Table of Contents

• Knowledge Router: Learning Disentangled Representations for Knowledge GraphsShuai Zhang 0007, Xi Rao, Yi Tay, Ce Zhang 0001. 1-10 [doi]
• Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base PriorsFenia Christopoulou, Makoto Miwa, Sophia Ananiadou. 11-26 [doi]
• Cross-Task Instance Representation Interactions and Label Dependencies for Joint Information Extraction with Graph Convolutional NetworksMinh Van Nguyen, Viet Lai, Thien Huu Nguyen. 27-38 [doi]
• Abstract Meaning Representation Guided Graph Encoding and Decoding for Joint Information ExtractionZixuan Zhang, Heng Ji. 39-49 [doi]
• A Frustratingly Easy Approach for Entity and Relation ExtractionZexuan Zhong, Danqi Chen. 50-61 [doi]
• Event Time Extraction and Propagation via Graph Attention NetworksHaoyang Wen, Yanru Qu, Heng Ji, Qiang Ning, Jiawei Han 0001, Avi Sil, Hanghang Tong, Dan Roth. 62-73 [doi]
• Probing Word Translations in the Transformer and Trading Decoder for Encoder LayersHongfei Xu, Josef van Genabith, Qiuhui Liu, Deyi Xiong. 74-85 [doi]
• Mediators in Determining what Processing BERT Performs FirstAviv Slobodkin, Leshem Choshen, Omri Abend. 86-93 [doi]
• Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQAYonatan Bitton, Gabriel Stanovsky, Roy Schwartz 0001, Michael Elhadad. 94-105 [doi]
• Multilingual Language Models Predict Human Reading BehaviorNora Hollenstein, Federico Pirovano, Ce Zhang 0001, Lena Jäger, Lisa Beinborn. 106-123 [doi]
• Do Syntactic Probes Probe Syntax? Experiments with Jabberwocky ProbingRowan Hall Maudslay, Ryan Cotterell. 124-131 [doi]
• A Non-Linear Structural ProbeJennifer C. White, Tiago Pimentel, Naomi Saphra, Ryan Cotterell. 132-138 [doi]
• Concealed Data Poisoning Attacks on NLP ModelsEric Wallace, Tony Z. Zhao, Shi Feng, Sameer Singh 0001. 139-150 [doi]
• Backtranslation Feedback Improves User Confidence in MT, Not QualityVilém Zouhar, Michal Novák, Matús Zilinec, Ondrej Bojar, Mateo Obregón, Robin L. Hill, Frédéric Blain, Marina Fomicheva, Lucia Specia, Lisa Yankovskaya. 151-161 [doi]
• Data Filtering using Cross-Lingual Word EmbeddingsChristian Herold, Jan Rosendahl, Joris Vanvinckenroye, Hermann Ney. 162-172 [doi]
• Improving the Lexical Ability of Pretrained Language Models for Unsupervised Neural Machine TranslationAlexandra Chronopoulou, Dario Stojanovski, Alexander Fraser 0001. 173-180 [doi]
• Neural Machine Translation without EmbeddingsUri Shaham, Omer Levy. 181-186 [doi]
• Counterfactual Data Augmentation for Neural Machine TranslationQi Liu, Matt J. Kusner, Phil Blunsom. 187-197 [doi]
• Cultural and Geographical Influences on Image Translatability of Words across LanguagesNikzad Khani, Isidora Chara Tourni, Mohammad Sadegh Rasooli, Chris Callison-Burch, Derry Tanti Wijaya. 198-209 [doi]
• Multilingual BERT Post-Pretraining AlignmentLin Pan, Chung-Wei Hang, Haode Qi, Abhishek Shah, Saloni Potdar, Mo Yu. 210-219 [doi]
• A Million Tweets Are Worth a Few Points: Tuning Transformers for Customer Service TasksAmir Hadifar, Sofie Labat, Véronique Hoste, Chris Develder, Thomas Demeester. 220-225 [doi]
• Paragraph-level Rationale Extraction through Regularization: A case study on European Court of Human Rights CasesIlias Chalkidis, Manos Fergadiotis, Dimitrios Tsarapatsanis, Nikolaos Aletras, Ion Androutsopoulos, Prodromos Malakasiotis. 226-241 [doi]
• Answering Product-Questions by Utilizing Questions from Other Contextually Similar ProductsOhad Rozen, David Carmel, Avihai Mejer, Vitaly Mirkis, Yftah Ziser. 242-253 [doi]
• EnSidNet: Enhanced Hybrid Siamese-Deep Network for grouping clinical trials into drug-development pathwaysLucia Pagani. 254-266 [doi]
• DATE: Detecting Anomalies in Text via Self-Supervision of TransformersAndrei Manolache, Florin Brad, Elena Burceanu. 267-277 [doi]
• A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source CodeNadezhda Chirkova, Sergey Troshin. 278-288 [doi]
• Fast and Scalable Dialogue State Tracking with Explicit Modular DecompositionDingmin Wang, Chenghua Lin, Qi Liu, Kam-Fai Wong. 289-295 [doi]
• Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring TasksNandan Thakur, Nils Reimers 0001, Johannes Daxenberger, Iryna Gurevych. 296-310 [doi]
• SmBoP: Semi-autoregressive Bottom-up Semantic ParsingOhad Rubin, Jonathan Berant. 311-324 [doi]
• SGL: Speaking the Graph Languages of Semantic Parsing via Multilingual TranslationLuigi Procopio, Rocco Tripodi, Roberto Navigli. 325-337 [doi]
• Unifying Cross-Lingual Semantic Role Labeling with Heterogeneous Linguistic ResourcesSimone Conia, Andrea Bacciu, Roberto Navigli. 338-351 [doi]
• Fool Me Twice: Entailment from Wikipedia GamificationJulian Eisenschlos, Bhuwan Dhingra, Jannis Bulian, Benjamin Börschinger, Jordan L. Boyd-Graber. 352-365 [doi]
• Meta-Learning for Domain Generalization in Semantic ParsingBailin Wang, Mirella Lapata, Ivan Titov. 366-379 [doi]
• Aspect-Controlled Neural Argument GenerationBenjamin Schiller, Johannes Daxenberger, Iryna Gurevych. 380-396 [doi]
• Text Generation from Discourse Representation StructuresJiangming Liu, Shay B. Cohen, Mirella Lapata. 397-415 [doi]
• APo-VAE: Text Generation in Hyperbolic SpaceShuyang Dai, Zhe Gan, Yu Cheng 0001, Chenyang Tao, Lawrence Carin, Jingjing Liu 0001. 416-431 [doi]
• DART: Open-Domain Structured Data Record to Text GenerationLinyong Nan, Dragomir R. Radev, Rui Zhang 0037, Amrit Rau, Abhinand Sivaprasad, Chiachun Hsieh, Xiangru Tang, Aadit Vyas, Neha Verma, Pranav Krishna, Yangxiaokang Liu, Nadia Irwanto, Jessica Pan, Faiaz Rahman, Ahmad Zaidi, Mutethia Mutuma, Yasin Tarabar, Ankit Gupta, Tao Yu 0009, Yi Chern Tan, Xi Victoria Lin, Caiming Xiong, Richard Socher, Nazneen Fatema Rajani. 432-447 [doi]
• When Being Unseen from mBERT is just the Beginning: Handling New Languages With Multilingual Language ModelsBenjamin Müller, Antonios Anastasopoulos, Benoît Sagot, Djamé Seddah. 448-462 [doi]
• Multi-Adversarial Learning for Cross-Lingual Word EmbeddingsHaozhou Wang, James Henderson, Paola Merlo. 463-472 [doi]
• Multi-view Subword RegularizationXinyi Wang, Sebastian Ruder, Graham Neubig. 473-482 [doi]
• mT5: A Massively Multilingual Pre-trained Text-to-Text TransformerLinting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, Colin Raffel. 483-498 [doi]
• MetaXL: Meta Representation Transformation for Low-resource Cross-lingual LearningMengzhou Xia, Guoqing Zheng, Subhabrata Mukherjee, Milad Shokouhi, Graham Neubig, Ahmed Hassan Awadallah. 499-511 [doi]
• Open Domain Question Answering over Tables via Dense RetrievalJonathan Herzig, Thomas Müller 0009, Syrine Krichene, Julian Eisenschlos. 512-519 [doi]
• Open-Domain Question Answering Goes Conversational via Question RewritingRaviteja Anantha, Svitlana Vakulenko, Zhucheng Tu, Shayne Longpre, Stephen Pulman, Srinivas Chappidi. 520-534 [doi]
• QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question AnsweringMichihiro Yasunaga, Hongyu Ren, Antoine Bosselut, Percy Liang, Jure Leskovec. 535-546 [doi]
• XOR QA: Cross-lingual Open-Retrieval Question AnsweringAkari Asai, Jungo Kasai, Jonathan H. Clark, Kenton Lee, Eunsol Choi, Hannaneh Hajishirzi. 547-564 [doi]
• SPARTA: Efficient Open-Domain Question Answering via Sparse Transformer Matching RetrievalTiancheng Zhao, XiaoPeng Lu, Kyusong Lee. 565-575 [doi]
• Implicitly Abusive Language - What does it actually look like and why are we not getting there?Michael Wiegand, Josef Ruppenhofer, Elisabeth Eder. 576-587 [doi]
• The Importance of Modeling Social Factors of Language: Theory and PracticeDirk Hovy, Diyi Yang. 588-602 [doi]
• On learning and representing social meaning in NLP: a sociolinguistic perspectiveDong Nguyen 0002, Laura Rosseel, Jack Grieve. 603-612 [doi]
• Preregistering NLP researchEmiel van Miltenburg, Chris van der Lee, Emiel Krahmer. 613-623 [doi]
• Get Your Vitamin C! Robust Fact Verification with Contrastive EvidenceTal Schuster, Adam Fisch, Regina Barzilay. 624-643 [doi]
• Representing Numbers in NLP: a Survey and a VisionAvijit Thawani, Jay Pujara, Filip Ilievski, Pedro A. Szekely. 644-656 [doi]
• Extending Multi-Document Summarization Evaluation to the Interactive SettingOri Shapira, Ramakanth Pasunuru, Hadar Ronen, Mohit Bansal, Yael Amsterdamer, Ido Dagan. 657-677 [doi]
• Identifying Helpful Sentences in Product ReviewsIftah Gamzu, Hila Gonen, Gilad Kutiel, Ran Levy, Eugene Agichtein. 678-691 [doi]
• Noisy Self-Knowledge Distillation for Text SummarizationYang Liu, Sheng Shen, Mirella Lapata. 692-703 [doi]
• Improving Zero and Few-Shot Abstractive Summarization with Intermediate Fine-tuning and Data AugmentationAlexander R. Fabbri, Simeng Han, Haoyuan Li, Haoran Li, Marjan Ghazvininejad, Shafiq R. Joty, Dragomir R. Radev, Yashar Mehdad. 704-717 [doi]
• Enhancing Factual Consistency of Abstractive SummarizationChenguang Zhu, William Hinthorn, Ruochen Xu, Qingkai Zeng, Michael Zeng, Xuedong Huang 0001, Meng Jiang 0001. 718-733 [doi]
• Few-shot Intent Classification and Slot Filling with Retrieved ExamplesDian Yu, Luheng He, Yuan Zhang, Xinya Du, Panupong Pasupat, Qi Li. 734-749 [doi]
