Table of Contents

• Frontmatter [doi]
• Social Norms Guide Reference ResolutionMitchell Abrams, Matthias Scheutz. 1-11 [doi]
• Learning Natural Language Generation with Truncated Reinforcement LearningAlice Martin, Guillaume Quispe, Charles Ollion, Sylvain Le Corff, Florian Strub, Olivier Pietquin. 12-37 [doi]
• Language Model Augmented Monotonic Attention for Simultaneous TranslationSathish Reddy Indurthi, Mohd Abbas Zaidi, Beomseok Lee, Nikhil Kumar Lakumarapu, Sangha Kim 0002. 38-45 [doi]
• What Makes a Good and Useful Summary? Incorporating Users in Automatic Summarization ResearchMaartje ter Hoeve, Julia Kiseleva, Maarten de Rijke. 46-75 [doi]
• ErAConD: Error Annotated Conversational Dialog Dataset for Grammatical Error CorrectionXun Yuan 0002, Derek Pham, Sam Davidson, Zhou Yu. 76-84 [doi]
• Semantic Diversity in Dialogue with Natural Language InferenceKatherine Stasaski, Marti Hearst. 85-98 [doi]
• LEA: Meta Knowledge-Driven Self-Attentive Document Embedding for Few-Shot Text ClassificationS. K. Hong, Tae Young Jang. 99-106 [doi]
• Enhancing Self-Attention with Knowledge-Assisted Attention MapsJiangang Bai, Yujing Wang, Hong Sun, Ruonan Wu, Tianmeng Yang, Pengfei Tang, Defu Cao, Mingliang Zhang, Yunhai Tong, Yaming Yang 0001, Jing Bai, Ruofei Zhang, Hao Sun, Wei Shen. 107-115 [doi]
• Batch-Softmax Contrastive Loss for Pairwise Sentence Scoring TasksAnton Chernyavskiy, Dmitry Ilvovsky, Pavel Kalinin, Preslav Nakov. 116-126 [doi]
• NewsEdits: A News Article Revision Dataset and a Novel Document-Level Reasoning ChallengeAlexander Spangher, Xiang Ren, Jonathan May, Nanyun Peng. 127-157 [doi]
• Putting the Con in Context: Identifying Deceptive Actors in the Game of MafiaSamee Ibraheem, Gaoyue Zhou, John DeNero. 158-168 [doi]
• SUBS: Subtree Substitution for Compositional Semantic ParsingJingfeng Yang, Le Zhang, Diyi Yang. 169-174 [doi]
• Two Contrasting Data Annotation Paradigms for Subjective NLP TasksPaul Röttger, Bertie Vidgen, Dirk Hovy, Janet B. Pierrehumbert. 175-190 [doi]
• Do Deep Neural Nets Display Human-like Attention in Short Answer Scoring?Zijie Zeng, Xinyu Li, Dragan Gasevic, Guanliang Chen. 191-205 [doi]
• Knowledge-Grounded Dialogue Generation with a Unified Knowledge RepresentationYu Li, Baolin Peng, Yelong Shen, Yi Mao, Lars Liden, Zhou Yu, Jianfeng Gao. 206-218 [doi]
• CERES: Pretraining of Graph-Conditioned Transformer for Semi-Structured Session DataRui Feng, Chen Luo, Qingyu Yin, Bing Yin, Tuo Zhao, Chao Zhang. 219-230 [doi]
• Political Ideology and Polarization: A Multi-dimensional ApproachBarea Sinno, Bernardo Oviedo, Katherine Atwell, Malihe Alikhani, Junyi Jessy Li. 231-243 [doi]
• Cooperative Self-training of Machine Reading ComprehensionHongyin Luo, Shang-wen Li 0001, Mingye Gao, Seunghak Yu, James R. Glass. 244-257 [doi]
• GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in TransformersAli Modarressi, Mohsen Fayyaz, Yadollah Yaghoobzadeh, Mohammad Taher Pilehvar. 258-271 [doi]
• A Robustly Optimized BMRC for Aspect Sentiment Triplet ExtractionShu Liu 0002, Kaiwen Li, Zuhe Li. 272-278 [doi]
• Seed-Guided Topic Discovery with Out-of-Vocabulary SeedsYu Zhang, Yu Meng 0001, Xuan Wang, Sheng Wang, Jiawei Han 0001. 279-290 [doi]
• Towards Process-Oriented, Modular, and Versatile Question Generation that Meets Educational NeedsXu Wang, Simin Fan, Jessica Houghton, Lu Wang. 291-302 [doi]
• SwahBERT: Language Model of SwahiliGati L. Martin, Medard Edmund Mswahili, Young-Seob Jeong, Jiyoung Woo. 303-313 [doi]
• Deconstructing NLG Evaluation: Evaluation Practices, Assumptions, and Their ImplicationsKaitlyn Zhou, Su Lin Blodgett, Adam Trischler, Hal Daumé III, Kaheer Suleman, Alexandra Olteanu. 314-324 [doi]
• TSTR: Too Short to Represent, Summarize with Details! Intro-Guided Extended Summary GenerationSajad Sotudeh, Nazli Goharian. 325-335 [doi]
• Empathic Machines: Using Intermediate Features as Levers to Emulate Emotions in Text-To-Speech SystemsSaiteja Kosgi, Sarath Sivaprasad, Niranjan Pedanekar, Anil Nelakanti, Vineet Gandhi. 336-347 [doi]
• The Why and The How: A Survey on Natural Language Interaction in VisualizationHenrik Voigt, Özge Alaçam, Monique Meuschke, Kai Lawonn, Sina Zarrieß. 348-374 [doi]
• Understand before Answer: Improve Temporal Reading Comprehension via Precise Question UnderstandingHao Huang, Xiubo Geng, Guodong Long, Daxin Jiang. 375-384 [doi]
• User-Driven Research of Medical Note Generation SoftwareTom Knoll, Francesco Moramarco, Alex Papadopoulos-Korfiatis, Rachel Young, Claudia Ruffini, Mark Perera, Christian Perstl, Ehud Reiter, Anya Belz, Aleksandar Savkov. 385-394 [doi]
• Ask Me Anything in Your Native LanguageNikita Sorokin, Dmitry Abulkhanov, Irina Piontkovskaya, Valentin Malykh. 395-406 [doi]
• Diversifying Neural Dialogue Generation via Negative DistillationYiwei Li, Shaoxiong Feng, Bin Sun, Kan Li 0001. 407-418 [doi]
• On Synthetic Data for Back TranslationJiahao Xu, Yubin Ruan, Wei Bi, Guoping Huang, Shuming Shi 0001, Lihui Chen 0001, Lemao Liu. 419-430 [doi]
• Mapping the Design Space of Human-AI Interaction in Text SummarizationRuijia Cheng, Alison Smith-Renner, Ke Zhang, Joel R. Tetreault, Alejandro Jaimes-Larrarte. 431-455 [doi]
• Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style TransferSharan Narasimhan, Suvodip Dey, Maunendra Sankar Desarkar. 456-474 [doi]
• An Exploration of Post-Editing Effectiveness in Text SummarizationVivian Lai, Alison Smith-Renner, Ke Zhang, Ruijia Cheng, Wenjuan Zhang, Joel R. Tetreault, Alejandro Jaimes-Larrarte. 475-493 [doi]
• Automatic Correction of Human TranslationsJessy Lin, Geza Kovacs, Aditya Shastry, Joern Wuebker, John DeNero. 494-507 [doi]
• On the Robustness of Reading Comprehension Models to Entity RenamingJun Yan 0012, Yang Xiao, Sagnik Mukherjee, Bill Yuchen Lin, Robin Jia, Xiang Ren. 508-520 [doi]
• Explaining Why: How Instructions and User Interfaces Impact Annotator Rationales When Labeling Text DataJamar L. Sullivan Jr., William Brackenbury, Andrew McNut, Kevin Bryson, Kwam Byll, Yuxin Chen, Michael L. Littman, Chenhao Tan, Blase Ur. 521-531 [doi]
• Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and IsotropizationHaode Zhang, Haowen Liang, Yuwei Zhang, Li-Ming Zhan, Xiao-Ming Wu 0003, Xiaolei Lu, Albert Y. S. Lam. 532-542 [doi]
• Cross-document Misinformation Detection based on Event Graph ReasoningXueqing Wu 0001, Kung-Hsiang Huang, Yi Fung, Heng Ji. 543-558 [doi]
• Disentangled Action Recognition with Knowledge BasesZhekun Luo, Shalini Ghosh, Devin Guillory, Keizo Kato, Trevor Darrell, Huijuan Xu 0001. 559-572 [doi]
• Machine-in-the-Loop Rewriting for Creative Image CaptioningVishakh Padmakumar, He He 0001. 573-586 [doi]
• A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock PredictionYong Xie, Dakuo Wang, Pin-Yu Chen, Jinjun Xiong, Sijia Liu, Oluwasanmi Koyejo. 587-599 [doi]
• Building Multilingual Machine Translation Systems That Serve Arbitrary XY TranslationsAkiko Eriguchi, Shufang Xie 0003, Tao Qin, Hany Hassan. 600-606 [doi]
• Non-Autoregressive Neural Machine Translation with Consistency Regularization Optimized Variational FrameworkMinghao Zhu, Junli Wang, ChunGang Yan. 607-617 [doi]
• User-Centric Gender RewritingBashar Alhafni, Nizar Habash, Houda Bouamor. 618-631 [doi]
• Reframing Human-AI Collaboration for Generating Free-Text ExplanationsSarah Wiegreffe, Jack Hessel, Swabha Swayamdipta, Mark O. Riedl, Yejin Choi. 632-658 [doi]
• EmRel: Joint Representation of Entities and Embedded Relations for Multi-triple ExtractionBenfeng Xu, Quan Wang, Yajuan Lyu, YaBing Shi, Yong Zhu 0004, Jie Gao, Zhendong Mao. 659-665 [doi]
• Meta Learning for Natural Language Processing: A SurveyHung-yi Lee, Shang-wen Li 0001, Thang Vu. 666-684 [doi]
• Analyzing Modality Robustness in Multimodal Sentiment AnalysisDevamanyu Hazarika, Yingting Li, Bo Cheng 0001, Shuai Zhao 0001, Roger Zimmermann, Soujanya Poria. 685-696 [doi]
• Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text GenerationJinyi Hu, Xiaoyuan Yi, Wenhao Li, Maosong Sun, Xing Xie. 697-716 [doi]
• Easy Adaptation to Mitigate Gender Bias in Multilingual Text ClassificationXiaolei Huang. 717-723 [doi]
• On the Use of External Data for Spoken Named Entity RecognitionAnkita Pasad, Felix Wu, Suwon Shon, Karen Livescu, Kyu J. Han. 724-737 [doi]
• Long-term Control for Dialogue Generation: Methods and EvaluationRamya Ramakrishnan, Hashan Buddhika Narangodage, Mauro Schilman, Kilian Q. Weinberger, Ryan Mcdonald. 738-753 [doi]
• Learning Dialogue Representations from Consecutive UtterancesZhihan Zhou 0001, Dejiao Zhang, Wei Xiao 0001, Nicholas Dingwall, Xiaofei Ma, Andrew O. Arnold, Bing Xiang. 754-768 [doi]
• On the Machine Learning of Ethical Judgments from Natural LanguageZeerak Talat, Hagen Blix, Josef Valvoda, Maya Indira Ganesh, Ryan Cotterell, Adina Williams. 769-779 [doi]
• NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead HeuristicsXiming Lu, Sean Welleck, Peter West, Liwei Jiang, Jungo Kasai, Daniel Khashabi, Ronan Le Bras, Lianhui Qin, Youngjae Yu, Rowan Zellers, Noah A. Smith, Yejin Choi. 780-799 [doi]
• PARADISE: Exploiting Parallel Data for Multilingual Sequence-to-Sequence PretrainingMachel Reid, Mikel Artetxe. 800-810 [doi]
• Explaining Toxic Text via Knowledge Enhanced Text GenerationRohit Sridhar, Diyi Yang. 811-826 [doi]
• Teaching BERT to Wait: Balancing Accuracy and Latency for Streaming Disfluency DetectionAngelica Chen, Vicky Zayats, Daniel D. Walker, Dirk Padfield. 827-838 [doi]
• GRAM: Fast Fine-tuning of Pre-trained Language Models for Content-based Collaborative FilteringYoonseok Yang, Kyu Seok Kim, Minsam Kim, Juneyoung Park. 839-851 [doi]
• Generating Repetitions with Appropriate Repeated WordsToshiki Kawamoto, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura. 852-859 [doi]
• Textless Speech-to-Speech Translation on Real DataAnn Lee, Hongyu Gong, Paul-Ambroise Duquenne, Holger Schwenk, Peng-Jen Chen, Changhan Wang, Sravya Popuri, Yossi Adi, Juan Pino, Jiatao Gu, Wei-Ning Hsu. 860-872 [doi]
• WALNUT: A Benchmark on Semi-weakly Supervised Learning for Natural Language UnderstandingGuoqing Zheng, Giannis Karamanolakis, Kai Shu, Ahmed Hassan Awadallah. 873-899 [doi]
• CompactIE: Compact Facts in Open Information ExtractionFarima Fatahi Bayat, Nikita Bhutani, H. V. Jagadish. 900-910 [doi]
• CoSIm: Commonsense Reasoning for Counterfactual Scene ImaginationHyounghun Kim, Abhay Zala, Mohit Bansal. 911-923 [doi]
• Abstraction not Memory: BERT and the English Article SystemHarish Tayyar Madabushi, Dagmar Divjak, Petar Milin. 924-931 [doi]
• OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question AnsweringZhengbao Jiang, Yi Mao, Pengcheng He, Graham Neubig, Weizhu Chen. 932-942 [doi]
• Provably Confidential Language ModellingXuandong Zhao, Lei Li, Yu-Xiang Wang 0003. 943-955 [doi]
• KAT: A Knowledge Augmented Transformer for Vision-and-LanguageLiangke Gui, Borui Wang, Qiuyuan Huang, Alexander Hauptmann 0001, Yonatan Bisk, Jianfeng Gao. 956-968 [doi]
• When a sentence does not introduce a discourse entity, Transformer-based models still sometimes refer to itSebastian Schuster, Tal Linzen. 969-982 [doi]
• On Curriculum Learning for Commonsense ReasoningAdyasha Maharana, Mohit Bansal. 983-992 [doi]
• DocTime: A Document-level Temporal Dependency Graph ParserPuneet Mathur, Vlad I. Morariu, Verena Kaynig-Fittkau, Jiuxiang Gu, Franck Dernoncourt, Quan Hung Tran, Ani Nenkova, Dinesh Manocha, Rajiv Jain. 993-1009 [doi]
• FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive SummarizationDavid Wan, Mohit Bansal. 1010-1028 [doi]
• ScAN: Suicide Attempt and Ideation Events DatasetBhanu Pratap Singh Rawat, Samuel Kovaly, Hong Yu 0001, Wilfred R. Pigeon. 1029-1040 [doi]
• Socially Aware Bias Measurements for Hindi Language RepresentationsVijit Malik, Sunipa Dev, Akihiro Nishi, Nanyun Peng, Kai-Wei Chang. 1041-1052 [doi]
• AmbiPun: Generating Humorous Puns with Ambiguous ContextAnirudh Mittal, Yufei Tian, Nanyun Peng. 1053-1062 [doi]
• EmpHi: Generating Empathetic Responses with Human-like IntentsMao Yan Chen, Siheng Li, Yujiu Yang. 1063-1074 [doi]
• Yes, No or IDK: The Challenge of Unanswerable Yes/No QuestionsElior Sulem, Jamaal Hay, Dan Roth. 1075-1085 [doi]
• Inducing and Using Alignments for Transition-based AMR ParsingAndrew Drozdov, Jiawei Zhou, Radu Florian, Andrew McCallum, Tahira Naseem, Yoon Kim, Ramón Fernandez Astudillo. 1086-1098 [doi]
• Masked Part-Of-Speech Model: Does Modeling Long Context Help Unsupervised POS-tagging?Xiang Zhou, Shiyue Zhang, Mohit Bansal. 1099-1114 [doi]
• DREAM: Improving Situational QA by First Elaborating the SituationYuling Gu, Bhavana Dalvi, Peter Clark. 1115-1127 [doi]
• CoSe-Co: Text Conditioned Generative CommonSense ContextualizerRachit Bansal, Milan Aggarwal, Sumit Bhatia, Jivat Neet Kaur, Balaji Krishnamurthy. 1128-1143 [doi]
• Probing via PromptingJiaoda Li, Ryan Cotterell, Mrinmaya Sachan. 1144-1157 [doi]
• Database Search Results Disambiguation for Task-Oriented Dialog SystemsKun Qian, Satwik Kottur, Ahmad Beirami, Shahin Shayandeh, Paul A. Crook, Alborz Geramifard, Zhou Yu, Chinnadhurai Sankar. 1158-1173 [doi]
• Unsupervised Slot Schema Induction for Task-oriented DialogDian Yu, Mingqiu Wang, Yuan Cao 0007, Izhak Shafran, Laurent El Shafey, Hagen Soltau. 1174-1193 [doi]
• Towards a Progression-Aware Autonomous Dialogue AgentAbraham Sanders, Tomek Strzalkowski, Mei Si, Albert Chang, Deepanshu Dey, Jonas Braasch, Dakuo Wang. 1194-1212 [doi]
• Cross-Domain Detection of GPT-2-Generated Technical TextJuan Rodriguez, Todd Hay, David Gros, Zain Shamsi, Ravi Srinivasan. 1213-1233 [doi]
• DISAPERE: A Dataset for Discourse Structure in Peer Review DiscussionsNeha Nayak Kennard, Tim O'Gorman, Rajarshi Das, Akshay Sharma, Chhandak Bagchi, Matthew Clinton, Pranay Kumar Yelugam, Hamed Zamani, Andrew McCallum. 1234-1249 [doi]
• MultiSpanQA: A Dataset for Multi-Span Question AnsweringHaonan Li 0003, Martin Tomko, Maria Vasardani, Timothy Baldwin. 1250-1260 [doi]
• Context-Aware Abbreviation Expansion Using Large Language ModelsShanqing Cai, Subhashini Venugopalan, Katrin Tomanek, Ajit Narayanan, Meredith Ringel Morris, Michael P. Brenner. 1261-1275 [doi]
• Theory-Grounded Measurement of U.S. Social Stereotypes in English Language ModelsYang Trista Cao, Anna Sotnikova, Hal Daumé III, Rachel Rudinger, Linda Zou. 1276-1295 [doi]
• Sort by Structure: Language Model Ranking as Dependency ProbingMax Müller-Eberstein, Rob van der Goot, Barbara Plank. 1296-1307 [doi]
• Quantifying Synthesis and Fusion and their Impact on Machine TranslationArturo Oncevay, Duygu Ataman, Niels van Berkel, Barry Haddow, Alexandra Birch, Johannes Bjerva. 1308-1321 [doi]
• Commonsense and Named Entity Aware Knowledge Grounded Dialogue GenerationDeeksha Varshney, Akshara Prabhakar, Asif Ekbal. 1322-1335 [doi]
• Efficient Hierarchical Domain Adaptation for Pretrained Language ModelsAlexandra Chronopoulou, Matthew E. Peters, Jesse Dodge. 1336-1351 [doi]
• Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-Based HateHannah Kirk, Bertie Vidgen, Paul Röttger, Tristan Thrush, Scott A. Hale. 1352-1368 [doi]
• On the Economics of Multilingual Few-shot Learning: Modeling the Cost-Performance Trade-offs of Machine Translated and Manual DataKabir Ahuja, Monojit Choudhury, Sandipan Dandapat. 1369-1384 [doi]
• Learning to Selectively Learn for Weakly Supervised Paraphrase Generation with Model-based Reinforcement LearningHaiyan Yin, Dingcheng Li, Ping Li. 1385-1395 [doi]
• Quality-Aware Decoding for Neural Machine TranslationPatrick Fernandes, António Farinhas, Ricardo Rei, José Guilherme Camargo de Souza, Perez Ogayo, Graham Neubig, André F. T. Martins. 1396-1412 [doi]
• Pretrained Models for Multilingual Federated LearningOrion Weller, Marc Marone, Vladimir Braverman, Dawn J. Lawrie, Benjamin Van Durme. 1413-1421 [doi]
• AcTune: Uncertainty-Based Active Self-Training for Active Fine-Tuning of Pretrained Language ModelsYue Yu, Lingkai Kong, Jieyu Zhang, Rongzhi Zhang, Chao Zhang. 1422-1436 [doi]
• Label Anchored Contrastive Learning for Language UnderstandingZhenyu Zhang, Yuming Zhao, Meng Chen, Xiaodong He 0002. 1437-1449 [doi]
• Go Back in Time: Generating Flashbacks in Stories with Event Temporal PromptsRujun Han, Hong Chen, Yufei Tian, Nanyun Peng. 1450-1470 [doi]
• Forecasting COVID-19 Caseloads Using Unsupervised Embedding Clusters of Social Media PostsFelix Drinkall, Stefan Zohren, Janet B. Pierrehumbert. 1471-1484 [doi]
• Many Hands Make Light Work: Using Essay Traits to Automatically Score EssaysRahul Kumar, Sandeep Mathias, Sriparna Saha 0001, Pushpak Bhattacharyya. 1485-1495 [doi]
• Natural Language Inference with Self-Attention for Veracity Assessment of Pandemic ClaimsMiguel Arana-Catania, Elena Kochkina, Arkaitz Zubiaga, Maria Liakata, Robert Procter, Yulan He 0001. 1496-1511 [doi]
• Beyond Emotion: A Multi-Modal Dataset for Human Desire UnderstandingAo Jia, Yu He, Yazhou Zhang, Sagar Uprety, Dawei Song 0001, Christina Lioma. 1512-1522 [doi]
• Relation-Specific Attentions over Entity Mentions for Enhanced Document-Level Relation ExtractionJiaxin Yu, Deqing Yang, Shuyu Tian. 1523-1529 [doi]
• Twitter-COMMs: Detecting Climate, COVID, and Military Multimodal MisinformationGiscard Biamby, Grace Luo, Trevor Darrell, Anna Rohrbach. 1530-1549 [doi]
• BlonDe: An Automatic Evaluation Metric for Document-level Machine TranslationYuchen Jiang, Tianyu Liu, Shuming Ma, Dongdong Zhang 0001, Jian Yang, Haoyang Huang, Rico Sennrich, Ryan Cotterell, Mrinmaya Sachan, Ming Zhou 0001. 1550-1565 [doi]
• Disentangled Learning of Stance and Aspect Topics for Vaccine Attitude Detection in Social MediaLixing Zhu, Zheng Fang, Gabriele Pergola, Robert Procter, Yulan He 0001. 1566-1580 [doi]
