Table of Contents

• Frontmatter [doi]
• PubHealthTab: A Public Health Table-based Dataset for Evidence-based Fact CheckingMubashara Akhtar, Oana Cocarascu, Elena Simperl. 1-16 [doi]
• Masked Measurement Prediction: Learning to Jointly Predict Quantities and Units from Textual ContextDaniel Spokoyny, Ivan Lee, Zhao Jin, Taylor Berg-Kirkpatrick. 17-29 [doi]
• PromptGen: Automatically Generate Prompts using Generative ModelsYue Zhang, Hongliang Fei, Dingcheng Li, Ping Li 0001. 30-37 [doi]
• Improving Conversational Recommendation Systems' Quality with Context-Aware Item Meta-InformationBowen Yang, Cong Han, Yu Li, Lei Zuo, Zhou Yu. 38-48 [doi]
• SEQZERO: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot ModelsJingfeng Yang, Haoming Jiang, Qingyu Yin, Danqing Zhang, Bing Yin, Diyi Yang. 49-60 [doi]
• MultiVerS: Improving scientific claim verification with weak supervision and full-document contextDavid Wadden, Kyle Lo, Lucy Lu Wang, Arman Cohan, Iz Beltagy, Hannaneh Hajishirzi. 61-76 [doi]
• An Item Response Theory Framework for PersuasionAnastassia Kornilova, Vladimir Eidelman, Daniel Douglass. 77-86 [doi]
• Self-Supervised Contrastive Learning with Adversarial Perturbations for Defending Word Substitution-based AttacksZhao Meng, Yihan Dong, Mrinmaya Sachan, Roger Wattenhofer. 87-101 [doi]
• Quiz Design Task: Helping Teachers Create Quizzes with Automated Question GenerationPhilippe Laban, Chien-Sheng Wu, Lidiya Murakhovs'ka, Wenhao Liu, Caiming Xiong. 102-111 [doi]
• In-BoXBART: Get Instructions into Biomedical Multi-Task LearningMihir Parmar, Swaroop Mishra, Mirali Purohit, Man Luo, Murad Mohammad, Chitta Baral. 112-128 [doi]
• How to Translate Your Samples and Choose Your Shots? Analyzing Translate-train & Few-shot Cross-lingual TransferIman Jundi, Gabriella Lapesa. 129-150 [doi]
• Multi-Hop Open-Domain Question Answering over Structured and Unstructured KnowledgeYue Feng, Zhen Han, Mingming Sun, Ping Li 0001. 151-156 [doi]
• FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing TasksBill Yuchen Lin, Chaoyang He 0001, Zihang Ze, Hulin Wang, Yufen Hua, Christophe Dupuy, Rahul Gupta, Mahdi Soltanolkotabi, Xiang Ren, Salman Avestimehr. 157-175 [doi]
• SemAttack: Natural Textual Attacks via Different Semantic SpacesBoxin Wang, Chejian Xu, Xiangyu Liu, Yu Cheng, Bo Li. 176-205 [doi]
• Lacuna Reconstruction: Self-Supervised Pre-Training for Low-Resource Historical Document TranscriptionNikolai Vogler, Jonathan Parkes Allen, Matthew Thomas Miller, Taylor Berg-Kirkpatrick. 206-216 [doi]
• FreeTransfer-X: Safe and Label-Free Cross-Lingual Transfer from Off-the-Shelf ModelsYinpeng Guo, Liangyou Li, Xin Jiang 0002, Qun Liu 0001. 217-228 [doi]
• Opportunities for Human-centered Evaluation of Machine Translation SystemsDaniel Liebling, Katherine Heller, Samantha Robertson, Wesley Hanwen Deng. 229-240 [doi]
• Aligning Generative Language Models with Human ValuesRuibo Liu, Ge Zhang, Xinyu Feng, Soroush Vosoughi. 241-252 [doi]
• PerKGQA: Question Answering over Personalized Knowledge GraphsRitam Dutt, Kasturi Bhattacharjee, Rashmi Gangadharaiah, Dan Roth, Carolyn Rosé. 253-268 [doi]