• "Nice Try, Kiddo": Investigating Ad Hominems in Dialogue ResponsesEmily Sheng, Kai-Wei Chang, Prem Natarajan, Nanyun Peng. 750-767 [doi]
• Human-like informative conversations: Better acknowledgements using conditional mutual informationAshwin Paranjape, Christopher D. Manning. 768-781 [doi]
• A Comparative Study on Schema-Guided Dialogue State TrackingJie Cao, Yi Zhang. 782-796 [doi]
• Spoken Language Understanding for Task-oriented Dialogue Systems with Augmented Memory NetworksJie Wu, Ian Harris, Hongzhi Zhao. 797-806 [doi]
• How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy WorldsPrithviraj Ammanabrolu, Jack Urbanek, Margaret Li, Arthur Szlam, Tim Rocktäschel, Jason Weston. 807-833 [doi]
• Linking Entities to Unseen Knowledge Bases with Arbitrary SchemasYogarshi Vyas, Miguel Ballesteros. 834-844 [doi]
• Self-Training with Weak SupervisionGiannis Karamanolakis, Subhabrata Mukherjee, Guoqing Zheng, Ahmed Hassan Awadallah. 845-863 [doi]
• Neural Language Modeling for Contextualized Temporal Graph GenerationAman Madaan, Yiming Yang. 864-881 [doi]
• Probabilistic Box Embeddings for Uncertain Knowledge Graph ReasoningXuelu Chen, Michael Boratko, Muhao Chen, Shib Sankar Dasgupta, Xiang Lorraine Li, Andrew McCallum. 882-893 [doi]
• Document-Level Event Argument Extraction by Conditional GenerationSha Li, Heng Ji, Jiawei Han 0001. 894-908 [doi]
• Template Filling with Generative TransformersXinya Du, Alexander M. Rush, Claire Cardie. 909-914 [doi]
• Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU modelsMengnan Du, Varun Manjunatha, Rajiv Jain, Ruchi Deshpande, Franck Dernoncourt, Jiuxiang Gu, Tong Sun, Xia Hu. 915-929 [doi]
• On Attention Redundancy: A Comprehensive StudyYuchen Bian, Jiaji Huang, Xingyu Cai, Jiahong Yuan, Kenneth Church 0001. 930-945 [doi]
• Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?Eric Lehman, Sarthak Jain, Karl Pichotta, Yoav Goldberg, Byron C. Wallace. 946-959 [doi]
• Low-Complexity Probing via Finding SubnetworksVictor Sanh, Alexander M. Rush. 960-966 [doi]
• An Empirical Comparison of Instance Attribution Methods for NLPPouya Pezeshkpour, Sarthak Jain, Byron C. Wallace, Sameer Singh 0001. 967-975 [doi]
• Generalization in Instruction Following SystemsSoham Dan, Michael Zhou, Dan Roth. 976-981 [doi]
• LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text RetrievalSiqi Sun, Yen-Chun Chen 0001, Linjie Li, Shuohang Wang, Yuwei Fang, Jingjing Liu 0001. 982-997 [doi]
• Measuring Social Biases in Grounded Vision and Language EmbeddingsCandace Ross, Boris Katz, Andrei Barbu. 998-1008 [doi]
• MTAG: Modal-Temporal Attention Graph for Unaligned Human Multimodal Language SequencesJianing Yang, Yongxin Wang, Ruitao Yi, Yuying Zhu 0004, Azaan Rehman, Amir Zadeh 0001, Soujanya Poria, Louis-Philippe Morency. 1009-1021 [doi]
• Grounding Open-Domain Instructions to Automate Web Support TasksNancy Xu, Sam Masling, Michael Du, Giovanni Campagna, Larry Heck, James A. Landay, Monica S. Lam. 1022-1032 [doi]
• Modular Networks for Compositional Instruction FollowingRodolfo Corona, Daniel Fried, Coline Devin, Dan Klein, Trevor Darrell. 1033-1040 [doi]
• Improving Cross-Modal Alignment in Vision Language Navigation via Syntactic InformationJialu Li, Hao Tan, Mohit Bansal. 1041-1050 [doi]
• Improving Pretrained Models for Zero-shot Multi-label Text Classification through Reinforced Label Hierarchy ReasoningHui Liu, Danqing Zhang, Bing Yin, Xiaodan Zhu. 1051-1062 [doi]
• Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training ApproachYue Yu, Simiao Zuo, Haoming Jiang, Wendi Ren, Tuo Zhao, Chao Zhang 0014. 1063-1077 [doi]
• Posterior Differential Regularization with f-divergence for Improving Model RobustnessHao Cheng 0002, Xiaodong Liu, Lis Pereira, Yaoliang Yu, Jianfeng Gao. 1078-1089 [doi]
• Understanding Hard Negatives in Noise Contrastive EstimationWenzheng Zhang, Karl Stratos. 1090-1101 [doi]
• Certified Robustness to Word Substitution Attack with Differential PrivacyWenjie Wang, Pengfei Tang, Jian Lou 0001, Li Xiong 0001. 1102-1112 [doi]
• DReCa: A General Task Augmentation Strategy for Few-Shot Natural Language InferenceShikhar Murty, Tatsunori Hashimoto, Christopher D. Manning. 1113-1125 [doi]
• Harnessing Multilinguality in Unsupervised Machine Translation for Rare LanguagesXavier Garcia, Aditya Siddhant, Orhan Firat, Ankur P. Parikh. 1126-1137 [doi]
• Macro-Average: Rare Types Are Important TooThamme Gowda, Weiqiu You, Constantine Lignos, Jonathan May. 1138-1157 [doi]
• Assessing Reference-Free Peer Evaluation for Machine TranslationSweta Agrawal, George F. Foster, Markus Freitag, Colin Cherry. 1158-1171 [doi]
• The Curious Case of Hallucinations in Neural Machine TranslationVikas Raunak, Arul Menezes, Marcin Junczys-Dowmunt. 1172-1183 [doi]
• Towards Continual Learning for Multilingual Machine Translation via Vocabulary SubstitutionXavier Garcia, Noah Constant, Ankur P. Parikh, Orhan Firat. 1184-1192 [doi]
• Towards Modeling the Style of Translators in Neural Machine TranslationYue Wang, Cuong Hoang, Marcello Federico. 1193-1199 [doi]
• Self-Supervised Test-Time Learning for Reading ComprehensionPratyay Banerjee, Tejas Gokhale, Chitta Baral. 1200-1211 [doi]
• Capturing Row and Column Semantics in Transformer Based Question Answering over TablesMichael R. Glass, Mustafa Canim, Alfio Gliozzo, Saneem A. Chemmengath, Vishwajeet Kumar, Rishav Chakravarti, Avi Sil, Feifei Pan, Samarth Bharadwaj, Nicolas Rodolfo Fauceglia. 1212-1224 [doi]
• Explainable Multi-hop Verbal Reasoning Through Internal MonologueZhengzhong Liang, Steven Bethard, Mihai Surdeanu. 1225-1250 [doi]
• Robust Question Answering Through Sub-part AlignmentJifan Chen, Greg Durrett. 1251-1263 [doi]
• Text Modular Networks: Learning to Decompose Tasks in the Language of Existing ModelsTushar Khot, Daniel Khashabi, Kyle Richardson 0001, Peter Clark, Ashish Sabharwal. 1264-1279 [doi]
• RECONSIDER: Improved Re-Ranking using Span-Focused Cross-Attention for Open Domain Question AnsweringSrinivasan Iyer, Sewon Min, Yashar Mehdad, Wen-tau Yih. 1280-1287 [doi]
• On the Transferability of Minimal Prediction Preserving Inputs in Question AnsweringShayne Longpre, Yi Lu, Chris DuBois. 1288-1300 [doi]
• Understanding by Understanding Not: Modeling Negation in Language ModelsArian Hosseini, Siva Reddy, Dzmitry Bahdanau, R. Devon Hjelm, Alessandro Sordoni, Aaron C. Courville. 1301-1312 [doi]
• DuoRAT: Towards Simpler Text-to-SQL ModelsTorsten Scholak, Raymond Li, Dzmitry Bahdanau, Harm de Vries, Chris Pal. 1313-1321 [doi]
• Looking Beyond Sentence-Level Natural Language Inference for Question Answering and Text SummarizationAnshuman Mishra, Dhruvesh Patel, Aparna Vijayakumar, Xiang Lorraine Li, Pavan Kapanipathi, Kartik Talamadupula. 1322-1336 [doi]
• Structure-Grounded Pretraining for Text-to-SQLXiang Deng, Ahmed Hassan Awadallah, Christopher Meek, Oleksandr Polozov, Huan Sun, Matthew Richardson. 1337-1350 [doi]
• Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and SystemCongying Xia, Wenpeng Yin 0001, Yihao Feng, Philip S. Yu. 1351-1360 [doi]
• Temporal Reasoning on Implicit Events from Distant SupervisionBen Zhou, Kyle Richardson 0001, Qiang Ning, Tushar Khot, Ashish Sabharwal, Dan Roth. 1361-1371 [doi]
• Disentangling Semantics and Syntax in Sentence Embeddings with Pre-trained Language ModelsJames Y. Huang, Kuan-Hao Huang, Kai-Wei Chang. 1372-1379 [doi]
• Structure-Aware Abstractive Conversation Summarization via Discourse and Action GraphsJiaao Chen, Diyi Yang. 1380-1391 [doi]
• A New Approach to Overgenerating and Scoring Abstractive SummariesKaiqiang Song, Bingqing Wang, Zhe Feng 0003, Fei Liu 0004. 1392-1404 [doi]
• D2S: Document-to-Slide Generation Via Query-Based Text SummarizationEdward Sun, Yufang Hou, Dakuo Wang, Yunfeng Zhang, Nancy Xin Ru Wang. 1405-1418 [doi]
• Efficient Attentions for Long Document SummarizationLuyang Huang, Shuyang Cao, Nikolaus Nova Parulian, Heng Ji, Lu Wang 0008. 1419-1436 [doi]
• RefSum: Refactoring Neural SummarizationYixin Liu, Zi-Yi Dou, Pengfei Liu 0003. 1437-1448 [doi]
• Annotating and Modeling Fine-grained Factuality in SummarizationTanya Goyal, Greg Durrett. 1449-1462 [doi]
• Larger-Context Tagging: When and Why Does It Work?JinLan Fu, Liangjing Feng, Qi Zhang 0001, Xuanjing Huang, Pengfei Liu 0003. 1463-1475 [doi]
• Neural Sequence Segmentation as Determining the Leftmost SegmentsYangming Li, Lemao Liu, Kaisheng Yao. 1476-1486 [doi]
• PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many SymbolsSonglin Yang, Yanpeng Zhao, Kewei Tu. 1487-1498 [doi]
• GEMNET: Effective Gated Gazetteer Representations for Recognizing Complex Entities in Low-context InputTao Meng, Anjie Fang, Oleg Rokhlenko, Shervin Malmasi. 1499-1512 [doi]
• Video-aided Unsupervised Grammar InductionSongyang Zhang, Linfeng Song, Lifeng Jin, Kun Xu, Dong Yu 0001, Jiebo Luo. 1513-1524 [doi]
• Generating Negative Samples by Manipulating Golden Responses for Unsupervised Learning of a Response Evaluation ModelChaeHun Park, Eugene Jang, Wonsuk Yang, Jong Park. 1525-1534 [doi]