• SKILL: Structured Knowledge Infusion for Large Language ModelsFedor Moiseev, Zhe Dong, Enrique Alfonseca, Martin Jaggi. 1581-1588 [doi]
• Same Neurons, Different Languages: Probing Morphosyntax in Multilingual Pre-trained ModelsKarolina Stanczak, Edoardo M. Ponti, Lucas Torroba Hennigen, Ryan Cotterell, Isabelle Augenstein. 1589-1598 [doi]
• Aspect Is Not You Need: No-aspect Differential Sentiment Framework for Aspect-based Sentiment AnalysisJiahao Cao, Rui Liu, Huailiang Peng, Lei Jiang, Xu Bai. 1599-1609 [doi]
• MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided AdaptationSimiao Zuo, Qingru Zhang, Chen Liang, Pengcheng He, Tuo Zhao, Weizhu Chen. 1610-1623 [doi]
• Implicit n-grams Induced by RecurrenceXiaobing Sun, Wei Lu. 1624-1639 [doi]
• Guiding Visual Question GenerationNihir Vedd, Zixu Wang, Marek Rei, Yishu Miao, Lucia Specia. 1640-1654 [doi]
• OPERA: Operation-Pivoted Discrete Reasoning over TextYongwei Zhou, Junwei Bao 0001, Chaoqun Duan, Haipeng Sun, Jiahui Liang, Yifan Wang, Jing Zhao, Youzheng Wu, Xiaodong He 0002, Tiejun Zhao. 1655-1666 [doi]
• Improving Multi-Document Summarization through Referenced Flexible Extraction with Credit-AwarenessYun-Zhu Song, Yi-Syuan Chen, Hong-Han Shuai. 1667-1681 [doi]
• Improving Constituent Representation with Hypertree Neural NetworksHao Zhou, Gongshen Liu, Kewei Tu. 1682-1692 [doi]
• Measuring Fairness with Biased Rulers: A Comparative Study on Bias Metrics for Pre-trained Language ModelsPieter Delobelle, Ewoenam Kwaku Tokpo, Toon Calders, Bettina Berendt. 1693-1706 [doi]
• MuCPAD: A Multi-Domain Chinese Predicate-Argument DatasetYahui Liu, Haoping Yang, Chen Gong, Qingrong Xia, Zhenghua Li, Min Zhang 0005. 1707-1717 [doi]
• Representation Learning for Conversational Data using Discourse Mutual Information MaximizationBishal Santra, Sumegh Roychowdhury, Aishik Mandal, Vasu Gurram, Atharva Naik, Manish Gupta, Pawan Goyal 0002. 1718-1734 [doi]
• ValCAT: Variable-Length Contextualized Adversarial Transformations Using Encoder-Decoder Language ModelChuyun Deng, Mingxuan Liu, Yue Qin, Jia Zhang, Hai-Xin Duan, Donghong Sun. 1735-1746 [doi]
• A Study of Syntactic Multi-Modality in Non-Autoregressive Machine TranslationKexun Zhang, Rui Wang, Xu Tan 0003, Junliang Guo, Yi Ren 0006, Tao Qin, Tie-Yan Liu. 1747-1757 [doi]
• CIAug: Equipping Interpolative Augmentation with Curriculum LearningRamit Sawhney, Ritesh Soun, Shrey Pandit, Megh Thakkar, Sarvagya Malaviya, Yuval Pinter. 1758-1764 [doi]
• Proposition-Level Clustering for Multi-Document SummarizationOri Ernst, Avi Caciularu, Ori Shapira, Ramakanth Pasunuru, Mohit Bansal, Jacob Goldberger, Ido Dagan. 1765-1779 [doi]
• Non-Autoregressive Machine Translation: It's Not as Fast as it SeemsJindrich Helcl, Barry Haddow, Alexandra Birch. 1780-1790 [doi]
• BAD-X: Bilingual Adapters Improve Zero-Shot Cross-Lingual TransferMarinela Parovic, Goran Glavas, Ivan Vulic, Anna Korhonen. 1791-1799 [doi]
• Combining Humor and Sarcasm for Improving Political Parody DetectionXiao Ao, Danae Sanchez Villegas, Daniel Preotiuc-Pietro, Nikolaos Aletras. 1800-1807 [doi]
• TIE: Topological Information Enhanced Structural Reading Comprehension on Web PagesZihan Zhao, Lu Chen, Ruisheng Cao, Hongshen Xu, Xingyu Chen, Kai Yu 0004. 1808-1821 [doi]
• RSTGen: Imbuing Fine-Grained Interpretable Control into Long-FormText GeneratorsRilwan Adewoyin, Ritabrata Dutta, Yulan He 0001. 1822-1835 [doi]
• Intent Detection and Discovery from User Logs via Deep Semi-Supervised Contrastive ClusteringRajat Kumar, Mayur Patidar, Vaibhav Varshney, Lovekesh Vig, Gautam Shroff. 1836-1853 [doi]
• Extending Multi-Text Sentence Fusion Resources via Pyramid AnnotationsDaniela Brook Weiss, Paul Roit, Ori Ernst, Ido Dagan. 1854-1860 [doi]
• The Devil is in the Details: On the Pitfalls of Vocabulary Selection in Neural Machine TranslationTobias Domhan, Eva Hasler, Ke Tran, Sony Trenous, Bill Byrne, Felix Hieber. 1861-1874 [doi]
• MultiCite: Modeling realistic citations requires moving beyond the single-sentence single-label settingAnne Lauscher, Brandon Ko, Bailey Kuehl, Sophie Johnson, Arman Cohan, David Jurgens, Kyle Lo. 1875-1889 [doi]
• DEGREE: A Data-Efficient Generation-Based Event Extraction ModelI-Hung Hsu, Kuan-Hao Huang, Elizabeth Boschee, Scott Miller, Prem Natarajan, Kai-Wei Chang, Nanyun Peng. 1890-1908 [doi]
• Bridging the Gap between Language Models and Cross-Lingual Sequence LabelingNuo Chen, Linjun Shou, Ming Gong, Jian Pei, Daxin Jiang. 1909-1923 [doi]
• Hero-Gang Neural Model For Named Entity RecognitionJinpeng Hu, Yaling Shen, Yang Liu, Xiang Wan, Tsung-Hui Chang. 1924-1936 [doi]
• MGIMN: Multi-Grained Interactive Matching Network for Few-shot Text ClassificationJianhai Zhang, Mieradilijiang Maimaiti, Gao Xing, Yuanhang Zheng, Ji Zhang. 1937-1946 [doi]
• All You May Need for VQA are Image CaptionsSoravit Changpinyo, Doron Kukliansy, Idan Szpektor, Xi Chen, Nan Ding 0002, Radu Soricut. 1947-1963 [doi]
• Frustratingly Easy System Combination for Grammatical Error CorrectionMuhammad Qorib, Seung-Hoon Na, Hwee Tou Ng. 1964-1974 [doi]
• Simple Local Attentions Remain Competitive for Long-Context TasksWenhan Xiong, Barlas Oguz, Anchit Gupta, Xilun Chen, Diana Liskovich, Omer Levy, Scott Yih, Yashar Mehdad. 1975-1986 [doi]
• Even the Simplest Baseline Needs Careful Re-investigation: A Case Study on XML-CNNSi-An Chen, Jie-Jyun Liu, Tsung-Han Yang, Hsuan-Tien Lin, Chih-Jen Lin. 1987-2000 [doi]
• Multi-Relational Graph Transformer for Automatic Short Answer GradingRajat Agarwal, Varun Khurana, Karish Grover, Mukesh K. Mohania, Vikram Goyal. 2001-2012 [doi]
• Event Schema Induction with Double Graph AutoencodersXiaomeng Jin, Manling Li, Heng Ji. 2013-2025 [doi]
• CS1QA: A Dataset for Assisting Code-based Question Answering in an Introductory Programming CourseChangyoon Lee, Yeon Seonwoo, Alice Oh. 2026-2040 [doi]
• Unsupervised Cross-Lingual Transfer of Structured Predictors without Source DataKemal Kurniawan, Lea Frermann, Philip Schulz, Trevor Cohn. 2041-2054 [doi]
• Don't Take It Literally: An Edit-Invariant Sequence Loss for Text GenerationGuangyi Liu, Zichao Yang, Tianhua Tao, Xiaodan Liang, Junwei Bao 0001, Zhen Li 0026, Xiaodong He 0002, Shuguang Cui, Zhiting Hu. 2055-2078 [doi]
• Modeling Exemplification in Long-form Question Answering via RetrievalShufan Wang, Fangyuan Xu, Laure Thompson, Eunsol Choi, Mohit Iyyer. 2079-2092 [doi]
• D2U: Distance-to-Uniform Learning for Out-of-Scope DetectionEyup Halit Yilmaz, Cagri Toraman. 2093-2108 [doi]
• Reference-free Summarization Evaluation via Semantic Correlation and Compression RatioYizhu Liu, Qi Jia 0003, Kenny Q. Zhu. 2109-2115 [doi]
• KroneckerBERT: Significant Compression of Pre-trained Language Models Through Kronecker Decomposition and Knowledge DistillationMarzieh S. Tahaei, Ella Charlaix, Vahid Partovi Nia, Ali Ghodsi 0001, Mehdi Rezagholizadeh. 2116-2127 [doi]
• Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language ModelsSanghwan Bae, Dong-Hyun Kwak, Sungdong Kim, DongHoon Ham, Soyoung Kang, Sang-Woo Lee, Woo-Myoung Park. 2128-2150 [doi]
• Sentence-Level Resampling for Named Entity RecognitionXiaochen Wang, Yue Wang. 2151-2165 [doi]
• Word Tour: One-dimensional Word Embeddings via the Traveling Salesman ProblemRyoma Sato. 2166-2172 [doi]
• On the Diversity and Limits of Human ExplanationsChenhao Tan. 2173-2188 [doi]
• Locally Aggregated Feature Attribution on Natural Language Model UnderstandingSheng Zhang, Jin Wang, Haitao Jiang, Rui Song. 2189-2201 [doi]
• Generic and Trend-aware Curriculum Learning for Relation ExtractionNidhi Vakil, Hadi Amiri. 2202-2213 [doi]
• On Systematic Style Differences between Unsupervised and Supervised MT and an Application for High-Resource Machine TranslationKelly Marchisio, Markus Freitag, David Grangier. 2214-2225 [doi]
• Evidentiality-guided Generation for Knowledge-Intensive NLP TasksAkari Asai, Matt Gardner 0001, Hannaneh Hajishirzi. 2226-2243 [doi]
• Modularized Transfer Learning with Multiple Knowledge Graphs for Zero-shot Commonsense ReasoningYu-Jin Kim, Beong-woo Kwak, Youngwook Kim, Reinald Kim Amplayo, Seung-won Hwang, Jinyoung Yeo. 2244-2257 [doi]
• Learning to Express in Knowledge-Grounded ConversationXueliang Zhao, Tingchen Fu, Chongyang Tao, Wei Wu 0014, Dongyan Zhao 0001, Rui Yan 0001. 2258-2273 [doi]
• End-to-End Chinese Speaker IdentificationDian Yu, Ben Zhou, Dong Yu. 2274-2285 [doi]
• MINION: a Large-Scale and Diverse Dataset for Multilingual Event DetectionAmir Pouran Ben Veyseh, Minh Van Nguyen, Franck Dernoncourt, Thien Nguyen. 2286-2299 [doi]
• Do Prompt-Based Models Really Understand the Meaning of Their Prompts?Albert Webson, Ellie Pavlick. 2300-2344 [doi]
• GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense RetrievalKexin Wang, Nandan Thakur, Nils Reimers 0001, Iryna Gurevych. 2345-2360 [doi]
• Sparse Distillation: Speeding Up Text Classification by Using Bigger Student ModelsQinyuan Ye, Madian Khabsa, Mike Lewis, Sinong Wang, Xiang Ren, Aaron Jaech. 2361-2375 [doi]
• Towards Understanding Large-Scale Discourse Structures in Pre-Trained and Fine-Tuned Language ModelsPatrick Huber, Giuseppe Carenini. 2376-2394 [doi]
• SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation ExtractionYuxin Xiao, Zecheng Zhang, Yuning Mao, Carl Yang, Jiawei Han 0001. 2395-2409 [doi]
• LITE: Intent-based Task Representation Learning Using Weak SupervisionNaoki Otani, Michael Gamon, Sujay Kumar Jauhar, Mei Yang, Sri Raghu Malireddi, Oriana Riva. 2410-2424 [doi]
• Does Summary Evaluation Survive Translation to Other Languages?Spencer Braun, Oleg V. Vasilyev 0001, Neslihan Iskender, John Bohannon. 2425-2435 [doi]
• A Shoulder to Cry on: Towards A Motivational Virtual Assistant for Assuaging Mental AgonyTulika Saha, Saichethan Miriyala Reddy, Anindya Sundar Das 0002, Sriparna Saha 0001, Pushpak Bhattacharyya. 2436-2449 [doi]
• SueNes: A Weakly Supervised Approach to Evaluating Single-Document Summarization via Negative SamplingForrest Sheng Bao, Ge Luo 0002, Hebi Li, Minghui Qiu, Yinfei Yang, Youbiao He, Cen Chen. 2450-2458 [doi]
• Combating the Curse of Multilinguality in Cross-Lingual WSD by Aligning Sparse Contextualized Word RepresentationsGábor Berend. 2459-2471 [doi]
• Cheat Codes to Quantify Missing Source Information in Neural Machine TranslationProyag Pal, Kenneth Heafield. 2472-2477 [doi]
• WiC = TSV = WSD: On the Equivalence of Three Semantic TasksBradley Hauer, Grzegorz Kondrak. 2478-2486 [doi]
• What do tokens know about their characters and how do they know it?Ayush Kaushal, Kyle Mahowald. 2487-2507 [doi]
• AnswerSumm: A Manually-Curated Dataset and Pipeline for Answer SummarizationAlexander R. Fabbri, XiaoJian Wu, Srini Iyer, Haoran Li, Mona Diab. 2508-2520 [doi]
• Paragraph-based Transformer Pre-training for Multi-Sentence InferenceLuca Di Liello, Siddhant Garg, Luca Soldaini, Alessandro Moschitti. 2521-2531 [doi]
• Text Style Transfer via Optimal TransportNasim Nouri. 2532-2541 [doi]
• Exploring the Role of Task Transferability in Large-Scale Multi-Task LearningVishakh Padmakumar, Leonard Lausen, Miguel Ballesteros, Sheng Zha, He He 0001, George Karypis. 2542-2550 [doi]
• Interactive Query-Assisted Summarization via Deep Reinforcement LearningOri Shapira, Ramakanth Pasunuru, Mohit Bansal, Ido Dagan, Yael Amsterdamer. 2551-2568 [doi]
• Data Augmentation with Dual Training for Offensive Span DetectionNasim Nouri. 2569-2575 [doi]
• Training Mixed-Domain Translation Models via Federated LearningPeyman Passban, Tanya G. Roosta, Rahul Gupta, Ankit Chadha, Clement Chung. 2576-2586 [doi]
• QAFactEval: Improved QA-Based Factual Consistency Evaluation for SummarizationAlexander R. Fabbri, Chien-Sheng Wu, Wenhao Liu, Caiming Xiong. 2587-2601 [doi]
• How Gender Debiasing Affects Internal Model Representations, and Why It MattersHadas Orgad, Seraphina Goldfarb-Tarrant, Yonatan Belinkov. 2602-2628 [doi]
• A Structured Span SelectorTianyu Liu, Yuchen Eleanor Jiang, Ryan Cotterell, Mrinmaya Sachan. 2629-2641 [doi]
• Unified Semantic Typing with Meaningful Label InferenceJames Y. Huang, Bangzheng Li, Jiashu Xu, Muhao Chen. 2642-2654 [doi]
• Learning To Retrieve Prompts for In-Context LearningOhad Rubin, Jonathan Herzig, Jonathan Berant. 2655-2671 [doi]
• Necessity and Sufficiency for Explaining Text Classifiers: A Case Study in Hate Speech DetectionEsma Balkir, Isar Nejadgholi, Kathleen C. Fraser, Svetlana Kiritchenko. 2672-2686 [doi]
• Learning to Retrieve Passages without SupervisionOri Ram, Gal Shachaf, Omer Levy, Jonathan Berant, Amir Globerson. 2687-2700 [doi]
• Re2G: Retrieve, Rerank, GenerateMichael R. Glass, Gaetano Rossiello, Md. Faisal Mahbub Chowdhury, Ankita Naik, Pengshan Cai, Alfio Gliozzo. 2701-2715 [doi]
• Don't sweat the small stuff, classify the rest: Sample Shielding to protect text classifiers against adversarial attacksJonathan Rusert, Padmini Srinivasan. 2716-2725 [doi]
• Federated Learning with Noisy User FeedbackRahul Sharma, Anil Ramakrishna, Ansel MacLaughlin, Anna Rumshisky, Jimit Majmudar, Clement Chung, Salman Avestimehr, Rahul Gupta. 2726-2739 [doi]
• Gender Bias in Masked Language Models for Multiple LanguagesMasahiro Kaneko, Aizhan Imankulova, Danushka Bollegala, Naoaki Okazaki. 2740-2750 [doi]
• Multi-Domain Targeted Sentiment AnalysisOrith Toledo-Ronen, Matan Orbach, Yoav Katz, Noam Slonim. 2751-2762 [doi]
• Falsesum: Generating Document-level NLI Examples for Recognizing Factual Inconsistency in SummarizationPrasetya Utama, Joshua Bambrick, Nafise Sadat Moosavi, Iryna Gurevych. 2763-2776 [doi]
• Dynamic Gazetteer Integration in Multilingual Models for Cross-Lingual and Cross-Domain Named Entity RecognitionBesnik Fetahu, Anjie Fang, Oleg Rokhlenko, Shervin Malmasi. 2777-2790 [doi]
• MetaICL: Learning to Learn In ContextSewon Min, Mike Lewis, Luke Zettlemoyer, Hannaneh Hajishirzi. 2791-2809 [doi]
• Enhancing Knowledge Selection for Grounded Dialogues via Document Semantic GraphsSha Li, Mahdi Namazifar, Di Jin, Mohit Bansal, Heng Ji, Yang Liu 0004, Dilek Hakkani-Tur. 2810-2823 [doi]
• Using Natural Sentence Prompts for Understanding Biases in Language ModelsSarah Alnegheimish, Alicia Guo, Yi Sun. 2824-2830 [doi]
• Robust Conversational Agents against Imperceptible Toxicity TriggersNinareh Mehrabi, Ahmad Beirami, Fred Morstatter, Aram Galstyan. 2831-2847 [doi]
• Selective Differential Privacy for Language ModelingWeiyan Shi, Aiqi Cui, Evan Li, Ruoxi Jia, Zhou Yu. 2848-2859 [doi]
• Do Trajectories Encode Verb Meaning?Dylan Ebert, Chen Sun, Ellie Pavlick. 2860-2871 [doi]
• Long Context Question Answering via Supervised Contrastive LearningAvi Caciularu, Ido Dagan, Jacob Goldberger, Arman Cohan. 2872-2879 [doi]
• The USMLE® Step 2 Clinical Skills Patient Note CorpusVictoria Yaneva, Janet Mee, Le An Ha, Polina Harik, Michael Jodoin, Alex Mechaber. 2880-2886 [doi]
• Learning to Borrow- Relation Representation for Without-Mention Entity-Pairs for Knowledge Graph CompletionHuda Hakami, Mona Hakami, Angrosh Mandya, Danushka Bollegala. 2887-2898 [doi]
• Improving Entity Disambiguation by Reasoning over a Knowledge BaseTom Ayoola, Joseph Fisher, Andrea Pierleoni. 2899-2912 [doi]
• Modal Dependency Parsing via Language Model PrimingJiarui Yao, Nianwen Xue, Bonan Min. 2913-2919 [doi]
• Document-Level Relation Extraction with Sentences Importance Estimation and FocusingWang Xu, Kehai Chen, Lili Mou, Tiejun Zhao. 2920-2929 [doi]
• Are All the Datasets in Benchmark Necessary? A Pilot Study of Dataset Evaluation for Text ClassificationYang Xiao, JinLan Fu, See-Kiong Ng, Pengfei Liu 0003. 2930-2941 [doi]
• Triggerless Backdoor Attack for NLP Tasks with Clean LabelsLeilei Gan, Jiwei Li, Tianwei Zhang 0004, Xiaoya Li, Yuxian Meng, Fei Wu 0001, Yi Yang 0001, Shangwei Guo, Chun Fan. 2942-2952 [doi]
• PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided MCTS DecodingAntoine Chaffin, Vincent Claveau, Ewa Kijak. 2953-2967 [doi]
• Interpretable Proof Generation via Iterative Backward ReasoningHanhao Qu, Yu Cao, Jun Gao, Liang Ding, Ruifeng Xu. 2968-2981 [doi]
• Domain Confused Contrastive Learning for Unsupervised Domain AdaptationQuanyu Long, Tianze Luo, Wenya Wang, Sinno Jialin Pan. 2982-2995 [doi]
• Incorporating Centering Theory into Neural Coreference ResolutionHaixia Chai, Michael Strube 0001. 2996-3002 [doi]
• Progressive Class Semantic Matching for Semi-supervised Text ClassificationHai-ming Xu, Lingqiao Liu, Ehsan Abbasnejad. 3003-3013 [doi]
• Low Resource Style Transfer via Domain Adaptive Meta LearningXiangyang Li, Xiang Long, Yu Xia, Sujian Li. 3014-3026 [doi]
• Features or Spurious Artifacts? Data-centric Baselines for Fair and Robust Hate Speech DetectionAlan Ramponi, Sara Tonelli. 3027-3040 [doi]
• Document-Level Event Argument Extraction by Leveraging Redundant Information and Closed Boundary LossHanzhang Zhou, Kezhi Mao. 3041-3052 [doi]
• A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News TranslationDavid Ifeoluwa Adelani, Jesujoba O. Alabi, Angela Fan, Julia Kreutzer, Xiaoyu Shen 0001, Machel Reid, Dana Ruiter, Dietrich Klakow, Peter Nabende, Ernie Chang, Tajuddeen Gwadabe, Freshia Sackey, Bonaventure F. P. Dossou, Chris Emezue, Colin Leong, Michael Beukman, Shamsuddeen Hassan Muhammad, Guyo Dub Jarso, Oreen Yousuf, Andre Niyongabo Rubungo, Gilles Hacheme, Eric Peter Wairagala, Muhammad Umair Nasir, Benjamin Ajibade, Tunde Ajayi, Yvonne Wambui Gitau, Jade Z. Abbott, Mohamed Ahmed, Millicent Ochieng, Aremu Anuoluwapo, Perez Ogayo, Jonathan Mukiibi, Fatoumata Ouoba Kabore, Godson Kalipe, Derguene Mbaye, Allahsera Auguste Tapo, Victoire Memdjokam Koagne, Edwin Munkoh-Buabeng, Valencia Wagner, Idris Abdulmumin, Ayodele Awokoya, Happy Buzaaba, Blessing Sibanda, Andiswa Bukula, Sam Manthalu. 3053-3070 [doi]
• Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual AnalysisYiwei Wang, Muhao Chen, Wenxuan Zhou, Yujun Cai, Yuxuan Liang, Dayiheng Liu, Baosong Yang, Juncheng Liu, Bryan Hooi. 3071-3081 [doi]
• Analyzing Encoded Concepts in Transformer Language ModelsHassan Sajjad, Nadir Durrani, Fahim Dalvi, Firoj Alam, Abdul Rafae Khan, Jia Xu 0004. 3082-3101 [doi]
• Boosted Dense RetrieverPatrick Lewis, Barlas Oguz, Wenhan Xiong, Fabio Petroni, Scott Yih, Sebastian Riedel 0001. 3102-3117 [doi]
• MuCGEC: a Multi-Reference Multi-Source Evaluation Dataset for Chinese Grammatical Error CorrectionYue Zhang 0004, Zhenghua Li, Zuyi Bao, Jiacheng Li, Bo Zhang, Chen Li, Fei Huang, Min Zhang. 3118-3130 [doi]
• NeuS: Neutral Multi-News Summarization for Mitigating Framing BiasNayeon Lee, Yejin Bang, Tiezheng Yu, Andrea Madotto, Pascale Fung. 3131-3148 [doi]
• Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text GenerationShumpei Inoue, Tsungwei Liu, Son Nguyen, Minh-Tien Nguyen. 3149-3158 [doi]
• Efficient Constituency Tree based Encoding for Natural Language to Bash TranslationShikhar Bharadwaj, Shirish K. Shevade. 3159-3168 [doi]
• Privacy-Preserving Text Classification on BERT Embeddings with Homomorphic EncryptionGaram Lee, Minsoo Kim, Jai Hyun Park, Seung-won Hwang, Jung Hee Cheon. 3169-3175 [doi]
• ITA: Image-Text Alignments for Multi-Modal Named Entity RecognitionXinyu Wang, Min Gui, Yong Jiang, Zixia Jia, Nguyen Bach, Tao Wang, Zhongqiang Huang, Kewei Tu. 3176-3189 [doi]
• A Dataset for N-ary Relation Extraction of Drug CombinationsAryeh Tiktinsky, Vijay Viswanathan 0002, Danna Niezni, Dana Meron Azagury, Yosi Shamay, Hillel Taub-Tabib, Tom Hope, Yoav Goldberg. 3190-3203 [doi]
• Curriculum: A Broad-Coverage Benchmark for Linguistic Phenomena in Natural Language UnderstandingZeming Chen, Qiyue Gao. 3204-3219 [doi]
• Neural Language Taskonomy: Which NLP Tasks are the most Predictive of fMRI Brain Activity?Subba Reddy Oota, Jashn Arora, Veeral Agarwal, Mounika Marreddy, Manish Gupta 0001, Bapi Raju Surampudi. 3220-3237 [doi]
• FactGraph: Evaluating Factuality in Summarization with Semantic Graph RepresentationsLeonardo Ribeiro, Mengwen Liu, Iryna Gurevych, Markus Dreyer, Mohit Bansal. 3238-3253 [doi]
• Unsupervised Paraphrasability Prediction for Compound NominalizationsJohn Sie Yuen Lee, Ho Hung Lim, Carol Webster. 3254-3263 [doi]
• Global Entity Disambiguation with BERTIkuya Yamada, Koki Washio, Hiroyuki Shindo, Yuji Matsumoto 0001. 3264-3271 [doi]
• Clues Before Answers: Generation-Enhanced Multiple-Choice QAZixian Huang, Ao Wu, Jiaying Zhou, Yu Gu, Yue Zhao, Gong Cheng 0001. 3272-3287 [doi]
• Towards Efficient NLP: A Standard Evaluation and A Strong BaselineXiangyang Liu, Tianxiang Sun, Junliang He, Jiawen Wu, Lingling Wu, Xinyu Zhang, Hao Jiang, Zhao Cao, Xuanjing Huang, Xipeng Qiu. 3288-3303 [doi]
• Stylized Knowledge-Grounded Dialogue Generation via Disentangled Template RewritingQingfeng Sun, Can Xu, Huang Hu, Yujing Wang, Jian Miao, Xiubo Geng, Yining Chen, Fei Xu, Daxin Jiang. 3304-3318 [doi]
• LUNA: Learning Slot-Turn Alignment for Dialogue State TrackingYifan Wang, Jing Zhao, Junwei Bao 0001, Chaoqun Duan, Youzheng Wu, Xiaodong He 0002. 3319-3328 [doi]
• Crossroads, Buildings and Neighborhoods: A Dataset for Fine-grained Location RecognitionPei Chen, Haotian Xu, Cheng Zhang, Ruihong Huang. 3329-3339 [doi]
• Tricks for Training Sparse Translation ModelsDheeru Dua, Shruti Bhosale, Vedanuj Goswami, James Cross, Mike Lewis, Angela Fan. 3340-3345 [doi]
• Persona-Guided Planning for Controlling the Protagonist's Persona in Story GenerationZhexin Zhang, Jiaxin Wen, Jian Guan, Minlie Huang. 3346-3361 [doi]
• CHEF: A Pilot Chinese Dataset for Evidence-Based Fact-CheckingXuming Hu, Zhijiang Guo, Guanyu Wu, Aiwei Liu, Lijie Wen, Philip S. Yu. 3362-3376 [doi]
• VGNMN: Video-grounded Neural Module Networks for Video-Grounded Dialogue SystemsHung Le, Nancy F. Chen, Steven C. H. Hoi. 3377-3393 [doi]
• Multimodal Dialogue State TrackingHung Le, Nancy Chen, Steven Hoi. 3394-3415 [doi]
• On the Use of Bert for Automated Essay Scoring: Joint Learning of Multi-Scale Essay RepresentationYongJie Wang, Chuang Wang, Ruobing Li, Hui Lin. 3416-3425 [doi]
• Recognition of They/Them as Singular Personal Pronouns in Coreference ResolutionConnor Baumler, Rachel Rudinger. 3426-3432 [doi]
• TWEETSPIN: Fine-grained Propaganda Detection in Social Media Using Multi-View RepresentationsPrashanth Vijayaraghavan, Soroush Vosoughi. 3433-3448 [doi]
• UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment AnalysisFatemehsadat Mireshghallah, Vaishnavi Shrivastava, Milad Shokouhi, Taylor Berg-Kirkpatrick, Robert Sim, Dimitrios Dimitriadis. 3449-3456 [doi]
• Improving Neural Models for Radiology Report Retrieval with Lexicon-based Automated AnnotationLuyao Shi, Tanveer F. Syeda-Mahmood, Tyler Baldwin. 3457-3463 [doi]
• Transparent Human Evaluation for Image CaptioningJungo Kasai, Keisuke Sakaguchi, Lavinia Dunagan, Jacob Morrison, Ronan Le Bras, Yejin Choi, Noah Smith. 3464-3478 [doi]
• Lifting the Curse of Multilinguality by Pre-training Modular TransformersJonas Pfeiffer, Naman Goyal, Xi Victoria Lin, Xian Li, James Cross, Sebastian Riedel 0001, Mikel Artetxe. 3479-3495 [doi]
• DocAMR: Multi-Sentence AMR Representation and EvaluationTahira Naseem, Austin Blodgett, Sadhana Kumaravel, Tim O'Gorman, Young-Suk Lee, Jeffrey Flanigan, Ramón Fernandez Astudillo, Radu Florian, Salim Roukos, Nathan Schneider 0001. 3496-3505 [doi]
• Learning to Transfer Prompts for Text GenerationJunyi Li, Tianyi Tang, Jian-Yun Nie, Ji-Rong Wen, Xin Zhao. 3506-3518 [doi]
• ElitePLM: An Empirical Study on General Language Ability Evaluation of Pretrained Language ModelsJunyi Li, Tianyi Tang, Zheng Gong, Lixin Yang, Zhuohao Yu, Zhipeng Chen, Jingyuan Wang, Xin Zhao, Ji-Rong Wen. 3519-3539 [doi]
• Bidimensional Leaderboards: Generate and Evaluate Language Hand in HandJungo Kasai, Keisuke Sakaguchi, Ronan Le Bras, Lavinia Dunagan, Jacob Morrison, Alexander R. Fabbri, Yejin Choi, Noah A. Smith. 3540-3557 [doi]
• Improving In-Context Few-Shot Learning via Self-Supervised TrainingMingda Chen, Jingfei Du, Ramakanth Pasunuru, Todor Mihaylov, Srini Iyer, Veselin Stoyanov, Zornitsa Kozareva. 3558-3573 [doi]
• Exposing the Limits of Video-Text Models through Contrast SetsJae Sung Park, Sheng Shen, Ali Farhadi, Trevor Darrell, Yejin Choi, Anna Rohrbach. 3574-3586 [doi]
• Zero-shot Sonnet Generation with Discourse-level Planning and Aesthetics FeaturesYufei Tian, Nanyun Peng. 3587-3597 [doi]
• Benchmarking Intersectional Biases in NLPJohn Lalor, Yi Yang, Kendall Smith, Nicole Forsgren, Ahmed Abbasi. 3598-3609 [doi]
• When is BERT Multilingual? Isolating Crucial Ingredients for Cross-lingual TransferAmeet Deshpande, Partha Talukdar, Karthik Narasimhan. 3610-3623 [doi]
• How Conservative are Language Models? Adapting to the Introduction of Gender-Neutral PronounsStephanie Brandl, Ruixiang Cui, Anders Søgaard. 3624-3630 [doi]
• Prompt Waywardness: The Curious Case of Discretized Interpretation of Continuous PromptsDaniel Khashabi, Xinxi Lyu, Sewon Min, Lianhui Qin, Kyle Richardson 0001, Sean Welleck, Hannaneh Hajishirzi, Tushar Khot, Ashish Sabharwal, Sameer Singh 0001, Yejin Choi. 3631-3643 [doi]
• Contrastive Representation Learning for Cross-Document Coreference Resolution of Events and EntitiesBenjamin Hsu, Graham Horwood. 3644-3655 [doi]
• Learning the Ordering of Coordinate Compounds and Elaborate Expressions in Hmong, Lahu, and ChineseChenxuan Cui, Katherine J. Zhang, David R. Mortensen. 3656-3669 [doi]
• FRUIT: Faithfully Reflecting Updated Information in TextRobert L. Logan IV, Alexandre Passos, Sameer Singh 0001, Ming-Wei Chang. 3670-3686 [doi]
• Multi2WOZ: A Robust Multilingual Dataset and Conversational Pretraining for Task-Oriented DialogChia-Chien Hung, Anne Lauscher, Ivan Vulic, Simone Paolo Ponzetto, Goran Glavas. 3687-3703 [doi]
• ChapterBreak: A Challenge Dataset for Long-Range Language ModelsSimeng Sun, Katherine Thai, Mohit Iyyer. 3704-3714 [doi]
• ColBERTv2: Effective and Efficient Retrieval via Lightweight Late InteractionKeshav Santhanam, Omar Khattab, Jon Saad-Falcon, Christopher Potts, Matei Zaharia. 3715-3734 [doi]
• Quantifying Language Variation Acoustically with Few ResourcesMartijn Bartelds, Martijn Wieling. 3735-3741 [doi]
• Adaptable AdaptersNafise Sadat Moosavi, Quentin Delfosse, Kristian Kersting, Iryna Gurevych. 3742-3753 [doi]
• Models in the Loop: Aiding Crowdworkers with Generative Annotation AssistantsMax Bartolo, Tristan Thrush, Sebastian Riedel 0001, Pontus Stenetorp, Robin Jia, Douwe Kiela. 3754-3767 [doi]