• Zero-shot Cross-lingual Conversational Semantic Role LabelingHan Wu, Haochen Tan, Kun Xu 0005, Shuqi Liu, Lianwei Wu, Linqi Song. 269-281 [doi]
• A Framework to Generate High-Quality Datapoints for Multiple Novel Intent DetectionAnkan Mullick, Sukannya Purkayastha, Pawan Goyal 0002, Niloy Ganguly. 282-292 [doi]
• Design Challenges for a Multi-Perspective Search EngineSihao Chen, Siyi Liu, Xander Uyttendaele, Yi Zhang, William Bruno, Dan Roth. 293-303 [doi]
• Exploring the Value of Multi-View Learning for Session-Aware Query RepresentationDiego Ortiz, Jose G. Moreno 0001, Gilles Hubert, Karen Pinel-Sauvagnat, Lynda Tamine. 304-315 [doi]
• Hierarchical Relation-Guided Type-Sentence Alignment for Long-Tail Relation Extraction with Distant SupervisionYang Li, Guodong Long, Tao Shen, Jing Jiang. 316-326 [doi]
• PCEE-BERT: Accelerating BERT Inference via Patient and Confident Early ExitingZhen Zhang, Wei Zhu, Jinfan Zhang, Peng Wang, Rize Jin, Tae-Sun Chung. 327-338 [doi]
• Learning to repair: Repairing model output errors after deployment using a dynamic memory of feedbackNiket Tandon, Aman Madaan, Peter Clark, Yiming Yang. 339-352 [doi]
• One Size Does Not Fit All: The Case for Personalised Word Complexity ModelsSian Gooding, Manuel Tragut. 353-365 [doi]
• TEAM: A multitask learning based Taxonomy Expansion approach for Attach and MergeBornali Phukon, Anasua Mitra, Ranbir Sanasam Singh, Priyankoo Sarmah. 366-378 [doi]
• Extracting Temporal Event Relation with Syntax-guided Graph TransformerShuaicheng Zhang, Qiang Ning, Lifu Huang. 379-390 [doi]
• From Cognitive to Computational Modeling: Text-based Risky Decision-Making Guided by Fuzzy Trace TheoryJaron Mar, Jiamou Liu. 391-409 [doi]
• Few-Shot Self-Rationalization with Natural Language PromptsAna Marasovic, Iz Beltagy, Doug Downey, Matthew E. Peters. 410-424 [doi]
• DOCmT5: Document-Level Pretraining of Multilingual Language ModelsChia-Hsuan Lee 0001, Aditya Siddhant, Viresh Ratnakar, Melvin Johnson. 425-437 [doi]
• Literature-Augmented Clinical Outcome PredictionAakanksha Naik, Sravanthi Parasa, Sergey Feldman, Lucy Lu Wang, Tom Hope. 438-453 [doi]
• Improving Few-Shot Relation Classification by Prototypical Representation Learning with Definition TextZhenzhen Li, Yuyang Zhang, Jian-Yun Nie, Dongsheng Li. 454-464 [doi]
• Entailment Tree Explanations via Iterative Retrieval-Generation ReasonerDanilo Neves Ribeiro, Shen Wang 0005, Xiaofei Ma, Rui Dong, Xiaokai Wei, Henghui Zhu, Xinchi Chen, Peng Xu, Zhiheng Huang, Andrew O. Arnold, Dan Roth. 465-475 [doi]
• Multimodal Intent Discovery from Livestream VideosAdyasha Maharana, Quan Hung Tran, Franck Dernoncourt, Seunghyun Yoon 0002, Trung Bui, Walter Chang, Mohit Bansal. 476-489 [doi]
• A Question-Answer Driven Approach to Reveal Affirmative Interpretations from Verbal NegationsMd Mosharaf Hossain, Luke Holman, Anusha Kakileti, Tiffany Kao, Nathan Raul Brito, Aaron Abraham Mathews, Eduardo Blanco 0002. 490-503 [doi]
• Harmless Transfer Learning for Item EmbeddingsChengYue Gong, Xiaocong Du, Dhruv Choudhary, Bhargav Bhushanam, Qiang Liu 0001, Arun Kejariwal. 504-516 [doi]
• Fine-grained Image Captioning with CLIP RewardJaemin Cho 0001, Seunghyun Yoon 0002, Ajinkya Kale, Franck Dernoncourt, Trung Bui, Mohit Bansal. 517-527 [doi]