• How Robust are Fact Checking Systems on Colloquial Claims?Byeongchang Kim 0002, Hyunwoo Kim, Seokhee Hong, Gunhee Kim. 1535-1548 [doi]
• Fine-grained Post-training for Improving Retrieval-based Dialogue SystemsJanghoon Han, Taesuk Hong, Byoungjae Kim, Youngjoong Ko, Jungyun Seo. 1549-1558 [doi]
• Put Chatbot into Its Interlocutor's Shoes: New Framework to Learn Chatbot Responding with IntentionHsuan Su, Jiun-Hao Jhan, Fan-Yun Sun, Saurav Sahay, Hung-yi Lee. 1559-1569 [doi]
• Adding Chit-Chat to Enhance Task-Oriented DialoguesKai Sun 0006, Seungwhan Moon, Paul A. Crook, Stephen Roller, Becka Silvert, Bing Liu, Zhiguang Wang, Honglei Liu, Eunjoon Cho, Claire Cardie. 1570-1583 [doi]
• Incorporating Syntax and Semantics in Coreference Resolution with Heterogeneous Graph Attention NetworkFan Jiang, Trevor Cohn. 1584-1591 [doi]
• Context Tracking Network: Graph-based Context Modeling for Implicit Discourse Relation RecognitionYingxue Zhang, Fandong Meng, Peng Li 0030, Ping Jian, Jie Zhou 0016. 1592-1599 [doi]
• Improving Neural RST Parsing Model with Silver Agreement SubtreesNaoki Kobayashi, Tsutomu Hirao, Hidetaka Kamigaito, Manabu Okumura, Masaaki Nagata. 1600-1612 [doi]
• RST Parsing from ScratchThanh Tung Nguyen, Xuan-Phi Nguyen, Shafiq R. Joty, Xiaoli Li 0001. 1613-1625 [doi]
• Did they answer? Subjective acts and intents in conversational discourseElisa Ferracane, Greg Durrett, Junyi Jessy Li, Katrin Erk. 1626-1644 [doi]
• Evaluating the Impact of a Hierarchical Discourse Representation on Entity Coreference Resolution PerformanceSopan Khosla, James Fiacco, Carolyn P. Rosé. 1645-1651 [doi]
• Bridging Resolution: Making Sense of the State of the ArtHideo Kobayashi, Vincent Ng. 1652-1659 [doi]
• Explicitly Modeling Syntax in Language Models with Incremental Parsing and a Dynamic OracleYikang Shen, Shawn Tan, Alessandro Sordoni, Siva Reddy, Aaron C. Courville. 1660-1672 [doi]
• Revisiting the Weaknesses of Reinforcement Learning for Neural Machine TranslationSamuel Kiegeland, Julia Kreutzer. 1673-1681 [doi]
• Learning to Organize a Bag of Words into Sentences with Neural Networks: An Empirical StudyChongyang Tao, Shen Gao, Juntao Li, Yansong Feng, Dongyan Zhao 0001, Rui Yan 0001. 1682-1691 [doi]
• Mask Attention Networks: Rethinking and Strengthen TransformerZhihao Fan, Yeyun Gong, Dayiheng Liu, Zhongyu Wei, Siyuan Wang, Jian Jiao 0007, Nan Duan, Ruofei Zhang, Xuanjing Huang. 1692-1701 [doi]
• ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language UnderstandingDongling Xiao, Yu-Kun Li, Han Zhang, Yu Sun, Hao Tian, Hua Wu 0003, Haifeng Wang 0001. 1702-1715 [doi]
• Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language ModelsYuxuan Lai, Yijia Liu, Yansong Feng, Songfang Huang, Dongyan Zhao 0001. 1716-1731 [doi]
• Modeling Event Plausibility with Consistent Conceptual AbstractionIan Porada, Kaheer Suleman, Adam Trischler, Jackie Chi Kit Cheung. 1732-1743 [doi]
• UmlsBERT: Clinical Domain Knowledge Augmentation of Contextual Embeddings Using the Unified Medical Language System MetathesaurusGeorge Michalopoulos, Yuanxin Wang, Hussam Kaka, Helen H. Chen, Alexander Wong. 1744-1753 [doi]
• Field Embedding: A Unified Grain-Based Framework for Word RepresentationJunjie Luo, Xi Chen, Jichao Sun, Yuejia Xiang, Ningyu Zhang, Xiang Wan. 1754-1762 [doi]
• MelBERT: Metaphor Detection via Contextualized Late Interaction using Metaphorical Identification TheoriesMinjin Choi, Sunkyung Lee, Eunseong Choi, Heesoo Park, Junhyuk Lee, Dongwon Lee 0001, Jongwuk Lee. 1763-1773 [doi]
• Non-Parametric Few-Shot Learning for Word Sense DisambiguationHoward Chen, Mengzhou Xia, Danqi Chen. 1774-1781 [doi]
• Why Do Document-Level Polarity Classifiers Fail?Karen S. Martins, Pedro O. S. Vaz de Melo, Rodrygo L. T. Santos. 1782-1794 [doi]
• A Unified Span-Based Approach for Opinion Mining with Syntactic ConstituentsQingrong Xia, Bo Zhang, Rui Wang 0051, Zhenghua Li, Yue Zhang, Fei Huang, Luo Si, Min Zhang 0005. 1795-1804 [doi]
• Target-specified Sequence Labeling with Multi-head Self-attention for Target-oriented Opinion Words ExtractionYuhao Feng, Yanghui Rao, Yuyao Tang, Ninghua Wang, He Liu. 1805-1815 [doi]
• Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTaJunqi Dai, Hang Yan, Tianxiang Sun, Pengfei Liu 0003, Xipeng Qiu. 1816-1829 [doi]
• Domain Divergences: A Survey and Empirical AnalysisAbhinav Ramesh Kashyap, Devamanyu Hazarika, Min-Yen Kan, Roger Zimmermann. 1830-1849 [doi]
• Target-Aware Data Augmentation for Stance DetectionYingjie Li, Cornelia Caragea. 1850-1860 [doi]
• End-to-end ASR to jointly predict transcriptions and linguistic annotationsMotoi Omachi, Yuya Fujita, Shinji Watanabe 0001, Matthew Wiesner. 1861-1871 [doi]
• Source and Target Bidirectional Knowledge Distillation for End-to-end Speech TranslationHirofumi Inaguma, Tatsuya Kawahara, Shinji Watanabe 0001. 1872-1881 [doi]
• Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence TasksSiddharth Dalmia, Brian Yan, Vikas Raunak, Florian Metze, Shinji Watanabe 0001. 1882-1896 [doi]
• SPLAT: Speech-Language Joint Pre-Training for Spoken Language UnderstandingYu-An Chung, Chenguang Zhu, Michael Zeng. 1897-1907 [doi]
• Worldly Wise (WoW) - Cross-Lingual Knowledge Fusion for Fact-based Visual Spoken-Question AnsweringKiran Ramnath, Leda Sari, Mark Hasegawa-Johnson, Chang Yoo. 1908-1919 [doi]
• Align-Refine: Non-Autoregressive Speech Recognition via Iterative RealignmentEthan A. Chi, Julian Salazar, Katrin Kirchhoff. 1920-1927 [doi]
• Everything Has a Cause: Leveraging Causal Inference in Legal Text AnalysisXiao Liu, Da Yin, Yansong Feng, Yuting Wu, Dongyan Zhao 0001. 1928-1941 [doi]
• Counterfactual Supporting Facts Extraction for Explainable Medical Record Based Diagnosis with Graph NetworkHaoran Wu, Wei Chen 0048, Shuang Xu, Bo Xu 0002. 1942-1955 [doi]
• Personalized Response Generation via Generative Split Memory NetworkYuwei Wu, Xuezhe Ma, Diyi Yang. 1956-1970 [doi]
• Towards Few-shot Fact-Checking via PerplexityNayeon Lee, Yejin Bang, Andrea Madotto, Pascale Fung. 1971-1981 [doi]
• Active² Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine TranslationRishi Hazra, Parag Dutta, Shubham Gupta, Mohammed Abdul Qaathir, Ambedkar Dukkipati. 1982-1995 [doi]
• Generating An Optimal Interview Question Plan Using A Knowledge Graph And Integer Linear ProgrammingSoham Datta, Prabir Mallick, Sangameshwar Patil, Indrajit Bhattacharya, Girish K. Palshikar. 1996-2005 [doi]
• Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!Xuanli He, Lingjuan Lyu, Lichao Sun, Qiongkai Xu. 2006-2012 [doi]
• A Global Past-Future Early Exit Method for Accelerating Inference of Pre-trained Language ModelsKaiyuan Liao, Yi Zhang 0050, Xuancheng Ren, Qi Su 0001, Xu Sun 0001, Bin He. 2013-2023 [doi]
• Masked Conditional Random Fields for Sequence LabelingTianwen Wei, Jianwei Qi, Shenghuan He, Songtao Sun. 2024-2035 [doi]
• Heterogeneous Graph Neural Networks for Concept Prerequisite Relation Learning in Educational DataChenghao Jia, Yongliang Shen 0001, Yechun Tang, Lu Sun, Weiming Lu 0001. 2036-2047 [doi]
• Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP ModelsWenkai Yang, Lei Li, Zhiyuan Zhang, Xuancheng Ren, Xu Sun 0001, Bin He. 2048-2058 [doi]
• DA-Transformer: Distance-aware TransformerChuhan Wu, Fangzhao Wu, Yongfeng Huang 0001. 2059-2068 [doi]
• ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating PredictionJiahao Bu, Lei Ren, Shuang Zheng, Yang Yang, Jingang Wang, Fuzheng Zhang, Wei Wu. 2069-2079 [doi]
• Are NLP Models really able to Solve Simple Math Word Problems?Arkil Patel, Satwik Bhattamishra, Navin Goyal. 2080-2094 [doi]
• WRIME: A New Dataset for Emotional Intensity Estimation with Subjective and Objective AnnotationsTomoyuki Kajiwara, Chenhui Chu, Noriko Takemura, Yuta Nakashima, Hajime Nagahara. 2095-2104 [doi]
• KPQA: A Metric for Generative Question Answering Using Keyphrase WeightsHwanhee Lee, Seunghyun Yoon 0002, Franck Dernoncourt, Doo Soon Kim, Trung Bui, Joongbo Shin, Kyomin Jung. 2105-2115 [doi]
• StylePTB: A Compositional Benchmark for Fine-grained Controllable Text Style TransferYiwei Lyu, Paul Pu Liang, Hai Pham, Eduard H. Hovy, Barnabás Póczos, Ruslan Salakhutdinov, Louis-Philippe Morency. 2116-2138 [doi]
• Blow the Dog Whistle: A Chinese Dataset for Cant Understanding with Common Sense and World KnowledgeCanwen Xu, Wangchunshu Zhou, Tao Ge, Ke Xu 0001, Julian J. McAuley, Furu Wei. 2139-2145 [doi]
• COVID-19 Named Entity Recognition for VietnameseThinh Hung Truong, Mai Hoang Dao, Dat Quoc Nguyen. 2146-2153 [doi]
• Framing Unpacked: A Semi-Supervised Interpretable Multi-View Model of Media FramesShima Khanehzar, Trevor Cohn, Gosia Mikolajczak, Andrew Turpin, Lea Frermann. 2154-2166 [doi]
• Automatic Classification of Neutralization Techniques in the Narrative of Climate Change ScepticismShraey Bhatia, Jey Han Lau, Timothy Baldwin. 2167-2175 [doi]
• Suicide Ideation Detection via Social and Temporal User Representations using Hyperbolic LearningRamit Sawhney, Harshit Joshi, Rajiv Ratn Shah, Lucie Flek. 2176-2190 [doi]