• GMN: Generative Multi-modal Network for Practical Document Information ExtractionHaoyu Cao, Jiefeng Ma, Antai Guo, Yiqing Hu, Hao Liu, Deqiang Jiang, Yinsong Liu, Bo Ren. 3768-3778 [doi]
• One Reference Is Not Enough: Diverse Distillation with Reference Selection for Non-Autoregressive TranslationChenze Shao, Xuanfu Wu, Yang Feng 0004. 3779-3791 [doi]
• Can Rationalization Improve Robustness?Howard Chen 0003, Jacqueline He, Karthik Narasimhan, Danqi Chen. 3792-3805 [doi]
• On the Effectiveness of Sentence Encoding for Intent Detection Meta-LearningTingting Ma, Qianhui Wu, Zhiwei Yu, Tiejun Zhao, Chin-Yew Lin. 3806-3818 [doi]
• A Computational Acquisition Model for Multimodal Word CategorizationUri Berger, Gabriel Stanovsky, Omri Abend, Lea Frermann. 3819-3835 [doi]
• Residue-Based Natural Language Adversarial Attack DetectionVyas Raina, Mark J. F. Gales. 3836-3848 [doi]
• Does it Really Generalize Well on Unseen Data? Systematic Evaluation of Relational Triple Extraction MethodsJuhyuk Lee, Min-Joong Lee, June Yong Yang, Eunho Yang. 3849-3858 [doi]
• From spoken dialogue to formal summary: An utterance rewriting for dialogue summarizationYue Fang, Hainan Zhang, Hongshen Chen, Zhuoye Ding, Bo Long, Yanyan Lan, Yanquan Zhou. 3859-3869 [doi]
• EASE: Entity-Aware Contrastive Learning of Sentence EmbeddingSosuke Nishikawa, Ryokan Ri, Ikuya Yamada, Yoshimasa Tsuruoka, Isao Echizen. 3870-3885 [doi]
• Is Neural Topic Modelling Better than Clustering? An Empirical Study on Clustering with Contextual Embeddings for TopicsZihan Zhang, Meng Fang, Ling Chen, Mohammad-Reza Namazi-Rad. 3886-3893 [doi]
• Dynamic Multistep Reasoning based on Video Scene Graph for Video Question AnsweringJianguo Mao, Wenbin Jiang, Xiangdong Wang, Zhifan Feng, Yajuan Lyu, Hong Liu 0007, Yong Zhu 0004. 3894-3904 [doi]
• TRUE: Re-evaluating Factual Consistency EvaluationOr Honovich, Roee Aharoni, Jonathan Herzig, Hagai Taitelbaum, Doron Kukliansy, Vered Cohen, Thomas Scialom, Idan Szpektor, Avinatan Hassidim, Yossi Matias. 3905-3920 [doi]
• Knowledge Inheritance for Pre-trained Language ModelsYujia Qin, Yankai Lin, Jing Yi, Jiajie Zhang, Xu Han 0007, Zhengyan Zhang, Yusheng Su, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou 0016. 3921-3937 [doi]
• Bi-SimCut: A Simple Strategy for Boosting Neural Machine TranslationPengzhi Gao, Zhongjun He, Hua Wu 0003, Haifeng Wang 0001. 3938-3948 [doi]
• On Transferability of Prompt Tuning for Natural Language ProcessingYusheng Su, Xiaozhi Wang, Yujia Qin, Chi-Min Chan, Yankai Lin, Huadong Wang, Kaiyue Wen, Zhiyuan Liu, Peng Li, Juanzi Li, Lei Hou 0001, Maosong Sun, Jie Zhou. 3949-3969 [doi]
• DocEE: A Large-Scale and Fine-grained Benchmark for Document-level Event ExtractionMeihan Tong, Bin Xu 0001, Shuai Wang 0030, Meihuan Han, Yixin Cao 0002, Jiangqi Zhu, Siyu Chen, Lei Hou, Juanzi Li. 3970-3982 [doi]
• Towards Debiasing Translation ArtifactsKoel Dutta Chowdhury, Rricha Jalota, Cristina España-Bonet, Josef van Genabith. 3983-3991 [doi]
• WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language modelsBenjamin Minixhofer, Fabian Paischer, Navid Rekabsaz. 3992-4006 [doi]
• A New Concept of Knowledge based Question Answering (KBQA) System for Multi-hop ReasoningYu Wang 0091, Vijay Srinivasan, Hongxia Jin. 4007-4017 [doi]
• Bilingual Tabular Inference: A Case Study on Indic LanguagesChaitanya Agarwal, Vivek Gupta, Anoop Kunchukuttan, Manish Shrivastava. 4018-4037 [doi]
• Generative Biomedical Entity Linking via Knowledge Base-Guided Pre-training and Synonyms-Aware Fine-tuningHongyi Yuan, Zheng Yuan 0002, Sheng Yu 0002. 4038-4048 [doi]
• Robust Self-Augmentation for Named Entity Recognition with Meta ReweightingLinzhi Wu, Pengjun Xie, Jie Zhou 0013, Meishan Zhang, Chunping Ma, Guangwei Xu, Min Zhang. 4049-4060 [doi]
• Unsupervised Stem-based Cross-lingual Part-of-Speech Tagging for Morphologically Rich Low-Resource LanguagesRamy Eskander, Cass Lowry, Sujay Khandagale, Judith Klavans, Maria Polinsky, Smaranda Muresan. 4061-4072 [doi]
• Optimising Equal Opportunity Fairness in Model TrainingAili Shen, Xudong Han, Trevor Cohn, Timothy Baldwin, Lea Frermann. 4073-4084 [doi]
• Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image RetrievalSiyu Ren, Kenny Q. Zhu. 4085-4090 [doi]
• Joint Learning-based Heterogeneous Graph Attention Network for Timeline SummarizationJingyi You, Dongyuan Li, Hidetaka Kamigaito, Kotaro Funakoshi, Manabu Okumura. 4091-4104 [doi]
• Early Rumor Detection Using Neural Hawkes Process with a New Benchmark DatasetFengzhu Zeng, Wei Gao. 4105-4117 [doi]
• Emp-RFT: Empathetic Response Generation via Recognizing Feature Transitions between UtterancesWongyu Kim, Youbin Ahn, Donghyun Kim, Kyong-Ho Lee. 4118-4128 [doi]
• KCD: Knowledge Walks and Textual Cues Enhanced Political Perspective Detection in News MediaWenqian Zhang, Shangbin Feng, Zilong Chen, Zhenyu Lei, Jundong Li, Minnan Luo. 4129-4140 [doi]
• Collective Relevance Labeling for Passage RetrievalJihyuk Kim, Minsoo Kim, Seung-won Hwang. 4141-4147 [doi]
• COGMEN: COntextualized GNN based Multimodal Emotion recognitioNAbhinav Joshi, Ashwani Bhat, Ayush Jain, Atin Vikram Singh, Ashutosh Modi. 4148-4164 [doi]
• Revisit Overconfidence for OOD Detection: Reassigned Contrastive Learning with Adaptive Class-dependent ThresholdYanan Wu, Keqing He, Yuanmeng Yan, QiXiang Gao, Zhiyuan Zeng, Fujia Zheng, Lulu Zhao, Huixing Jiang, Wei Wu, Weiran Xu. 4165-4179 [doi]
• AISFG: Abundant Information Slot Filling GeneratorYang Yan, Junda Ye, Zhongbao Zhang, Liwen Wang. 4180-4187 [doi]
• Improving negation detection with negation-focused pre-trainingThinh Hung Truong, Timothy Baldwin, Trevor Cohn, Karin Verspoor. 4188-4193 [doi]
• Practice Makes a Solver Perfect: Data Augmentation for Math Word Problem SolversVivek Kumar, Rishabh Maheshwary, Vikram Pudi. 4194-4206 [doi]
• DiffCSE: Difference-based Contrastive Learning for Sentence EmbeddingsYung-Sung Chuang, Rumen Dangovski, Hongyin Luo, Yang Zhang, Shiyu Chang, Marin Soljacic, Shang-wen Li 0001, Scott Yih, Yoon Kim, James R. Glass. 4207-4218 [doi]
• Generative Cross-Domain Data Augmentation for Aspect and Opinion Co-ExtractionJunjie Li, Jianfei Yu, Rui Xia. 4219-4229 [doi]
• ProQA: Structural Prompt-based Pre-training for Unified Question AnsweringWanjun Zhong, YiFan Gao, Ning Ding, Yujia Qin, Zhiyuan Liu, Ming Zhou 0001, Jiahai Wang, Jian Yin 0001, Nan Duan. 4230-4243 [doi]
• A Data Cartography based MixUp for Pre-trained Language ModelsSeoyeon Park, Cornelia Caragea. 4244-4250 [doi]
• Grapheme-to-Phoneme Conversion for Thai using Neural Regression ModelsTomohiro Yamasaki. 4251-4255 [doi]
• Generating Authentic Adversarial Examples beyond Meaning-preserving with Doubly Round-trip TranslationSiyu Lai, Zhen Yang, Fandong Meng, Xue Zhang, Yufeng Chen, Jinan Xu, Jie Zhou 0016. 4256-4266 [doi]
• TVShowGuess: Character Comprehension in Stories as Speaker GuessingYisi Sang, Xiangyang Mou, Mo Yu, Shunyu Yao, Jing Li, Jeffrey Stanton. 4267-4287 [doi]
• Causal Distillation for Language ModelsZhengxuan Wu, Atticus Geiger, Joshua Rozner, Elisa Kreiss, Hanson Lu, Thomas Icard, Christopher Potts, Noah D. Goodman. 4288-4295 [doi]
• FNet: Mixing Tokens with Fourier TransformsJames Lee-Thorp, Joshua Ainslie, Ilya Eckstein, Santiago Ontañón. 4296-4313 [doi]
• Answer Consolidation: Formulation and BenchmarkingWenxuan Zhou, Qiang Ning, Heba Elfardy, Kevin Small, Muhao Chen. 4314-4325 [doi]
• Informativeness and Invariance: Two Perspectives on Spurious Correlations in Natural LanguageJacob Eisenstein. 4326-4331 [doi]
• FOAM: A Follower-aware Speaker Model For Vision-and-Language NavigationZi-Yi Dou, Nanyun Peng. 4332-4340 [doi]
• Improving Compositional Generalization with Latent Structure and Data AugmentationLinlu Qiu, Peter Shaw, Panupong Pasupat, Pawel Krzysztof Nowak, Tal Linzen, Fei Sha, Kristina Toutanova. 4341-4362 [doi]
• Joint Extraction of Entities, Relations, and Events via Modeling Inter-Instance and Inter-Label DependenciesMinh Van Nguyen, Bonan Min, Franck Dernoncourt, Thien Nguyen. 4363-4374 [doi]
• Linguistic Frameworks Go Toe-to-Toe at Neuro-Symbolic Language ModelingJakob Prange, Nathan Schneider 0001, Lingpeng Kong. 4375-4391 [doi]
• Imagination-Augmented Natural Language UnderstandingYujie Lu, Wanrong Zhu, Xin Wang 0061, Miguel Eckstein, William Yang Wang. 4392-4402 [doi]
• What company do words keep? Revisiting the distributional semantics of J.R. Firth & Zellig HarrisMikael Brunila, Jack LaViolette. 4403-4417 [doi]
• Compositional Task-Oriented Parsing as Abstractive Question AnsweringWenting Zhao, Konstantine Arkoudas, Weiqi Sun, Claire Cardie. 4418-4427 [doi]
• Learning Cross-Lingual IR from an English RetrieverYulong Li, Martin Franz, Md. Arafat Sultan, Bhavani Iyer, Young-Suk Lee, Avirup Sil. 4428-4436 [doi]