• Improving the Faithfulness of Abstractive Summarization via Entity Coverage ControlHaopeng Zhang, Semih Yavuz, Wojciech Kryscinski, Kazuma Hashimoto, Yingbo Zhou. 528-535 [doi]
• Modeling Ideological Salience and Framing in Polarized Online Groups with Graph Neural Networks and Structured SparsityValentin Hofmann, Xiaowen Dong, Janet B. Pierrehumbert, Hinrich Schütze. 536-550 [doi]
• On Measuring Social Biases in Prompt-Based Multi-Task LearningAfra Feyza Akyürek, Sejin Paik, Muhammed Yusuf Kocyigit, Seda Akbiyik, Serife Leman Runyun, Derry Wijaya. 551-564 [doi]
• Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue SystemChang Tian, Wenpeng Yin 0002, Marie-Francine Moens. 565-577 [doi]
• Penn-Helsinki Parsed Corpus of Early Modern English: First Parsing Results and AnalysisSeth Kulick, Neville Ryant, Beatrice Santorini. 578-593 [doi]
• Instilling Type Knowledge in Language Models via Multi-Task QAShuyang Li, Mukund Sridhar, Chandana Satya Prakash, Jin Cao, Wael Hamza, Julian J. McAuley. 594-603 [doi]
• StATIK: Structure and Text for Inductive Knowledge Graph CompletionElan Markowitz, Keshav Balasubramanian, Mehrnoosh Mirtaheri, Murali Annavaram, Aram Galstyan, Greg Ver Steeg. 604-615 [doi]
• CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to FormalityMaria Nadejde, Anna Currey, Benjamin Hsu, Xing Niu, Marcello Federico, Georgiana Dinu. 616-632 [doi]
• CLEAR: Improving Vision-Language Navigation with Cross-Lingual, Environment-Agnostic RepresentationsJialu Li, Hao Tan, Mohit Bansal. 633-649 [doi]
• Language Models for Code-switch Detection of te reo Māori and English in a Low-resource SettingJesin James, Vithya Yogarajan, Isabella Shields, Catherine I. Watson 0001, Peter Keegan, Keoni Mahelona, Peter-Lucas Jones. 650-660 [doi]
• Opponent Modeling in Negotiation Dialogues by Related Data AdaptationKushal Chawla, Gale M. Lucas, Jonathan May, Jonathan Gratch. 661-674 [doi]
• LMTurk: Few-Shot Learners as Crowdsourcing Workers in a Language-Model-as-a-Service FrameworkMengjie Zhao, Fei Mi, Yasheng Wang, Minglei Li, Xin Jiang, Qun Liu, Hinrich Schütze. 675-692 [doi]
• Entity Cloze By Date: What LMs Know About Unseen EntitiesYasumasa Onoe, Michael J. Q. Zhang, Eunsol Choi, Greg Durrett. 693-702 [doi]
• Data Augmentation for Low-Resource Dialogue SummarizationYongtai Liu, Joshua Maynez, Gonçalo Simões, Shashi Narayan. 703-710 [doi]
• A Versatile Adaptive Curriculum Learning Framework for Task-oriented Dialogue Policy LearningYang Zhao, Hua Qin, Zhenyu Wang, Changxi Zhu, Shihan Wang. 711-723 [doi]
• LongT5: Efficient Text-To-Text Transformer for Long SequencesMandy Guo, Joshua Ainslie, David C. Uthus, Santiago Ontañón, Jianmo Ni, Yun-Hsuan Sung, Yinfei Yang. 724-736 [doi]
• Challenging America: Modeling language in longer time scalesJakub Pokrywka, Filip Gralinski, Krzysztof Jassem, Karol Kaczmarek, Krzysztof Jurkiewicz, Piotr Wierzchon. 737-749 [doi]
• LM-CORE: Language Models with Contextually Relevant External KnowledgeJivat Neet Kaur, Sumit Bhatia, Milan Aggarwal, Rachit Bansal, Balaji Krishnamurthy. 750-769 [doi]
• A Generative Language Model for Few-shot Aspect-Based Sentiment AnalysisEhsan Hosseini-Asl, Wenhao Liu, Caiming Xiong. 770-787 [doi]