• WikiTalkEdit: A Dataset for modeling Editors' behaviors on WikipediaKokil Jaidka, Andrea Ceolin, Iknoor Singh, Niyati Chhaya, Lyle Ungar. 2191-2200 [doi]
• The structure of online social networks modulates the rate of lexical changeJian Zhu, David Jurgens. 2201-2218 [doi]
• Modeling Framing in Immigration Discourse on Social MediaJulia Mendelsohn, Ceren Budak, David Jurgens. 2219-2263 [doi]
• Modeling the Severity of Complaints in Social MediaMali Jin, Nikolaos Aletras. 2264-2274 [doi]
• What About the Precedent: An Information-Theoretic Analysis of Common LawJosef Valvoda, Tiago Pimentel, Niklas Stoehr, Ryan Cotterell, Simone Teufel. 2275-2288 [doi]
• Introducing CAD: the Contextual Abuse DatasetBertie Vidgen, Dong Nguyen 0002, Helen Z. Margetts, Patricia Rossini, Rebekah Tromble. 2289-2303 [doi]
• Lifelong Learning of Hate Speech Classification on Social MediaJing Qian, Hong Wang, Mai ElSherief, Xifeng Yan. 2304-2314 [doi]
• Learning to Recognize Dialect FeaturesDorottya Demszky, Devyani Sharma, Jonathan H. Clark, Vinodkumar Prabhakaran, Jacob Eisenstein. 2315-2338 [doi]
• It's Not Just Size That Matters: Small Language Models Are Also Few-Shot LearnersTimo Schick, Hinrich Schütze. 2339-2352 [doi]
• Static Embeddings as Efficient Knowledge Bases?Philipp Dufter, Nora Kassner, Hinrich Schütze. 2353-2363 [doi]
• Highly Efficient Knowledge Graph Embedding Learning with Orthogonal Procrustes AnalysisXutan Peng, Guanyi Chen, Chenghua Lin, Mark Stevenson. 2364-2375 [doi]
• Rethinking Network Pruning - under the Pre-train and Fine-tune ParadigmDongkuan Xu, Ian En-Hsu Yen, Jinxi Zhao, Zhibin Xiao. 2376-2382 [doi]
• Towards a Comprehensive Understanding and Accurate Evaluation of Societal Biases in Pre-Trained TransformersAndrew Silva, Pradyumna Tambwekar, Matthew C. Gombolay. 2383-2389 [doi]
• Detoxifying Language Models Risks Marginalizing Minority VoicesAlbert Xu, Eshaan Pathak, Eric Wallace, Suchin Gururangan, Maarten Sap, Dan Klein. 2390-2397 [doi]
• HONEST: Measuring Hurtful Sentence Completion in Language ModelsDebora Nozza, Federico Bianchi, Dirk Hovy. 2398-2406 [doi]
• EaSe: A Diagnostic Tool for VQA based on Answer DiversityShailza Jolly, Sandro Pezzelle, Moin Nabi. 2407-2414 [doi]
• DeCEMBERT: Learning from Noisy Instructional Videos via Dense Captions and Entropy MinimizationZineng Tang, Jie Lei, Mohit Bansal. 2415-2426 [doi]
• Improving Generation and Evaluation of Visual Stories via Semantic ConsistencyAdyasha Maharana, Darryl Hannan, Mohit Bansal. 2427-2442 [doi]
• Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language ModelsPoyao Huang 0001, Mandela Patrick, Junjie Hu 0001, Graham Neubig, Florian Metze, Alex Hauptmann 0001. 2443-2459 [doi]
• Video Question Answering with Phrases via Semantic RolesArka Sadhu, Kan Chen, Ram Nevatia. 2460-2478 [doi]
• From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language UnderstandingRob van der Goot, Ibrahim Sharaf, Aizhan Imankulova, Ahmet Üstün, Marija Stepanovic, Alan Ramponi, Siti Oryza Khairunnisa, Mamoru Komachi, Barbara Plank. 2479-2497 [doi]
• WEC: Deriving a Large-scale Cross-document Event Coreference dataset from WikipediaAlon Eirew, Arie Cattan, Ido Dagan. 2498-2510 [doi]
• Challenging distributional models with a conceptual network of philosophical termsYvette Oortwijn, Jelke Bloem, Pia Sommerauer, Francois Meyer, Wei Zhou, Antske Fokkens. 2511-2522 [doi]
• KILT: a Benchmark for Knowledge Intensive Language TasksFabio Petroni, Aleksandra Piktus, Angela Fan, Patrick S. H. Lewis, Majid Yazdani, Nicola De Cao, James Thorne, Yacine Jernite, Vladimir Karpukhin, Jean Maillard, Vassilis Plachouras, Tim Rocktäschel, Sebastian Riedel 0001. 2523-2544 [doi]
• A Survey on Recent Approaches for Natural Language Processing in Low-Resource ScenariosMichael A. Hedderich, Lukas Lange, Heike Adel, Jannik Strötgen, Dietrich Klakow. 2545-2568 [doi]
• Temporal Knowledge Graph Completion using a Linear Temporal Regularizer and Multivector EmbeddingsChengjin Xu, Yung-Yu Chen, Mojtaba Nayyeri, Jens Lehmann 0001. 2569-2578 [doi]
• UDALM: Unsupervised Domain Adaptation through Language ModelingConstantinos Karouzos, Georgios Paraskevopoulos, Alexandros Potamianos. 2579-2590 [doi]
• Beyond Black & White: Leveraging Annotator Disagreement via Soft-Label Multi-Task LearningTommaso Fornaciari, Alexandra Uma, Silviu Paun, Barbara Plank, Dirk Hovy, Massimo Poesio. 2591-2597 [doi]
• Clustering-based Inference for Biomedical Entity LinkingRico Angell, Nicholas Monath, Sunil Mohan, Nishant Yadav, Andrew McCallum. 2598-2608 [doi]
• Variance-reduced First-order Meta-learning for Natural Language Processing TasksLingxiao Wang, Kevin Huang 0002, Tengyu Ma, Quanquan Gu, Jing Huang 0019. 2609-2615 [doi]
• Diversity-Aware Batch Active Learning for Dependency ParsingTianze Shi, Adrian Benton, Igor Malioutov, Ozan Irsoy. 2616-2626 [doi]
• How many data points is a prompt worth?Teven Le Scao, Alexander M. Rush. 2627-2636 [doi]
• Can Latent Alignments Improve Autoregressive Machine Translation?Adi Haviv, Lior Vassertail, Omer Levy. 2637-2641 [doi]
• Smoothing and Shrinking the Sparse Seq2Seq Search SpaceBen Peters, André F. T. Martins. 2642-2654 [doi]
• Unified Pre-training for Program Understanding and GenerationWasi Uddin Ahmad, Saikat Chakraborty, Baishakhi Ray, Kai-Wei Chang. 2655-2668 [doi]
• Hyperparameter-free Continuous Learning for Domain Classification in Natural Language UnderstandingTing Hua, Yilin Shen, ChangSheng Zhao, Yen-Chang Hsu, Hongxia Jin. 2669-2678 [doi]
• On the Embeddings of Variables in Recurrent Neural Networks for Source CodeNadezhda Chirkova. 2679-2689 [doi]
• Cross-Lingual Word Embedding Refinement by $\ell_1$ Norm OptimisationXutan Peng, Chenghua Lin, Mark Stevenson. 2690-2701 [doi]
• Semantic Frame ForecastChieh-Yang Huang, Ting-Hao K. Huang. 2702-2713 [doi]
• MUSER: MUltimodal Stress detection using Emotion Recognition as an Auxiliary TaskYiqun Yao, Michalis Papakostas, Mihai Burzo, Mohamed Abouelenien, Rada Mihalcea. 2714-2725 [doi]
• Learning to Decompose and Organize Complex TasksYi Zhang, Sujay Kumar Jauhar, Julia Kiseleva, Ryen White, Dan Roth. 2726-2735 [doi]
• Continual Learning for Text Classification with Information Disentanglement Based RegularizationYufan Huang, Yanzhe Zhang, Jiaao Chen, Xuezhi Wang 0002, Diyi Yang. 2736-2746 [doi]
• Learning from Executions for Semantic ParsingBailin Wang, Mirella Lapata, Ivan Titov. 2747-2759 [doi]
• Learning to Synthesize Data for Semantic ParsingBailin Wang, Wenpeng Yin 0001, Xi Victoria Lin, Caiming Xiong. 2760-2766 [doi]
• Edge: Enriching Knowledge Graph Embeddings with External TextSaed Rezayi, Handong Zhao, SungChul Kim, Ryan A. Rossi, Nedim Lipka, Sheng Li 0001. 2767-2776 [doi]
• FLIN: A Flexible Natural Language Interface for Web NavigationSahisnu Mazumder, Oriana Riva. 2777-2788 [doi]
• Game-theoretic Vocabulary Selection via the Shapley Value and Banzhaf IndexRoma Patel, Marta Garnelo, Ian M. Gemp, Chris Dyer, Yoram Bachrach. 2789-2798 [doi]
• Incorporating External Knowledge to Enhance Tabular ReasoningJ. Neeraja, Vivek Gupta 0001, Vivek Srikumar. 2799-2809 [doi]
• Compositional Generalization for Neural Semantic Parsing via Span-level Supervised AttentionPengcheng Yin, Hao Fang, Graham Neubig, Adam Pauls, Emmanouil Antonios Platanios, Yu Su 0001, Sam Thomson, Jacob Andreas. 2810-2823 [doi]
• Domain Adaptation for Arabic Cross-Domain and Cross-Dialect Sentiment Analysis from Contextualized Word EmbeddingAbdellah El Mekki, Abdelkader El Mahdaouy, Ismail Berrada, Ahmed Khoumsi. 2824-2837 [doi]
• Multi-task Learning of Negation and Speculation for Targeted Sentiment ClassificationAndrew Moore, Jeremy Barnes. 2838-2869 [doi]
• A Disentangled Adversarial Neural Topic Model for Separating Opinions from Plots in User ReviewsGabriele Pergola, Lin Gui 0003, Yulan He. 2870-2883 [doi]
• Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment ClassificationXiaochen Hou, Peng Qi, Guangtao Wang, Rex Ying, Jing Huang 0019, Xiaodong He 0002, Bowen Zhou. 2884-2894 [doi]
• Emotion-Infused Models for Explainable Psychological Stress DetectionElsbeth Turcan, Smaranda Muresan, Kathleen R. McKeown. 2895-2909 [doi]
• Aspect-based Sentiment Analysis with Type-aware Graph Convolutional Networks and Layer EnsembleYuanhe Tian, Guimin Chen, Yan Song. 2910-2922 [doi]
• Supertagging-based Parsing with Linear Context-free Rewriting SystemsThomas Ruprecht, Richard Mörbitz. 2923-2935 [doi]
• Outside Computation with Superior FunctionsParker Riley, Daniel Gildea. 2936-2940 [doi]
• Learning Syntax from Naturally-Occurring BracketingsTianze Shi, Ozan Irsoy, Igor Malioutov, Lillian Lee. 2941-2949 [doi]
• Bot-Adversarial Dialogue for Safe Conversational AgentsJing Xu, Da Ju, Margaret Li, Y-Lan Boureau, Jason Weston, Emily Dinan. 2950-2968 [doi]
• Non-Autoregressive Semantic Parsing for Compositional Task-Oriented DialogArun Babu, Akshat Shrivastava, Armen Aghajanyan, Ahmed Aly, Angela Fan, Marjan Ghazvininejad. 2969-2978 [doi]
• Example-Driven Intent Prediction with ObserversShikib Mehri, Mihail Eric. 2979-2992 [doi]