• Testing the Ability of Language Models to Interpret Figurative LanguageEmmy Liu, Chenxuan Cui, Kenneth Zheng, Graham Neubig. 4437-4452 [doi]
• Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document SimilaritySheshera Mysore, Arman Cohan, Tom Hope. 4453-4470 [doi]
• CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement LearningSiddharth Verma, Justin Fu, Sherry Yang, Sergey Levine. 4471-4491 [doi]
• Connecting the Dots between Audio and Text without Parallel Data through Visual Knowledge TransferYanpeng Zhao, Jack Hessel, Youngjae Yu, Ximing Lu, Rowan Zellers, Yejin Choi. 4492-4507 [doi]
• SURF: Semantic-level Unsupervised Reward Function for Machine TranslationAtijit Anuchitanukul, Julia Ive. 4508-4522 [doi]
• Disentangling Categorization in Multi-agent Emergent CommunicationWashington Garcia, Hamilton Clouse, Kevin R. B. Butler. 4523-4540 [doi]
• Show, Don't Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented DialogueRaghav Gupta, Harrison Lee 0001, Jeffrey Zhao, Yuan Cao 0007, Abhinav Rastogi, Yonghui Wu. 4541-4549 [doi]
• Does Pre-training Induce Systematic Inference? How Masked Language Models Acquire Commonsense KnowledgeIan Porada, Alessandro Sordoni, Jackie Chi Kit Cheung. 4550-4557 [doi]
• Using Paraphrases to Study Properties of Contextual EmbeddingsLaura Burdick, Jonathan K. Kummerfeld, Rada Mihalcea. 4558-4568 [doi]
• Measure and Improve Robustness in NLP Models: A SurveyXuezhi Wang 0002, Haohan Wang, Diyi Yang. 4569-4586 [doi]
• Learning to Generate Examples for Semantic Processing TasksDanilo Croce, Simone Filice, Giuseppe Castellucci, Roberto Basili 0001. 4587-4601 [doi]
• Symbolic Knowledge Distillation: from General Language Models to Commonsense ModelsPeter West, Chandra Bhagavatula, Jack Hessel, Jena D. Hwang, Liwei Jiang, Ronan Le Bras, Ximing Lu, Sean Welleck, Yejin Choi. 4602-4625 [doi]
• GenIE: Generative Information ExtractionMartin Josifoski, Nicola De Cao, Maxime Peyrard, Fabio Petroni, Robert West 0001. 4626-4643 [doi]
• Entity Linking via Explicit Mention-Mention Coreference ModelingDhruv Agarwal 0003, Rico Angell, Nicholas Monath, Andrew McCallum. 4644-4658 [doi]
• Massive-scale Decoding for Text Generation using LatticesJiacheng Xu, Siddhartha Jonnalagadda, Greg Durrett. 4659-4676 [doi]
• Disentangling Indirect Answers to Yes-No Questions in Real ConversationsKrishna Chaitanya Sanagavarapu, Jathin Singaraju, Anusha Kakileti, Anirudh Kaza, Aaron Abraham Mathews, Helen Li, Nathan Raul Brito, Eduardo Blanco 0002. 4677-4695 [doi]
• Quantifying Adaptability in Pre-trained Language Models with 500 TasksBelinda Z. Li, Jane A. Yu, Madian Khabsa, Luke Zettlemoyer, Alon Y. Halevy, Jacob Andreas. 4696-4715 [doi]
• Counterfactually Augmented Data and Unintended Bias: The Case of Sexism and Hate Speech DetectionIndira Sen, Mattia Samory, Claudia Wagner 0001, Isabelle Augenstein. 4716-4726 [doi]
• A Study of the Attention Abnormality in Trojaned BERTsWeimin Lyu, Songzhu Zheng, Tengfei Ma, Chao Chen. 4727-4741 [doi]
• EPiDA: An Easy Plug-in Data Augmentation Framework for High Performance Text ClassificationMinyi Zhao, Lu Zhang, Yi Xu 0003, Jiandong Ding, Jihong Guan, Shuigeng Zhou. 4742-4752 [doi]
• Partial-input baselines show that NLI models can ignore context, but they don'tNeha Srikanth, Rachel Rudinger. 4753-4763 [doi]
• Lifelong Pretraining: Continually Adapting Language Models to Emerging CorporaXisen Jin, Dejiao Zhang, Henghui Zhu, Wei Xiao 0001, Shang-wen Li 0001, Xiaokai Wei, Andrew O. Arnold, Xiang Ren 0001. 4764-4780 [doi]
• Learning as Conversation: Dialogue Systems Reinforced for Information AcquisitionPengshan Cai, Hui Wan 0001, Fei Liu 0004, Mo Yu, Hong Yu 0001, Sachindra Joshi. 4781-4796 [doi]
• Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGsSonglin Yang, Wei Liu, Kewei Tu. 4797-4809 [doi]
• What Factors Should Paper-Reviewer Assignments Rely On? Community Perspectives on Issues and Ideals in Conference Peer-ReviewTerne Sasha Thorn Jakobsen, Anna Rogers. 4810-4823 [doi]
• Reducing Disambiguation Biases in NMT by Leveraging Explicit Word Sense InformationNiccolò Campolungo, Tommaso Pasini, Denis Emelin, Roberto Navigli. 4824-4838 [doi]
• Mining Clues from Incomplete Utterance: A Query-enhanced Network for Incomplete Utterance RewritingShuzheng Si, Shuang Zeng, Baobao Chang. 4839-4847 [doi]
• Domain-Oriented Prefix-Tuning: Towards Efficient and Generalizable Fine-tuning for Zero-Shot Dialogue SummarizationLulu Zhao, Fujia Zheng, Weihao Zeng, Keqing He, Weiran Xu, Huixing Jiang, Wei Wu, Yanan Wu. 4848-4862 [doi]
• Interactive Symbol Grounding with Complex Referential ExpressionsRimvydas Rubavicius, Alex Lascarides. 4863-4874 [doi]
• Generalized Quantifiers as a Source of Error in Multilingual NLU BenchmarksRuixiang Cui, Daniel Hershcovich, Anders Søgaard. 4875-4893 [doi]
• Exact Paired-Permutation Testing for Structured Test StatisticsRan Zmigrod, Tim Vieira, Ryan Cotterell. 4894-4902 [doi]
• A Balanced Data Approach for Evaluating Cross-Lingual Transfer: Mapping the Linguistic Blood BankDan Malkin, Tomasz Limisiewicz, Gabriel Stanovsky. 4903-4915 [doi]
• SSEGCN: Syntactic and Semantic Enhanced Graph Convolutional Network for Aspect-based Sentiment AnalysisZheng Zhang, Zili Zhou, Yanna Wang. 4916-4925 [doi]
• Mitigating Toxic Degeneration with Empathetic Data: Exploring the Relationship Between Toxicity and EmpathyAllison Lahnala, Charles Welch, Béla Neuendorf, Lucie Flek. 4926-4938 [doi]
• DUCK: Rumour Detection on Social Media by Modelling User and Comment Propagation NetworksLin Tian, Xiuzhen Zhang, Jey Han Lau. 4939-4949 [doi]
• Jam or Cream First? Modeling Ambiguity in Neural Machine Translation with SCONESFelix Stahlberg, Shankar Kumar. 4950-4961 [doi]
• SkillSpan: Hard and Soft Skill Extraction from English Job PostingsMike Zhang, Kristian Nørgaard Jensen, Sif Dam Sonniks, Barbara Plank. 4962-4984 [doi]
• RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event ExtractionYuan Liang, Zhuoxuan Jiang, Di Yin, Bo Ren. 4985-4997 [doi]
• A Double-Graph Based Framework for Frame Semantic ParsingCe Zheng, Xudong Chen, Runxin Xu, Baobao Chang. 4998-5011 [doi]
• An Enhanced Span-based Decomposition Method for Few-Shot Sequence LabelingPeiyi Wang, Runxin Xu, Tianyu Liu, Qingyu Zhou, Yunbo Cao, Baobao Chang, Zhifang Sui. 5012-5024 [doi]
• A Two-Stream AMR-enhanced Model for Document-level Event Argument ExtractionRunxin Xu, Peiyi Wang, Tianyu Liu, Shuang Zeng, Baobao Chang, Zhifang Sui. 5025-5036 [doi]
• Robust (Controlled) Table-to-Text Generation with Structure-Aware Equivariance LearningFei Wang, Zhewei Xu, Pedro A. Szekely, Muhao Chen. 5037-5048 [doi]
• JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question AnsweringYueqing Sun, Qi Shi, Le Qi, Yu Zhang. 5049-5060 [doi]
• Models In a Spelling Bee: Language Models Implicitly Learn the Character Composition of TokensItay Itzhak, Omer Levy. 5061-5068 [doi]
• A Corpus for Understanding and Generating Moral StoriesJian Guan, Ziqi Liu, Minlie Huang. 5069-5087 [doi]
• Modeling Multi-Granularity Hierarchical Features for Relation ExtractionXinnian Liang, Shuangzhi Wu, Mu Li 0001, Zhoujun Li 0001. 5088-5098 [doi]
• Cross-modal Contrastive Learning for Speech TranslationRong Ye, Mingxuan Wang, Lei Li. 5099-5113 [doi]
• Meet Your Favorite Character: Open-domain Chatbot Mimicking Fictional Characters with only a Few UtterancesSeungju Han, Beomsu Kim, Jin-Yong Yoo, Seokjun Seo, Sangbum Kim, Enkhbayar Erdenee, Buru Chang. 5114-5132 [doi]
• DynamicTOC: Persona-based Table of Contents for Consumption of Long DocumentsHimanshu Maheshwari, Nethraa Sivakumar, Shelly Jain, Tanvi Karandikar, Vinay Aggarwal, Navita Goyal, Sumit Shekhar. 5133-5143 [doi]
• KALA: Knowledge-Augmented Language Model AdaptationMinki Kang, Jinheon Baek, Sung Ju Hwang. 5144-5167 [doi]
• On the Effect of Pretraining Corpora on In-context Learning by a Large-scale Language ModelSeongjin Shin, Sang-Woo Lee, Hwijeen Ahn, Sungdong Kim, Hyoungseok Kim, Boseop Kim, KyungHyun Cho, Gichang Lee, Woo-Myoung Park, Jung-Woo Ha, Nako Sung. 5168-5186 [doi]
• Sketching as a Tool for Understanding and Accelerating Self-attention for Long SequencesYifan Chen, Qi Zeng, Dilek Hakkani-Tur, Di Jin, Heng Ji, Yun Yang. 5187-5199 [doi]
• Partner Personas Generation for Dialogue Response GenerationHongyuan Lu, Wai Lam, Hong Cheng 0001, Helen Meng. 5200-5212 [doi]
• Semantically Informed Slang InterpretationZhewei Sun, Richard S. Zemel, Yang Xu. 5213-5231 [doi]
• Dual-Channel Evidence Fusion for Fact Verification over Texts and TablesNan Hu, Zirui Wu, Yuxuan Lai, Xiao Liu, Yansong Feng. 5232-5242 [doi]
• TreeMix: Compositional Constituency-based Data Augmentation for Natural Language UnderstandingLe Zhang, Zichao Yang, Diyi Yang. 5243-5258 [doi]
• Syn2Vec: Synset Colexification Graphs for Lexical Semantic SimilarityJohn B. Harvill, Roxana Girju, Mark Hasegawa-Johnson. 5259-5270 [doi]
