the Dataset into Explicit Training Examples for Visual Question AnsweringJihyung Kil, Cheng Zhang, Dong Xuan, Wei-Lun Chao. 6346-6361 [doi]
• Improving Pre-trained Vision-and-Language Embeddings for Phrase GroundingZi-Yi Dou, Nanyun Peng. 6362-6371 [doi]
• Sequential Randomized Smoothing for Adversarially Robust Speech RecognitionRaphael Olivier, Bhiksha Raj. 6372-6386 [doi]
• Hitting your MARQ: Multimodal ARgument Quality Assessment in Long Debate VideoMd. Kamrul Hasan 0003, James Spann, Masum Hasan, Md Saiful Islam, Kurtis Haut, Rada Mihalcea, Ehsan Hoque. 6387-6397 [doi]
• Mind the Context: The Impact of Contextualization in Neural Module Networks for Grounding Visual Referring ExpressionsArjun Akula, Spandana Gella, Keze Wang, Song Chun Zhu, Siva Reddy. 6398-6416 [doi]
• Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question AnsweringMan Luo, Yankai Zeng, Pratyay Banerjee, Chitta Baral. 6417-6431 [doi]
• NDH-Full: Learning and Evaluating Navigational Agents on Full-Length DialogueHyounghun Kim, Jialu Li, Mohit Bansal. 6432-6442 [doi]
• Timeline Summarization based on Event Graph Compression via Time-Aware Optimal TransportManling Li, Tengfei Ma 0001, Mo Yu, Lingfei Wu, Tian Gao, Heng Ji, Kathleen R. McKeown. 6443-6456 [doi]
• StreamHover: Livestream Transcript Summarization and AnnotationSangwoo Cho, Franck Dernoncourt, Tim Ganter, Trung Bui, Nedim Lipka, Walter Chang, Hailin Jin, Jonathan Brandt, Hassan Foroosh, Fei Liu 0004. 6457-6474 [doi]
• Cross-Register Projection for Headline Part of Speech TaggingAdrian Benton, Hanyang Li, Igor Malioutov. 6475-6490 [doi]
• Editing Factual Knowledge in Language ModelsNicola De Cao, Wilker Aziz, Ivan Titov. 6491-6506 [doi]
• Sparse Attention with Linear UnitsBiao Zhang, Ivan Titov, Rico Sennrich. 6507-6520 [doi]
• Knowledge Base Completion Meets Transfer LearningVid Kocijan, Thomas Lukasiewicz. 6521-6533 [doi]
• SPECTRA: Sparse Structured Text RationalizationNuno Miguel Guerreiro, André F. T. Martins. 6534-6550 [doi]
• Towards Zero-Shot Knowledge Distillation for Natural Language ProcessingAhmad Rashid, Vasileios Lioutas, Abbas Ghaddar, Mehdi Rezagholizadeh. 6551-6561 [doi]
• Adversarial Regularization as Stackelberg Game: An Unrolled Optimization ApproachSimiao Zuo, Chen Liang, Haoming Jiang, Xiaodong Liu, Pengcheng He, Jianfeng Gao, Weizhu Chen, Tuo Zhao. 6562-6577 [doi]
• Aspect-Controllable Opinion SummarizationReinald Kim Amplayo, Stefanos Angelidis, Mirella Lapata. 6578-6593 [doi]
• QuestEval: Summarization Asks for Fact-based EvaluationThomas Scialom, Paul-Alexis Dray, Sylvain Lamprier, Benjamin Piwowarski, Jacopo Staiano, Alex Wang, Patrick Gallinari. 6594-6604 [doi]
• Simple Conversational Data Augmentation for Semi-supervised Abstractive Dialogue SummarizationJiaao Chen, Diyi Yang. 6605-6616 [doi]
• Finding a Balanced Degree of Automation for Summary EvaluationShiyue Zhang, Mohit Bansal. 6617-6632 [doi]
• CLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive SummarizationShuyang Cao, Lu Wang 0008. 6633-6649 [doi]
• Multilingual Unsupervised Neural Machine Translation with Denoising AdaptersAhmet Üstün, Alexandre Berard, Laurent Besacier, Matthias Gallé. 6650-6662 [doi]
• BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine TranslationHaoran Xu, Benjamin Van Durme, Kenton Murray. 6663-6675 [doi]
• Controlling Machine Translation for Multiple Attributes with Additive InterventionsAndrea Schioppa, David Vilar, Artem Sokolov,