• Imperfect also Deserves Reward: Multi-Level and Sequential Reward Modeling for Better Dialog ManagementZhengxu Hou, Bang Liu, Ruihui Zhao, Zijing Ou, Yafei Liu, Xi Chen, Yefeng Zheng. 2993-3001 [doi]
• Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue SystemsDerek Chen, Howard Chen, Yi Yang 0001, Alexander Lin, Zhou Yu. 3002-3017 [doi]
• Controlling Dialogue Generation with Semantic ExemplarsPrakhar Gupta, Jeffrey P. Bigham, Yulia Tsvetkov, Amy Pavel. 3018-3029 [doi]
• COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted ListLuyu Gao, Zhuyun Dai, Jamie Callan. 3030-3042 [doi]
• X-Class: Text Classification with Extremely Weak SupervisionZihan Wang, Dheeraj Mekala, Jingbo Shang. 3043-3053 [doi]
• Fine-tuning Encoders for Improved Monolingual and Zero-shot Polylingual Neural Topic ModelingAaron Mueller, Mark Dredze. 3054-3068 [doi]
• Exploring the Relationship Between Algorithm Performance, Vocabulary, and Run-Time in Text ClassificationWilson Fearn, Orion Weller, Kevin D. Seppi. 3069-3082 [doi]
• Faithfully Explainable Recommendation via Neural Logic ReasoningYaxin Zhu, Yikun Xian, Zuohui Fu, Gerard de Melo, Yongfeng Zhang. 3083-3090 [doi]
• You Sound Like Someone Who Watches Drama Movies: Towards Predicting Movie Preferences from Conversational InteractionsSergey Volokhin, Joyce C. Ho, Oleg Rokhlenko, Eugene Agichtein. 3091-3096 [doi]
• Reading and Acting while Blindfolded: The Need for Semantics in Text Game AgentsShunyu Yao, Karthik Narasimhan, Matthew J. Hausknecht. 3097-3102 [doi]
• SOrT-ing VQA Models : Contrastive Gradient Learning for Improved ConsistencySameer Dharur, Purva Tendulkar, Dhruv Batra, Devi Parikh, Ramprasaath R. Selvaraju. 3103-3111 [doi]
• Semi-Supervised Policy Initialization for Playing Games with Language HintsTsu-Jui Fu, William Yang Wang. 3112-3116 [doi]
• Revisiting Document Representations for Large-Scale Zero-Shot LearningJihyung Kil, Wei-Lun Chao. 3117-3128 [doi]
• Negative language transfer in learner English: A new datasetLeticia Farias Wanderley, Nicole Zhao, Carrie Demmans Epp. 3129-3142 [doi]
• SentSim: Crosslingual Semantic Evaluation of Machine TranslationYurun Song, Junchen Zhao, Lucia Specia. 3143-3156 [doi]
• Quality Estimation for Image Captions Based on Large-scale Human EvaluationsTomer Levinboim, Ashish V. Thapliyal, Piyush Sharma, Radu Soricut. 3157-3166 [doi]
• CaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic Negotiation SystemsKushal Chawla, Jaysa Ramirez, Rene Clever, Gale M. Lucas, Jonathan May, Jonathan Gratch. 3167-3185 [doi]
• News Headline Grouping as a Challenging NLU TaskPhilippe Laban, Lucas Bandarkar, Marti A. Hearst. 3186-3198 [doi]
• Olá, Bonjour, Salve! XFORMAL: A Benchmark for Multilingual Formality Style TransferEleftheria Briakou, Di Lu, Ke Zhang, Joel R. Tetreault. 3199-3216 [doi]
• Grouping Words with Semantic DiversityKarine Chubarian, Abdul Rafae Khan, Anastasios Sidiropoulos, Jia Xu. 3217-3228 [doi]
• Noise Stability Regularization for Improving BERT Fine-tuningHang Hua, Xingjian Li 0002, Dejing Dou, Cheng-Zhong Xu 0001, Jiebo Luo. 3229-3241 [doi]
• FlowPrior: Learning Expressive Priors for Latent Variable Sentence ModelsXiaoan Ding, Kevin Gimpel. 3242-3258 [doi]
• HTCInfoMax: A Global Model for Hierarchical Text Classification via Information MaximizationZhongfen Deng, Hao Peng, Dongxiao He, Jianxin Li 0002, Philip S. Yu. 3259-3265 [doi]
• Knowledge Guided Metric Learning for Few-Shot Text ClassificationDianbo Sui, Yubo Chen 0001, Binjie Mao, Delai Qiu, Kang Liu 0001, Jun Zhao 0001. 3266-3271 [doi]
• Ensemble of MRR and NDCG models for Visual DialogIdan Schwartz. 3272-3363 [doi]
• Supervised Neural Clustering via Latent Structured Output Learning: Application to Question IntentsIryna Haponchyk, Alessandro Moschitti. 3364-3374 [doi]
• ConVEx: Data-Efficient and Few-Shot Slot LabelingMatthew Henderson, Ivan Vulic. 3375-3389 [doi]
• CREAD: Combined Resolution of Ellipses and Anaphora in DialoguesBo-Hsiang Tseng, Shruti Bhargava, Jiarui Lu, Joel Ruben Antony Moniz, Dhivya Piraviperumal, Lin Li, Hong Yu. 3390-3406 [doi]
• Knowledge-Driven Slot Constraints for Goal-Oriented Dialogue SystemsPiyawat Lertvittayakumjorn, Daniele Bonadiman, Saab Mansour. 3407-3419 [doi]
• Clipping Loops for Sample-Efficient Dialogue Policy OptimisationYen-Chen Wu, Carl Edward Rasmussen. 3420-3428 [doi]
• Integrating Lexical Information into Entity Neighbourhood Representations for Relation PredictionIan D. Wood, Mark Johnson, Stephen Wan 0001. 3429-3436 [doi]
• Noisy-Labeled NER with Confidence EstimationKun Liu, Yao Fu, Chuanqi Tan, Mosha Chen, Ningyu Zhang, Songfang Huang, Sheng Gao. 3437-3445 [doi]
• TABBIE: Pretrained Representations of Tabular DataHiroshi Iida, Dung Thai, Varun Manjunatha, Mohit Iyyer. 3446-3456 [doi]
• Better Feature Integration for Named Entity RecognitionLu Xu, Zhanming Jie, Wei Lu 0011, Lidong Bing. 3457-3469 [doi]
• ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation LearningChih-Yao Chen, Cheng-Te Li. 3470-3479 [doi]
• Graph Convolutional Networks for Event Causality Identification with Rich Document-level StructuresMinh Tran Phu, Thien Huu Nguyen. 3480-3490 [doi]
• A Context-Dependent Gated Module for Incorporating Symbolic Semantics into Event Coreference ResolutionTuan Manh Lai, Heng Ji, Trung Bui, Quan Hung Tran, Franck Dernoncourt, Walter Chang. 3491-3499 [doi]
• Multi-Style Transfer with Discriminative Feedback on Disjoint CorpusNavita Goyal, Balaji Vasan Srinivasan, Anandhavelu Natarajan, Abhilasha Sancheti. 3500-3510 [doi]
• FUDGE: Controlled Text Generation With Future DiscriminatorsKevin Yang, Dan Klein. 3511-3535 [doi]
• Controllable Text Simplification with Explicit ParaphrasingMounica Maddela, Fernando Alva-Manchego, Wei Xu 0004. 3536-3553 [doi]
• Knowledge Graph Based Synthetic Corpus Generation for Knowledge-Enhanced Language Model Pre-trainingOshin Agarwal, Heming Ge, Siamak Shakeri, Rami Al-Rfou. 3554-3565 [doi]
• Choose Your Own Adventure: Paired Suggestions in Collaborative Writing for Evaluating Story Generation ModelsElizabeth Clark, Noah A. Smith. 3566-3575 [doi]
• InfoXLM: An Information-Theoretic Framework for Cross-Lingual Language Model Pre-TrainingZewen Chi, Li Dong 0004, Furu Wei, Nan Yang 0002, Saksham Singhal, Wenhui Wang, Xia Song, Xian-Ling Mao, Heyan Huang, Ming Zhou 0001. 3576-3588 [doi]
• Context-Interactive Pre-Training for Document Machine TranslationPengcheng Yang, Pei Zhang 0011, Boxing Chen, Jun Xie, Weihua Luo. 3589-3595 [doi]
• Code-Mixing on Sesame Street: Dawn of the Adversarial PolyglotsSamson Tan, Shafiq R. Joty. 3596-3616 [doi]
• X-METRA-ADA: Cross-lingual Meta-Transfer learning Adaptation to Natural Language Understanding and Question AnsweringMeryem M'hamdi, Doo Soon Kim, Franck Dernoncourt, Trung Bui, Xiang Ren 0001, Jonathan May. 3617-3632 [doi]
• Explicit Alignment Objectives for Multilingual Bidirectional EncodersJunjie Hu 0001, Melvin Johnson, Orhan Firat, Aditya Siddhant, Graham Neubig. 3633-3643 [doi]
• Cross-lingual Cross-modal Pretraining for Multimodal RetrievalHongliang Fei, Tan Yu, Ping Li 0001. 3644-3650 [doi]
• Wikipedia Entities as Rendezvous across Languages: Grounding Multilingual Language Models by Predicting Wikipedia HyperlinksIacer Calixto, Alessandro Raganato, Tommaso Pasini. 3651-3661 [doi]
• multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule ReasoningSwarnadeep Saha, Prateek Yadav, Mohit Bansal. 3662-3677 [doi]
• Adaptable and Interpretable Neural MemoryOver Symbolic KnowledgePat Verga, Haitian Sun, Livio Baldini Soares, William W. Cohen. 3678-3691 [doi]
• CLEVR_HYP: A Challenge Dataset and Baselines for Visual Question Answering with Hypothetical Actions over ImagesShailaja Keyur Sampat, Akshay Kumar, Yezhou Yang, Chitta Baral. 3692-3709 [doi]
• Refining Targeted Syntactic Evaluation of Language ModelsBenjamin Newman, Kai-Siang Ang, Julia Gong, John Hewitt. 3710-3723 [doi]
• Universal Adversarial Attacks with Natural Triggers for Text ClassificationLiwei Song, Xinwei Yu, Hsuan Tung Peng, Karthik Narasimhan. 3724-3733 [doi]
• QuadrupletBERT: An Efficient Model For Embedding-Based Large-Scale RetrievalPeiyang Liu, Sen Wang, Xi Wang, Wei Ye 0004, Shikun Zhang. 3734-3739 [doi]
• Dynamically Disentangling Social Bias from Task-Oriented Representations with Adversarial AttackLiwen Wang, Yuanmeng Yan, Keqing He, Yanan Wu, Weiran Xu. 3740-3750 [doi]
• An Empirical Investigation of Bias in the Multimodal Analysis of Financial Earnings CallsRamit Sawhney, Arshiya Aggarwal, Rajiv Ratn Shah. 3751-3757 [doi]
• Beyond Fair Pay: Ethical Implications of NLP CrowdsourcingBoaz Shmueli, Jan Fell, Soumya Ray, Lun-Wei Ku. 3758-3769 [doi]
• On Transferability of Bias Mitigation Effects in Language Model Fine-TuningXisen Jin, Francesco Barbieri, Brendan Kennedy, Aida Mostafazadeh Davani, Leonardo Neves, Xiang Ren 0001. 3770-3783 [doi]
• Case Study: Deontological Ethics in NLPShrimai Prabhumoye, Brendon Boldt, Ruslan Salakhutdinov, Alan W. Black. 3784-3798 [doi]
• Privacy Regularization: Joint Privacy-Utility Optimization in LanguageModelsFatemehsadat Mireshghallah, Huseyin A. Inan, Marcello Hasegawa, Victor Rühle, Taylor Berg-Kirkpatrick, Robert Sim. 3799-3807 [doi]