• On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?Nouha Dziri, Sivan Milton, Mo Yu, Osmar R. Zaïane, Siva Reddy. 5271-5285 [doi]
• Is "My Favorite New Movie" My Favorite Movie? Probing the Understanding of Recursive Noun PhrasesQing Lyu 0001, Zheng Hua, Daoxin Li, Li Zhang, Marianna Apidianaki, Chris Callison-Burch. 5286-5302 [doi]
• Original or Translated? A Causal Analysis of the Impact of Translationese on Machine Translation PerformanceJingwei Ni, Zhijing Jin, Markus Freitag, Mrinmaya Sachan, Bernhard Schölkopf. 5303-5320 [doi]
• Visual Commonsense in Pretrained Unimodal and Multimodal ModelsChenyu Zhang, Benjamin Van Durme, Zhuowan Li, Elias Stengel-Eskin. 5321-5335 [doi]
• QuALITY: Question Answering with Long Input Texts, Yes!Richard Yuanzhe Pang, Alicia Parrish, Nitish Joshi, Nikita Nangia, Jason Phang, Angelica Chen, Vishakh Padmakumar, Johnny Ma, Jana Thompson, He He 0001, Samuel R. Bowman. 5336-5358 [doi]
• ExSum: From Local Explanations to Model UnderstandingYilun Zhou, Marco Túlio Ribeiro, Julie Shah. 5359-5378 [doi]
• Maximum Bayes Smatch Ensemble Distillation for AMR ParsingYoung-Suk Lee, Ramón Fernandez Astudillo, Hoang Thanh Lam, Tahira Naseem, Radu Florian, Salim Roukos. 5379-5392 [doi]
• When Does Syntax Mediate Neural Language Model Performance? Evidence from Dropout ProbesMycal Tucker, Tiwalayo Eisape, Peng Qian, Roger Levy, Julie Shah. 5393-5408 [doi]
• Modeling Task Interactions in Document-Level Joint Entity and Relation ExtractionLiyan Xu, Jinho D. Choi. 5409-5416 [doi]
• Few-Shot Semantic Parsing with Language Models Trained on CodeRichard Shin, Benjamin Van Durme. 5417-5425 [doi]
• CORWA: A Citation-Oriented Related Work Annotation DatasetXiangci Li, Biswadip Mandal, Jessica Ouyang 0001. 5426-5440 [doi]
• Overcoming Catastrophic Forgetting During Domain Adaptation of Seq2seq Language GenerationDingcheng Li, Zheng Chen 0010, Eunah Cho, Jie Hao, Xiaohu Liu, Fan Xing, Chenlei Guo, Yang Liu. 5441-5454 [doi]
• Extreme Zero-Shot Learning for Extreme Text ClassificationYuanhao Xiong, Wei-Cheng Chang, Cho-Jui Hsieh, Hsiang-Fu Yu, Inderjit S. Dhillon. 5455-5468 [doi]
• ConfliBERT: A Pre-trained Language Model for Political Conflict and ViolenceYibo Hu, MohammadSaleh Hosseini, Erick Skorupa Parolin, Javier Osorio, Latifur Khan, Patrick T. Brandt, Vito D'Orazio. 5469-5482 [doi]
• Automatic Multi-Label Prompting: Simple and Interpretable Few-Shot ClassificationHan Wang, Canwen Xu, Julian J. McAuley. 5483-5492 [doi]
• Few-shot Subgoal Planning with Language ModelsLajanugen Logeswaran, Yao Fu, Moontae Lee, Honglak Lee. 5493-5506 [doi]
• IDPG: An Instance-Dependent Prompt Generation MethodZhuofeng Wu 0001, Sinong Wang, Jiatao Gu, Rui Hou, Yuxiao Dong, V. G. Vinod Vydiswaran, Hao Ma. 5507-5521 [doi]
• Embedding Hallucination for Few-shot Language Fine-tuningYiren Jian, Chongyang Gao, Soroush Vosoughi. 5522-5530 [doi]
• Cryptocurrency Bubble Detection: A New Stock Market Dataset, Financial Task & Hyperbolic ModelsRamit Sawhney, Shivam Agarwal, Vivek Mittal, Paolo Rosso, Vikram Nanda, Sudheer Chava. 5531-5545 [doi]
• Nearest Neighbor Knowledge Distillation for Neural Machine TranslationZhixian Yang, Renliang Sun, Xiaojun Wan 0001. 5546-5556 [doi]
• DEMix Layers: Disentangling Domains for Modular Language ModelingSuchin Gururangan, Mike Lewis, Ari Holtzman, Noah Smith, Luke Zettlemoyer. 5557-5576 [doi]
• Contrastive Learning for Prompt-based Few-shot Language LearnersYiren Jian, Chongyang Gao, Soroush Vosoughi. 5577-5587 [doi]
• Cross-Lingual Event Detection via Optimized Adversarial TrainingLuis Guzman-Nateras, Minh Van Nguyen, Thien Nguyen. 5588-5599 [doi]
• Identifying Implicitly Abusive Remarks about Identity Groups using a Linguistically Informed ApproachMichael Wiegand, Elisabeth Eder, Josef Ruppenhofer. 5600-5612 [doi]
• Label Definitions Improve Semantic Role LabelingLi Zhang, Ishan Jindal, Yunyao Li 0001. 5613-5620 [doi]
• Shedding New Light on the Language of the Dark WebYoungjin Jin, Eugene Jang, Yongjae Lee, Seungwon Shin, Jin-Woo Chung. 5621-5637 [doi]
• Conceptualizing Treatment Leakage in Text-based Causal InferenceAdel Daoud, Connor T. Jerzak, Richard Johansson. 5638-5645 [doi]
• Consistency Training with Virtual Adversarial Discrete PerturbationJungsoo Park, Gyuwan Kim, Jaewoo Kang. 5646-5656 [doi]
• CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuningXiangru Tang, Arjun Nair, Borui Wang, Bingyao Wang, Jai Desai, Aaron Wade, Haoran Li, Asli Celikyilmaz, Yashar Mehdad, Dragomir R. Radev. 5657-5668 [doi]
• CoMPM: Context Modeling with Speaker's Pre-trained Memory Tracking for Emotion Recognition in ConversationJoosung Lee, Wooin Lee. 5669-5679 [doi]
• Investigating Crowdsourcing Protocols for Evaluating the Factual Consistency of SummariesXiangru Tang, Alexander R. Fabbri, Haoran Li, Ziming Mao, Griffin Adams, Borui Wang, Asli Celikyilmaz, Yashar Mehdad, Dragomir Radev. 5680-5692 [doi]
• DialSummEval: Revisiting Summarization Evaluation for DialoguesMingqi Gao, Xiaojun Wan 0001. 5693-5709 [doi]
• Hyperbolic Relevance Matching for Neural Keyphrase ExtractionMingYang Song, Yi Feng, Liping Jing. 5710-5720 [doi]
• Template-free Prompt Tuning for Few-shot NERRuotian Ma, Xin Zhou, Tao Gui, Yiding Tan, Linyang Li, Qi Zhang, Xuanjing Huang. 5721-5732 [doi]
• Few-Shot Document-Level Relation ExtractionNicholas Popovic, Michael Färber 0001. 5733-5746 [doi]
• LaMemo: Language Modeling with Look-Ahead MemoryHaozhe Ji, Rongsheng Zhang, Zhenyu Yang, Zhipeng Hu, Minlie Huang. 5747-5762 [doi]
• Exploiting Inductive Bias in Transformers for Unsupervised Disentanglement of Syntax and Semantics with VAEsGhazi Felhi, Joseph Le Roux, Djamé Seddah. 5763-5776 [doi]
• Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical ConstraintsChun Zeng, Jiangjie Chen, Tianyi Zhuang, Rui Xu, Hao Yang, Ying Qin, Shimin Tao, Yanghua Xiao. 5777-5790 [doi]
• What do Toothbrushes do in the Kitchen? How Transformers Think our World is StructuredAlexander Henlein, Alexander Mehler. 5791-5807 [doi]
• Less is More: Learning to Refine Dialogue History for Personalized Dialogue GenerationHanxun Zhong, Zhicheng Dou, Yutao Zhu 0001, Hongjin Qian, Ji-Rong Wen. 5808-5820 [doi]
• A Holistic Framework for Analyzing the COVID-19 Vaccine DebateMaria Pacheco, Tunazzina Islam, Monal Mahajan, Andrey Shor, Ming Yin, Lyle Ungar, Dan Goldwasser. 5821-5839 [doi]
• Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask TrainingYuanxin Liu, Fandong Meng, Zheng Lin 0001, Peng Fu 0008, Yanan Cao, Weiping Wang 0005, Jie Zhou 0016. 5840-5857 [doi]
• You Don't Know My Favorite Color: Preventing Dialogue Representations from Revealing Speakers' Private PersonasHaoran Li 0003, Yangqiu Song, Lixin Fan. 5858-5870 [doi]
• Explaining Dialogue Evaluation Metrics using Adversarial Behavioral AnalysisBaber Khalid, Sungjin Lee. 5871-5883 [doi]
• Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language DetectionMaarten Sap, Swabha Swayamdipta, Laura Vianna, Xuhui Zhou, Yejin Choi, Noah A. Smith. 5884-5906 [doi]
• Non-Autoregressive Chinese ASR Error Correction with Phonological TrainingZheng Fang 0002, Ruiqing Zhang, Zhongjun He, Hua Wu 0003, Yanan Cao. 5907-5917 [doi]
• Hate Speech and Counter Speech Detection: Conversational Context Does MatterXinchen Yu, Eduardo Blanco 0002, Lingzi Hong. 5918-5930 [doi]
• DACSA: A large-scale Dataset for Automatic summarization of Catalan and Spanish newspaper ArticlesEncarnación Segarra Soriano, Vicent Ahuir, Lluís F. Hurtado, José González. 5931-5943 [doi]
• Time Waits for No One! Analysis and Challenges of Temporal MisalignmentKelvin Luu, Daniel Khashabi, Suchin Gururangan, Karishma Mandyam, Noah A. Smith. 5944-5958 [doi]
• MCSE: Multimodal Contrastive Learning of Sentence EmbeddingsMiaoran Zhang, Marius Mosbach, David Ifeoluwa Adelani, Michael A. Hedderich, Dietrich Klakow. 5959-5969 [doi]
• HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation ExtractionShuliang Liu, Xuming Hu, Chenwei Zhang, Shuang Li, Lijie Wen, Philip S. Yu. 5970-5980 [doi]
• Diagnosing Vision-and-Language Navigation: What Really MattersWanrong Zhu, Yuankai Qi, Pradyumna Narayana, Kazoo Sone, Sugato Basu, Xin Wang, Qi Wu, Miguel P. Eckstein, William Yang Wang. 5981-5993 [doi]
• Aligning to Social Norms and Values in Interactive NarrativesPrithviraj Ammanabrolu, Liwei Jiang, Maarten Sap, Hannaneh Hajishirzi, Yejin Choi. 5994-6017 [doi]
• MOVER: Mask, Over-generate and Rank for Hyperbole GenerationYunxiang Zhang 0002, Xiaojun Wan 0001. 6018-6030 [doi]
• Embarrassingly Simple Performance Prediction for Abductive Natural Language InferenceEmils Kadikis, Vaibhav Srivastav, Roman Klinger. 6031-6037 [doi]
• Re-Examining System-Level Correlations of Automatic Summarization Evaluation MetricsDaniel Deutsch, Rotem Dror, Dan Roth. 6038-6052 [doi]