• Permutation Invariant Strategy Using Transformer Encoders for Table UnderstandingSarthak Dash, Sugato Bagchi, Nandana Mihindukulasooriya, Alfio Gliozzo. 788-800 [doi]
• MultiNERD: A Multilingual, Multi-Genre and Fine-Grained Dataset for Named Entity Recognition (and Disambiguation)Simone Tedeschi, Roberto Navigli. 801-812 [doi]
• Learning to Embed Multi-Modal Contexts for Situated Conversational AgentsHaeju Lee, Oh Joon Kwon, Yunseon Choi, Minho Park, Ran Han, Yoonhyung Kim, Jinhyeon Kim, Youngjune Lee, Haebin Shin, Kangwook Lee 0004, Kee-Eung Kim. 813-830 [doi]
• Measuring and Improving Compositional Generalization in Text-to-SQL via Component AlignmentYujian Gan, Xinyun Chen, Qiuping Huang, Matthew Purver. 831-843 [doi]
• Empathetic Persuasion: Reinforcing Empathy and Persuasiveness in Dialogue SystemsAzlaan Mustafa Samad, Kshitij Mishra, Mauajama Firdaus, Asif Ekbal. 844-856 [doi]
• Attention Fusion: a light yet efficient late fusion mechanism for task adaptation in NLUJin Cao, Chandana Satya Prakash, Wael Hamza. 857-866 [doi]
• The Limits of Word Level Differential PrivacyJustus Mattern, Benjamin Weggenmann, Florian Kerschbaum. 867-881 [doi]
• Efficient Learning of Multiple NLP Tasks via Collective Weight Factorization on BERTChristos Papadopoulos, Yannis Panagakis, Manolis Koubarakis, Mihalis Nicolaou. 882-890 [doi]
• Learning Rich Representation of Keyphrases from TextMayank Kulkarni, Debanjan Mahata, Ravneet Arora, Rajarshi Bhowmik. 891-906 [doi]
• Improving Contextual Representation with Gloss Regularized Pre-trainingYu Lin, Zhecheng An, Peihao Wu, Zejun Ma. 907-920 [doi]
• An Information-Theoretic Approach and Dataset for Probing Gender Stereotypes in Multilingual Masked Language ModelsVictor Steinborn, Philipp Dufter, Haris Jabbar, Hinrich Schütze. 921-932 [doi]
• Self-Training with Differentiable TeacherSimiao Zuo, Yue Yu, Chen Liang, Haoming Jiang, Siawpeng Er, Chao Zhang, Tuo Zhao, Hongyuan Zha. 933-949 [doi]
• SHARP: Search-Based Adversarial Attack for Structured PredictionLiwen Zhang, Zixia Jia, Wenjuan Han, Zilong Zheng, Kewei Tu. 950-961 [doi]
• MM-Claims: A Dataset for Multimodal Claim Detection in Social MediaGullal Singh Cheema, Sherzod Hakimov, Abdul Sittar, Eric Müller-Budack, Christian Otto, Ralph Ewerth. 962-979 [doi]
• QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual ReasoningZechen Li, Anders Søgaard. 980-996 [doi]
• MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem SolvingZhenwen Liang, Jipeng Zhang, Lei Wang, Wei Qin, Yunshi Lan, Jie Shao, Xiangliang Zhang 0001. 997-1009 [doi]
• Restoring Hebrew Diacritics Without a DictionaryElazar Gershuni, Yuval Pinter. 1010-1018 [doi]
• Masked Summarization to Generate Factually Inconsistent Summaries for Improved Factual Consistency CheckingHwanhee Lee, Kang Min Yoo, Joonsuk Park, Hwaran Lee, Kyomin Jung. 1019-1030 [doi]
• Probing the Role of Positional Information in Vision-Language ModelsPhilipp J. Rösch, Jindrich Libovický. 1031-1041 [doi]
• "Diversity and Uncertainty in Moderation" are the Key to Data Selection for Multilingual Few-shot TransferShanu Kumar, Sandipan Dandapat, Monojit Choudhury. 1042-1055 [doi]