• On the Impact of Random Seeds on the Fairness of Clinical ClassifiersSilvio Amir, Jan-Willem van de Meent, Byron C. Wallace. 3808-3823 [doi]
• Topic Model or Topic Twaddle? Re-evaluating Semantic Interpretability MeasuresCaitlin Doogan, Wray L. Buntine. 3824-3848 [doi]
• Discourse Probing of Pretrained Language ModelsFajri Koto, Jey Han Lau, Timothy Baldwin. 3849-3864 [doi]
• UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra CostZhen Wu, Lijun Wu, Qi Meng, Yingce Xia, Shufang Xie 0003, Tao Qin, Xinyu Dai, Tie-Yan Liu. 3865-3878 [doi]
• tWT-WT: A Dataset to Assert the Role of Target Entities for Detecting Stance of TweetsAyush Kaushal, Avirup Saha, Niloy Ganguly. 3879-3889 [doi]
• Learning to Learn to be Right for the Right ReasonsPride Kavumba, Benjamin Heinzerling, Ana Brassard, Kentaro Inui. 3890-3898 [doi]
• Double Perturbation: On the Robustness of Robustness and Counterfactual Bias EvaluationChong Zhang, Jieyu Zhao, Huan Zhang 0001, Kai-Wei Chang, Cho-Jui Hsieh. 3899-3916 [doi]
• Explaining Neural Network Predictions on Sentence Pairs via Learning Word-Group MasksHanjie Chen, Song Feng, Jatin Ganhotra, Hui Wan 0001, R. Chulaka Gunasekara, Sachindra Joshi, Yangfeng Ji. 3917-3930 [doi]
• Almost Free Semantic Draft for Neural Machine TranslationXi Ai, Bin Fang. 3931-3941 [doi]
• Pruning-then-Expanding Model for Domain Adaptation of Neural Machine TranslationShuhao Gu, Yang Feng 0004, Wanying Xie. 3942-3952 [doi]
• Multi-Hop Transformer for Document-Level Machine TranslationLong Zhang, Tong Zhang, Haibo Zhang, Baosong Yang, Wei Ye 0004, Shikun Zhang. 3953-3963 [doi]
• Continual Learning for Neural Machine TranslationYue Cao, Hao-Ran Wei, Boxing Chen, Xiaojun Wan 0001. 3964-3974 [doi]
• Self-Training for Unsupervised Neural Machine Translation in Unbalanced Training Data ScenariosHaipeng Sun, Rui Wang 0015, Kehai Chen, Masao Utiyama, Eiichiro Sumita, Tiejun Zhao. 3975-3981 [doi]
• Smart-Start Decoding for Neural Machine TranslationJian Yang, Shuming Ma, Dongdong Zhang 0001, Juncheng Wan, Zhoujun Li, Ming Zhou 0001. 3982-3988 [doi]
• Multi-Task Learning with Shared Encoder for Non-Autoregressive Machine TranslationYongchang Hao, Shilin He, Wenxiang Jiao, Zhaopeng Tu, Michael R. Lyu, Xing Wang 0007. 3989-3996 [doi]
• ER-AE: Differentially Private Text Generation for Authorship AnonymizationHaohan Bo, Steven H. H. Ding, Benjamin C. M. Fung, Farkhund Iqbal. 3997-4007 [doi]
• Distantly Supervised Transformers For E-Commerce Product QAHappy Mittal, Aniket Chakrabarti, Belhassen Bayar, Animesh Anant Sharma, Nikhil Rasiwasia. 4008-4017 [doi]
• Quantitative Day Trading from Natural Language using Reinforcement LearningRamit Sawhney, Arnav Wadhwa, Shivam Agarwal, Rajiv Ratn Shah. 4018-4030 [doi]
• Restoring and Mining the Records of the Joseon Dynasty via Neural Language Modeling and Machine TranslationKyeongpil Kang, Kyohoon Jin, Soyoung Yang, Soojin Jang, Jaegul Choo, Youngbin Kim. 4031-4042 [doi]
• Modeling Diagnostic Label Correlation for Automatic ICD CodingShang-Chi Tsai, Chao-Wei Huang, Yun-Nung Chen. 4043-4052 [doi]
• Self-Supervised Contrastive Learning for Efficient User Satisfaction Prediction in Conversational AgentsMohammad Kachuee, Hao Yuan, Young-Bum Kim, Sungjin Lee. 4053-4064 [doi]
• A recipe for annotating grounded clarificationsLuciana Benotti, Patrick Blackburn. 4065-4077 [doi]
• Grey-box Adversarial Attack And Defence For Sentiment ClassificationYing Xu, Xu Zhong, Antonio Jimeno-Yepes, Jey Han Lau. 4078-4087 [doi]
• How low is too low? A monolingual take on lemmatisation in Indian languagesSaunack Kumar, Saurav Kumar, Pushpak Bhattacharyya. 4088-4094 [doi]
• Causal Effects of Linguistic PropertiesReid Pryzant, Dallas Card, Dan Jurafsky, Victor Veitch, Dhanya Sridhar. 4095-4109 [doi]
• Dynabench: Rethinking Benchmarking in NLPDouwe Kiela, Max Bartolo, Yixin Nie, Divyansh Kaushik, Atticus Geiger, Zhengxuan Wu, Bertie Vidgen, Grusha Prasad, Amanpreet Singh, Pratik Ringshia, Zhiyi Ma, Tristan Thrush, Sebastian Riedel 0001, Zeerak Waseem, Pontus Stenetorp, Robin Jia, Mohit Bansal, Christopher Potts, Adina Williams. 4110-4124 [doi]
• Translational NLP: A New Paradigm and General Principles for Natural Language Processing ResearchDenis Newman-Griffis, Jill Fain Lehman, Carolyn P. Rosé, Harry Hochheiser. 4125-4138 [doi]
• Predicting Discourse Trees from Transformer-based Neural SummarizersWen Xiao, Patrick Huber, Giuseppe Carenini. 4139-4152 [doi]
• Probing for Bridging Inference in Transformer Language ModelsOnkar Pandit, Yufang Hou. 4153-4163 [doi]
• Is Incoherence Surprising? Targeted Evaluation of Coherence Prediction from Language ModelsAnne Beyer, Sharid Loáiciga, David Schlangen. 4164-4173 [doi]
• Stay Together: A System for Single and Split-antecedent Anaphora ResolutionJuntao Yu, Nafise Sadat Moosavi, Silviu Paun, Massimo Poesio. 4174-4184 [doi]
• Redefining Absent Keyphrases and their Effect on Retrieval EffectivenessFlorian Boudin, Ygor Gallina. 4185-4193 [doi]
• CoRT: Complementary Rankings from TransformersMarco Wrzalik, Dirk Krechel. 4194-4204 [doi]
• Multi-source Neural Topic Modeling in Multi-view Embedding SpacesPankaj Gupta, Yatin Chaudhary, Hinrich Schütze. 4205-4217 [doi]
• Inductive Topic Variational Graph Auto-Encoder for Text ClassificationQianqian Xie, Jimin Huang, Pan Du, Min Peng, Jian-Yun Nie. 4218-4227 [doi]
• Self-Alignment Pretraining for Biomedical Entity RepresentationsFangyu Liu 0001, Ehsan Shareghi, Zaiqiao Meng, Marco Basaldella, Nigel Collier. 4228-4238 [doi]
• TaxoClass: Hierarchical Multi-Label Text Classification Using Only Class NamesJiaming Shen, Wenda Qiu, Yu Meng 0001, Jingbo Shang, Xiang Ren 0001, Jiawei Han 0001. 4239-4249 [doi]
• MERMAID: Metaphor Generation with Symbolism and Discriminative DecodingTuhin Chakrabarty, Xurui Zhang, Smaranda Muresan, Nanyun Peng. 4250-4261 [doi]
• On Learning Text Style Transfer with Direct RewardsYixin Liu, Graham Neubig, John Wieting. 4262-4273 [doi]
• Focused Attention Improves Document-Grounded GenerationShrimai Prabhumoye, Kazuma Hashimoto, Yingbo Zhou, Alan W. Black, Ruslan Salakhutdinov. 4274-4287 [doi]
• NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic ConstraintsXiming Lu, Peter West, Rowan Zellers, Ronan Le Bras, Chandra Bhagavatula, Yejin Choi. 4288-4299 [doi]
• Ask what's missing and what's useful: Improving Clarification Question Generation using Global KnowledgeBodhisattwa Prasad Majumder, Sudha Rao, Michel Galley, Julian J. McAuley. 4300-4312 [doi]
• Progressive Generation of Long Text with Pretrained Language ModelsBowen Tan, Zichao Yang, Maruan Al-Shedivat, Eric P. Xing, Zhiting Hu. 4313-4324 [doi]
• SOCCER: An Information-Sparse Discourse State Tracking Collection in the Sports Commentary DomainRuochen Zhang, Carsten Eickhoff. 4325-4333 [doi]
• Plot-guided Adversarial Example Construction for Evaluating Open-domain Story GenerationSarik Ghazarian, Zixi Liu, Akash SM, Ralph M. Weischedel, Aram Galstyan, Nanyun Peng. 4334-4344 [doi]
• MultiOpEd: A Corpus of Multi-Perspective News EditorialsSiyi Liu, Sihao Chen, Xander Uyttendaele, Dan Roth. 4345-4361 [doi]
• Swords: A Benchmark for Lexical Substitution with Improved Data Coverage and QualityMina Lee 0002, Chris Donahue, Robin Jia, Alexander Iyabor, Percy Liang. 4362-4379 [doi]
• "I'm Not Mad": Commonsense Implications of Negation and ContradictionLiwei Jiang, Antoine Bosselut, Chandra Bhagavatula, Yejin Choi. 4380-4397 [doi]
• Identifying Medical Self-Disclosure in Online CommunitiesMina Valizadeh, Pardis Ranjbar-Noiey, Cornelia Caragea, Natalie Parde. 4398-4408 [doi]
• Language in a (Search) Box: Grounding Language Learning in Real-World Human-Machine InteractionFederico Bianchi, Ciro Greco, Jacopo Tagliabue. 4409-4415 [doi]
• Finding Concept-specific Biases in Form-Meaning AssociationsTiago Pimentel, Brian Roark, Søren Wichmann, Ryan Cotterell, Damián E. Blasi. 4416-4425 [doi]
• How (Non-)Optimal is the Lexicon?Tiago Pimentel, Irene Nikkarinen, Kyle Mahowald, Ryan Cotterell, Damián E. Blasi. 4426-4438 [doi]
• Word Complexity is in the Eye of the BeholderSian Gooding, Ekaterina Kochmar, Seid Muhie Yimam, Chris Biemann. 4439-4449 [doi]
• Linguistic Complexity Loss in Text-Based TherapyJason Wei, Kelly Finn, Emma Templeton, Thalia Wheatley, Soroush Vosoughi. 4450-4459 [doi]
• Ab Antiquo: Neural Proto-language ReconstructionCarlo Meloni, Shauli Ravfogel, Yoav Goldberg. 4460-4473 [doi]
• On Biasing Transformer Attention Towards MonotonicityAnnette Rios, Chantal Amrhein, Noëmi Aepli, Rico Sennrich. 4474-4488 [doi]
• Extracting a Knowledge Base of Mechanisms from COVID-19 PapersTom Hope, Aida Amini, David Wadden, Madeleine van Zuylen, Sravanthi Parasa, Eric Horvitz, Daniel S. Weld, Roy Schwartz 0001, Hannaneh Hajishirzi. 4489-4503 [doi]
• Constrained Multi-Task Learning for Event Coreference ResolutionJing Lu, Vincent Ng. 4504-4514 [doi]
• Empirical Evaluation of Pre-trained Transformers for Human-Level NLP: The Role of Sample Size and DimensionalityAdithya V. Ganesan, Matthew Matero, Aravind Reddy Ravula, Huy Vu, H. Andrew Schwartz. 4515-4532 [doi]
• Leveraging Deep Representations of Radiology Reports in Survival Analysis for Predicting Heart Failure Patient MortalityHyun Gi Lee, Evan Sholle, Ashley Beecy, Subhi Al'Aref, Yifan Peng. 4533-4538 [doi]
• On the Use of Context for Predicting Citation Worthiness of Sentences in Scholarly ArticlesRakesh Gosangi, Ravneet Arora, Mohsen Gheisarieha, Debanjan Mahata, Haimin Zhang. 4539-4545 [doi]
• Data and Model Distillation as a Solution for Domain-transferable Fact VerificationMitch Paul Mithun, Sandeep Suntwal, Mihai Surdeanu. 4546-4552 [doi]
• Adapting Coreference Resolution for Processing Violent Death NarrativesAnkith Uppunda, Susan D. Cochran, Jacob G. Foster, Alina Arseniev-Koehler, Vickie M. Mays, Kai-Wei Chang. 4553-4559 [doi]
• Time-Stamped Language Model: Teaching Language Models to Understand The Flow of EventsHossein Rajaby Faghihi, Parisa KordJamshidi. 4560-4570 [doi]
• If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question AnsweringVikas Yadav, Steven Bethard, Mihai Surdeanu. 4571-4581 [doi]
• SPARTQA: A Textual Question Answering Benchmark for Spatial ReasoningRoshanak Mirzaee, Hossein Rajaby Faghihi, Qiang Ning, Parisa KordJamshidi. 4582-4598 [doi]
• A Dataset of Information-Seeking Questions and Answers Anchored in Research PapersPradeep Dasigi, Kyle Lo, Iz Beltagy, Arman Cohan, Noah A. Smith, Matt Gardner 0001. 4599-4610 [doi]
• Differentiable Open-Ended Commonsense ReasoningBill Yuchen Lin, Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Xiang Ren 0001, William W. Cohen. 4611-4625 [doi]
• Does Structure Matter? Encoding Documents for Machine Reading ComprehensionHui Wan 0001, Song Feng, R. Chulaka Gunasekara, Siva Sankalp Patel, Sachindra Joshi, Luis A. Lastras. 4626-4634 [doi]
• Multi-Step Reasoning Over Unstructured Text with Beam Dense RetrievalChen Zhao, Chenyan Xiong, Jordan L. Boyd-Graber, Hal Daumé III. 4635-4641 [doi]
• Scalable and Interpretable Semantic Change DetectionSyrielle Montariol, Matej Martinc, Lidia Pivovarova. 4642-4652 [doi]
• Scalar Adjective Identification and Multilingual RankingAina Garí Soler, Marianna Apidianaki. 4653-4660 [doi]
• ESC: Redesigning WSD with Extractive Sense ComprehensionEdoardo Barba, Tommaso Pasini, Roberto Navigli. 4661-4672 [doi]
• Recent advances in neural metaphor processing: A linguistic, cognitive and social perspectiveXiaoyu Tong, Ekaterina Shutova, Martha Lewis. 4673-4686 [doi]
• Constructing Taxonomies from Pretrained Language ModelsCatherine Chen, Kevin Lin, Dan Klein. 4687-4700 [doi]
• Event Representation with Sequential, Semi-Supervised Discrete VariablesMehdi Rezaee, Francis Ferraro. 4701-4716 [doi]
• Seq2Emo: A Sequence to Multi-Label Emotion Classification ModelChenyang Huang 0001, Amine Trabelsi, Xuebin Qin, Nawshad Farruque, Lili Mou, Osmar R. Zaïane. 4717-4724 [doi]
• Knowledge Enhanced Masked Language Model for Stance DetectionKornraphop Kawintiranon, Lisa Singh. 4725-4735 [doi]
• Learning Paralinguistic Features from Audiobooks through Style Voice ConversionZakaria Aldeneh, Matthew Perez, Emily Mower Provost. 4736-4745 [doi]
• Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification TasksZixuan Ke, Hu Xu, Bing Liu. 4746-4755 [doi]
• Adversarial Learning for Zero-Shot Stance Detection on Social MediaEmily Allaway, Malavika Srikanth, Kathleen R. McKeown. 4756-4767 [doi]
• Efficiently Summarizing Text and Graph Encodings of Multi-Document ClustersRamakanth Pasunuru, Mengwen Liu, Mohit Bansal, Sujith Ravi, Markus Dreyer. 4768-4779 [doi]
• Enriching Transformers with Structured Tensor-Product Representations for Abstractive SummarizationYichen Jiang, Asli Celikyilmaz, Paul Smolensky, Paul Soulos, Sudha Rao, Hamid Palangi, Roland Fernandez, Caitlin Smith, Mohit Bansal, Jianfeng Gao. 4780-4793 [doi]
• What's in a Summary? Laying the Groundwork for Advances in Hospital-Course SummarizationGriffin Adams, Emily Alsentzer, Mert Ketenci, Jason Zucker, Noémie Elhadad. 4794-4811 [doi]
• Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality MetricsArtidoro Pagnoni, Vidhisha Balachandran, Yulia Tsvetkov. 4812-4829 [doi]
• GSum: A General Framework for Guided Neural Abstractive SummarizationZi-Yi Dou, Pengfei Liu 0003, Hiroaki Hayashi, Zhengbao Jiang, Graham Neubig. 4830-4842 [doi]
• What Will it Take to Fix Benchmarking in Natural Language Understanding?Samuel R. Bowman, George E. Dahl. 4843-4855 [doi]
• TuringAdvice: A Generative and Dynamic Evaluation of Language UseRowan Zellers, Ari Holtzman, Elizabeth Clark, Lianhui Qin, Ali Farhadi, Yejin Choi. 4856-4880 [doi]
• Multitask Learning for Emotionally Analyzing Sexual Abuse DisclosuresRamit Sawhney, Puneet Mathur, Taru Jain, Akash Kumar Gautam, Rajiv Ratn Shah. 4881-4892 [doi]
• Self Promotion in US Congressional TweetsJun Wang, Kelly Cui, Bei Yu. 4893-4899 [doi]
• Profiling of Intertextuality in Latin Literature Using Word EmbeddingsPatrick J. Burns, James Brofos, Kyle Li, Pramit Chaudhuri, Joseph P. Dexter. 4900-4907 [doi]
• Identifying inherent disagreement in natural language inferenceXinliang Frederick Zhang, Marie-Catherine de Marneffe. 4908-4915 [doi]
• Modeling Human Mental States with an Entity-based Narrative GraphI-Ta Lee, Maria Leonor Pacheco, Dan Goldwasser. 4916-4926 [doi]
• A Simple and Efficient Multi-Task Learning Approach for Conditioned Dialogue GenerationYan Zeng, Jian-Yun Nie. 4927-4939 [doi]
• Hurdles to Progress in Long-form Question AnsweringKalpesh Krishna, Aurko Roy, Mohit Iyyer. 4940-4957 [doi]
• ENTRUST: Argument Reframing with Language Models and EntailmentTuhin Chakrabarty, Christopher Hidey, Smaranda Muresan. 4958-4971 [doi]
• Paragraph-level Simplification of Medical TextsAshwin Devaraj, Iain James Marshall, Byron C. Wallace, Junyi Jessy Li. 4972-4984 [doi]
• An Empirical Study on Neural Keyphrase GenerationRui Meng, Xingdi Yuan, Tong Wang, Sanqiang Zhao, Adam Trischler, Daqing He. 4985-5007 [doi]
• Attention Head Masking for Inference Time Content Selection in Abstractive SummarizationShuyang Cao, Lu Wang 0008. 5008-5016 [doi]
• Factual Probing Is [MASK]: Learning vs. Learning to RecallZexuan Zhong, Dan Friedman, Danqi Chen. 5017-5033 [doi]
• Evaluating Saliency Methods for Neural Language ModelsShuoyang Ding, Philipp Koehn. 5034-5052 [doi]
• Contextualized Perturbation for Textual Adversarial AttackDianqi Li, Yizhe Zhang, Hao Peng, Liqun Chen, Chris Brockett, Ming-Ting Sun, Bill Dolan. 5053-5069 [doi]
• DirectProbe: Studying Representations without ClassifiersYichu Zhou, Vivek Srikumar. 5070-5083 [doi]
• Evaluating the Values of Sources in Transfer LearningMd. Rizwan Parvez, Kai-Wei Chang. 5084-5116 [doi]
• Too Much in Common: Shifting of Embeddings in Transformer Language Models and its ImplicationsDaniel Bis, Maksim Podkorytov, Xiuwen Liu. 5117-5130 [doi]
• On the Inductive Bias of Masked Language Modeling: From Statistical to Syntactic DependenciesTianyi Zhang, Tatsunori Hashimoto. 5131-5146 [doi]
• Limitations of Autoregressive Models and Their AlternativesChu-Cheng Lin, Aaron Jaech, Xin Li, Matthew R. Gormley, Jason Eisner. 5147-5173 [doi]
• On the Transformer Growth for Progressive BERT TrainingXiaotao Gu, Liyuan Liu, Hongkun Yu, Jing Li, Chen Chen 0005, Jiawei Han 0001. 5174-5180 [doi]
• Revisiting Simple Neural Probabilistic Language ModelsSimeng Sun, Mohit Iyyer. 5181-5188 [doi]
• ReadTwice: Reading Very Large Documents with MemoriesYury Zemlyanskiy, Joshua Ainslie, Michiel de Jong, Philip Pham, Ilya Eckstein, Fei Sha. 5189-5195 [doi]
• SCRIPT: Self-Critic PreTraining of TransformersErik Nijkamp, Bo Pang, Ying Nian Wu, Caiming Xiong. 5196-5202 [doi]
• Learning How to Ask: Querying LMs with Mixtures of Soft PromptsGuanghui Qin, Jason Eisner. 5203-5212 [doi]
• Nutri-bullets Hybrid: Consensual Multi-document SummarizationDarsh J. Shah, Lili Yu, Tao Lei 0001, Regina Barzilay. 5213-5222 [doi]
• AVA: an Automatic eValuation Approach for Question Answering SystemsThuy Vu, Alessandro Moschitti. 5223-5233 [doi]
• SpanPredict: Extraction of Predictive Document Spans with Neural AttentionVivek Subramanian, Matthew Engelhard, Samuel Berchuck, Liqun Chen, Ricardo Henao, Lawrence Carin. 5234-5258 [doi]
• Text Editing by CommandFelix Faltings, Michel Galley, Gerold Hintz, Chris Brockett, Chris Quirk, Jianfeng Gao, Bill Dolan. 5259-5274 [doi]
• A Deep Metric Learning Approach to Account LinkingAleem Khan, Elizabeth Fleming, Noah Schofield, Marcus Bishop, Nicholas Andrews. 5275-5287 [doi]
• Improving Factual Completeness and Consistency of Image-to-Text Radiology Report GenerationYasuhide Miura, Yuhao Zhang 0004, Emily Bao Tsai, Curtis Langlotz, Dan Jurafsky. 5288-5304 [doi]
• Multimodal End-to-End Sparse Model for Emotion RecognitionWenliang Dai, Samuel Cahyawijaya, Zihan Liu, Pascale Fung. 5305-5316 [doi]
• MIMOQA: Multimodal Input Multimodal Output Question AnsweringHrituraj Singh, Anshul Nasery, Denil Mehta, Aishwarya Agarwal, Jatin Lamba, Balaji Vasan Srinivasan. 5317-5332 [doi]
• OCID-Ref: A 3D Robotic Dataset With Embodied Language For Clutter Scene GroundingKe-Jyun Wang, Yun-Hsuan Liu, Hung-Ting Su, Jen-Wei Wang, Yu-Siang Wang, Winston H. Hsu, Wen-Chin Chen. 5333-5338 [doi]
• Unsupervised Vision-and-Language Pre-training Without Parallel Images and CaptionsLiunian Harold Li, Haoxuan You, Zhecan Wang, Alireza Zareian, Shih-Fu Chang, Kai-Wei Chang. 5339-5350 [doi]
• Multitasking Inhibits Semantic DriftAthul Paul Jacob, Mike Lewis, Jacob Andreas. 5351-5366 [doi]
• Probing Contextual Language Models for Common Ground with Visual RepresentationsGabriel Ilharco, Rowan Zellers, Ali Farhadi, Hannaneh Hajishirzi. 5367-5377 [doi]
• BBAEG: Towards BERT-based Biomedical Adversarial Example Generation for Text ClassificationIshani Mondal. 5378-5384 [doi]
• Targeted Adversarial Training for Natural Language UnderstandingLis Pereira, Xiaodong Liu, Hao Cheng 0002, Hoifung Poon, Jianfeng Gao, Ichiro Kobayashi. 5385-5393 [doi]
• Latent-Optimized Adversarial Neural Transfer for Sarcasm DetectionXu Guo, Boyang Li, Han Yu 0001, Chunyan Miao. 5394-5407 [doi]
• Self-training Improves Pre-training for Natural Language UnderstandingJingfei Du, Edouard Grave, Beliz Gunel, Vishrav Chaudhary, Onur Celebi, Michael Auli, Veselin Stoyanov, Alexis Conneau. 5408-5418 [doi]
• Supporting Clustering with Contrastive LearningDejiao Zhang, Feng Nan, Xiaokai Wei, Shang-wen Li 0001, Henghui Zhu, Kathleen R. McKeown, Ramesh Nallapati, Andrew O. Arnold, Bing Xiang. 5419-5430 [doi]
• TITA: A Two-stage Interaction and Topic-Aware Text Matching ModelXingwu Sun, Yanling Cui, Hongyin Tang, Qiuyu Zhu, Fuzheng Zhang, Beihong Jin. 5431-5440 [doi]
• Neural Quality Estimation with Multiple Hypotheses for Grammatical Error CorrectionZhenghao Liu, Xiaoyuan Yi, Maosong Sun, Liner Yang, Tat-Seng Chua. 5441-5452 [doi]
• Neural Network Surgery: Injecting Data Patterns into Pre-trained Models with Minimal Instance-wise Side EffectsZhiyuan Zhang, Xuancheng Ren, Qi Su 0001, Xu Sun 0001, Bin He. 5453-5466 [doi]
• Discrete Argument Representation Learning for Interactive Argument Pair IdentificationLu Ji, Zhongyu Wei, Jing Li, Qi Zhang 0001, Xuanjing Huang. 5467-5478 [doi]
• On Unifying Misinformation DetectionNayeon Lee, Belinda Z. Li, Sinong Wang, Pascale Fung, Hao Ma, Wen-tau Yih, Madian Khabsa. 5479-5485 [doi]
• Frustratingly Easy Edit-based Linguistic Steganography with a Masked Language ModelHonai Ueoka, Yugo Murawaki, Sadao Kurohashi. 5486-5492 [doi]
• Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum LearningJason Wei, Chengyu Huang, Soroush Vosoughi, Yu Cheng, Shiqi Xu. 5493-5500 [doi]
• Do RNN States Encode Abstract Phonological Alternations?Miikka Silfverberg, Francis M. Tyers, Garrett Nicolai, Mans Hulden. 5501-5513 [doi]
• Pre-training with Meta Learning for Chinese Word SegmentationZhen Ke, Liang Shi, Songtao Sun, Erli Meng, Bin Wang 0004, Xipeng Qiu. 5514-5523 [doi]
• Decompose, Fuse and Generate: A Formation-Informed Method for Chinese Definition GenerationHua Zheng, Damai Dai, Lei Li, Tianyu Liu 0001, Zhifang Sui, Baobao Chang, Yang Liu. 5524-5531 [doi]
• User-Generated Text Corpus for Evaluating Japanese Morphological Analysis and Lexical NormalizationShohei Higashiyama, Masao Utiyama, Taro Watanabe, Eiichiro Sumita. 5532-5541 [doi]
• GPT Perdetry Test: Generating new meanings for new wordsNikolay Malkin, Sameera Lanka, Pranav Goel, Sudha Rao, Nebojsa Jojic. 5542-5553 [doi]
• Universal Semantic Tagging for English and Mandarin ChineseWenxi Li, Yiyang Hou, Yajie Ye, Li Liang, Weiwei Sun. 5554-5566 [doi]
• ShadowGNN: Graph Projection Neural Network for Text-to-SQL ParserZhi Chen 0006, Lu Chen 0002, Yanbin Zhao, Ruisheng Cao, Zihan Xu, Su Zhu, Kai Yu 0004. 5567-5577 [doi]
• Contextualized and Generalized Sentence Representations by Contrastive Self-Supervised Learning: A Case Study on Discourse Relation AnalysisHirokazu Kiyomaru, Sadao Kurohashi. 5578-5584 [doi]
• AMR Parsing with Action-Pointer TransformerJiawei Zhou, Tahira Naseem, Ramón Fernandez Astudillo, Radu Florian. 5585-5598 [doi]
• NL-EDIT: Correcting Semantic Parse Errors through Natural Language InteractionAhmed Elgohary, Christopher Meek, Matthew Richardson, Adam Fourney, Gonzalo A. Ramos, Ahmed Hassan Awadallah. 5599-5610 [doi]
• Unsupervised Concept Representation Learning for Length-Varying Text SimilarityXuchao Zhang, Bo Zong, Wei Cheng 0002, Jingchao Ni, Yanchi Liu, Haifeng Chen. 5611-5620 [doi]
• Augmenting Knowledge-grounded Conversations with Sequential Knowledge TransitionHaolan Zhan, Hainan Zhang, Hongshen Chen, Zhuoye Ding, Yongjun Bao, Yanyan Lan. 5621-5630 [doi]
• Adversarial Self-Supervised Learning for Out-of-Domain DetectionZhiyuan Zeng, Keqing He, Yuanmeng Yan, Hong Xu, Weiran Xu. 5631-5639 [doi]
• Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue StateTrackingZhaojiang Lin, Bing Liu, Seungwhan Moon, Paul A. Crook, Zhenpeng Zhou, Zhiguang Wang, Zhou Yu, Andrea Madotto, Eunjoon Cho, Rajen Subba. 5640-5648 [doi]
• Hierarchical Transformer for Task Oriented Dialog SystemsBishal Santra, Potnuru Anusha, Pawan Goyal. 5649-5658 [doi]
• Measuring the 'I don't know' Problem through the Lens of Gricean QuantityHuda Khayrallah, João Sedoc. 5659-5670 [doi]
• RTFE: A Recursive Temporal Fact Embedding Framework for Temporal Knowledge Graph CompletionYouri Xu, Haihong E, Meina Song, Wenyu Song, Xiaodong Lv, Haotian Wang, Jinrui Yang. 5671-5681 [doi]
• Open Hierarchical Relation ExtractionKai Zhang, Yuan Yao, Ruobing Xie, Xu Han 0007, Zhiyuan Liu 0001, Fen Lin, Leyu Lin, Maosong Sun. 5682-5693 [doi]
• Jointly Extracting Explicit and Implicit Relational Triples with Reasoning Pattern Enhanced Binary Pointer NetworkYubo Chen 0002, Yunqi Zhang, Changran Hu, Yongfeng Huang. 5694-5703 [doi]
• Multi-Grained Knowledge Distillation for Named Entity RecognitionXuan Zhou, Xiao Zhang, Chenyang Tao, Junya Chen, Bing Xu, Wei Wang, Jing Xiao. 5704-5716 [doi]
• SGG: Learning to Select, Guide, and Generate for Keyphrase GenerationJing Zhao, Junwei Bao 0001, Yifan Wang, Youzheng Wu, Xiaodong He 0002, Bowen Zhou. 5717-5726 [doi]
• Towards Sentiment and Emotion aided Multi-modal Speech Act Classification in TwitterTulika Saha, Apoorva Upadhyaya, Sriparna Saha 0001, Pushpak Bhattacharyya. 5727-5737 [doi]
• Generative Imagination Elevates Machine TranslationQuanyu Long, Mingxuan Wang, Lei Li. 5738-5748 [doi]
• Non-Autoregressive Translation by Learning Target Categorical CodesYu Bao, Shujian Huang, Tong Xiao, Dongqi Wang, Xinyu Dai, Jiajun Chen. 5749-5759 [doi]
• Training Data Augmentation for Code-Mixed TranslationAbhirut Gupta, Aditya Vavre, Sunita Sarawagi. 5760-5766 [doi]
• Rethinking Perturbations in Encoder-Decoders for Fast TrainingSho Takase, Shun Kiyono. 5767-5780 [doi]
• Context-aware Decoder for Neural Machine Translation using a Target-side Document-Level Language ModelAmane Sugiyama, Naoki Yoshinaga 0001. 5781-5791 [doi]
• Machine Translated Text Detection Through Text Similarity with Round-Trip TranslationHoang-Quoc Nguyen-Son, Tran Thao Phuong, Seira Hidano, Ishita Gupta, Shinsaku Kiyomoto. 5792-5797 [doi]
• TR-BERT: Dynamic Token Reduction for Accelerating BERT InferenceDeming Ye, Yankai Lin, Yufei Huang, Maosong Sun. 5798-5809 [doi]
• Breadth First Reasoning Graph for Multi-hop Question AnsweringYongjie Huang, Meng Yang. 5810-5821 [doi]
• Improving Zero-Shot Cross-lingual Transfer for Multilingual Question Answering over Knowledge GraphYucheng Zhou, Xiubo Geng, Tao Shen, Wenqiang Zhang, Daxin Jiang. 5822-5834 [doi]
• RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question AnsweringYingqi Qu, Yuchen Ding, Jing Liu 0022, Kai Liu 0023, Ruiyang Ren, Wayne Xin Zhao, Daxiang Dong, Hua Wu 0003, Haifeng Wang 0001. 5835-5847 [doi]
• DAGN: Discourse-Aware Graph Network for Logical ReasoningYinya Huang, Meng Fang, Yu Cao, Liwei Wang, Xiaodan Liang. 5848-5855 [doi]
• Designing a Minimal Retrieve-and-Read System for Open-Domain Question AnsweringSohee Yang, Minjoon Seo. 5856-5865 [doi]
• Unsupervised Multi-hop Question Answering by Question GenerationLiangming Pan, Wenhu Chen, Wenhan Xiong, Min-Yen Kan, William Yang Wang. 5866-5880 [doi]
• Sliding Selector Network with Dynamic Memory for Extractive Summarization of Long DocumentsPeng Cui 0006, Le Hu. 5881-5891 [doi]
• AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive SummarizationTiezheng Yu, Zihan Liu, Pascale Fung. 5892-5904 [doi]
• QMSum: A New Benchmark for Query-based Multi-domain Meeting SummarizationMing Zhong, Da Yin, Tao Yu 0009, Ahmad Zaidi, Mutethia Mutuma, Rahul Jha, Ahmed Hassan Awadallah, Asli Celikyilmaz, Yang Liu, Xipeng Qiu, Dragomir R. Radev. 5905-5921 [doi]
• MM-AVS: A Full-Scale Dataset for Multi-modal SummarizationXiyan Fu, Jun Wang 0023, Zhenglu Yang. 5922-5926 [doi]
• MediaSum: A Large-scale Media Interview Dataset for Dialogue SummarizationChenguang Zhu, Yang Liu, Jie Mei, Michael Zeng. 5927-5934 [doi]
• Improving Faithfulness in Abstractive Summarization with Contrast Candidate Generation and SelectionSihao Chen, Fan Zhang, Kazoo Sone, Dan Roth. 5935-5941 [doi]
• Inference Time Style Control for SummarizationShuyang Cao, Lu Wang 0008. 5942-5953 [doi]