• A Self-supervised Joint Training Framework for Document RerankingXiaozhi Zhu, Tianyong Hao, Sijie Cheng, Fu Lee Wang, Hai Liu 0006. 1056-1065 [doi]
• CODE-MVP: Learning to Represent Source Code from Multiple Views with Contrastive Pre-TrainingXin Wang, Yasheng Wang, Yao Wan, Jiawei Wang, Pingyi Zhou, Li Li, Hao Wu, Jin Liu. 1066-1077 [doi]
• RGL: A Simple yet Effective Relation Graph Augmented Prompt-based Tuning Approach for Few-Shot LearningYaqing Wang, Xin Tian, Haoyi Xiong, Yueyang Li, Zeyu Chen, Sheng Guo, Dejing Dou. 1078-1084 [doi]
• Seeing the wood for the trees: a contrastive regularization method for the low-resource Knowledge Base Question AnsweringJunping Liu, Shijie Mei, Xinrong Hu, Xun Yao, Jack Yang, Yi Guo. 1085-1094 [doi]
• Phrase-level Textual Adversarial Attack with Label PreservationYibin Lei, Yu Cao, Dianqi Li, Tianyi Zhou, Meng Fang, Mykola Pechenizkiy. 1095-1112 [doi]
• Prompt Augmented Generative Replay via Supervised Contrastive Learning for Lifelong Intent DetectionVaibhav Varshney, Mayur Patidar, Rajat Kumar, Lovekesh Vig, Gautam Shroff. 1113-1127 [doi]
• OTExtSum: Extractive Text Summarisation with Optimal TransportPeggy Tang, Kun Hu, Rui Yan, Lei Zhang, Junbin Gao, Zhiyong Wang 0001. 1128-1141 [doi]
• Speeding Up EntmaxMaxat Tezekbayev, Vassilina Nikoulina, Matthias Gallé, Zhenisbek Assylbekov. 1142-1158 [doi]
• Improving Code-Switching Dependency Parsing with Semi-Supervised Auxiliary TasksSaziye Betül Özates, Arzucan Özgür, Tunga Gungor, Özlem Çetinoglu. 1159-1171 [doi]
• Dangling-Aware Entity Alignment with Mixed High-Order ProximitiesJuncheng Liu, Zequn Sun, Bryan Hooi, Yiwei Wang, Dayiheng Liu, Baosong Yang, Xiaokui Xiao, Muhao Chen. 1172-1184 [doi]
• DecBERT: Enhancing the Language Understanding of BERT with Causal Attention MasksZiyang Luo, Yadong Xi, Jing Ma, Zhiwei Yang, Xiaoxi Mao, Changjie Fan, Rongsheng Zhang. 1185-1197 [doi]
• Towards Computationally Feasible Deep Active LearningAkim Tsvigun, Artem Shelmanov, Gleb Kuzmin, Leonid Sanochkin, Daniil Larionov, Gleb Gusev, Manvel Avetisian, Leonid Zhukov. 1198-1218 [doi]
• End-to-end Spoken Conversational Question Answering: Task, Dataset and ModelChenyu You, Nuo Chen, Fenglin Liu, Shen Ge, Xian Wu, Yuexian Zou. 1219-1232 [doi]
• Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative TrainingYifan Gao 0001, Qingyu Yin, Zheng Li, Rui Meng, Tong Zhao, Bing Yin, Irwin King, Michael R. Lyu. 1233-1246 [doi]
• FAtNet: Cost-Effective Approach Towards Mitigating the Linguistic Bias in Speaker Verification SystemsDivya Sharma, Arun Balaji Buduru. 1247-1258 [doi]
• A Survey on Stance Detection for Mis- and Disinformation IdentificationMomchil Hardalov, Arnav Arora, Preslav Nakov, Isabelle Augenstein. 1259-1277 [doi]
• Syntax Controlled Knowledge Graph-to-Text Generation with Order and Semantic ConsistencyJin Liu 0018, Chongfeng Fan, Fengyu Zhou, Huijuan Xu 0001. 1278-1291 [doi]
• To Answer or Not To Answer? Improving Machine Reading Comprehension Model with Span-based Contrastive LearningYunjie Ji, Liangyu Chen, Chenxiao Dou, Baochang Ma, Xiangang Li. 1292-1300 [doi]
• Target-Guided Dialogue Response Generation Using Commonsense and Data AugmentationPrakhar Gupta, Harsh Jhamtani, Jeffrey P. Bigham. 1301-1317 [doi]
• BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in BanglaAbhik Bhattacharjee, Tahmid Hasan, Wasi Ahmad, Kazi Samin Mubasshir, Md Saiful Islam, Anindya Iqbal, M. Sohel Rahman, Rifat Shahriyar. 1318-1327 [doi]
• ALLSH: Active Learning Guided by Local Sensitivity and HardnessShujian Zhang, ChengYue Gong, Xingchao Liu, Pengcheng He, Weizhu Chen, Mingyuan Zhou. 1328-1342 [doi]
• Low-resource Entity Set Expansion: A Comprehensive Study on User-generated TextYutong Shao, Nikita Bhutani, Sajjadur Rahman, Estevam Hruschka. 1343-1353 [doi]
• POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance DetectionYujian Liu, Xinliang Frederick Zhang, David Wegsman, Nicholas Beauchamp, Lu Wang 0008. 1354-1374 [doi]
• Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attentionYifan Chen, Devamanyu Hazarika, Mahdi Namazifar, Yang Liu 0004, Di Jin, Dilek Hakkani-Tur. 1375-1388 [doi]
• RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge DistillationMd. Akmal Haidar, Nithin Anchuri, Mehdi Rezagholizadeh, Abbas Ghaddar, Philippe Langlais, Pascal Poupart. 1389-1400 [doi]
• Unbiased Math Word Problems Benchmark for Mitigating Solving BiasZhicheng Yang, Jinghui Qin, Jiaqi Chen, Xiaodan Liang. 1401-1408 [doi]
• Learn To Remember: Transformer with Recurrent Memory for Document-Level Machine TranslationYukun Feng, Feng Li, Ziang Song, Boyuan Zheng, Philipp Koehn. 1409-1420 [doi]
• Improving Few-Shot Image Classification Using Machine- and User-Generated Natural Language DescriptionsKosuke Nishida, Kyosuke Nishida, Shuichi Nishioka. 1421-1430 [doi]
• All Information is Valuable: Question Matching over Full Information Transmission NetworkLe Qi, Yu Zhang 0030, Qingyu Yin, Guidong Zheng, Wen Junjie, Jinlong Li, Ting Liu 0001. 1431-1440 [doi]
• Pathway2Text: Dataset and Method for Biomedical Pathway Description GenerationJunwei Yang, Zequn Liu, Ming Zhang, Sheng Wang. 1441-1454 [doi]
• Exploring Neural Models for Query-Focused SummarizationJesse Vig, Alexander R. Fabbri, Wojciech Kryscinski, Chien-Sheng Wu, Wenhao Liu. 1455-1468 [doi]
• BitextEdit: Automatic Bitext Editing for Improved Low-Resource Machine TranslationEleftheria Briakou, Sida I. Wang, Luke Zettlemoyer, Marjan Ghazvininejad. 1469-1485 [doi]
• MixQG: Neural Question Generation with Mixed Answer TypesLidiya Murakhovs'ka, Chien-Sheng Wu, Philippe Laban, Tong Niu, Wenhao Liu, Caiming Xiong. 1486-1497 [doi]
• Temporal Attention for Language ModelsGuy D. Rosin, Kira Radinsky. 1498-1508 [doi]
• Efficient Few-Shot Fine-Tuning for Opinion SummarizationArthur Brazinskas, Ramesh Nallapati, Mohit Bansal, Markus Dreyer. 1509-1523 [doi]
• Domain-matched Pre-training Tasks for Dense RetrievalBarlas Oguz, Kushal Lakhotia, Anchit Gupta, Patrick Lewis, Vladimir Karpukhin, Aleksandra Piktus, Xilun Chen, Sebastian Riedel 0001, Scott Yih, Sonal Gupta, Yashar Mehdad. 1524-1534 [doi]
• UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question AnsweringBarlas Oguz, Xilun Chen, Vladimir Karpukhin, Stan Peshterliev, Dmytro Okhonko, Michael Sejr Schlichtkrull, Sonal Gupta, Yashar Mehdad, Scott Yih. 1535-1546 [doi]
• White-box Testing of NLP models with Mask Neuron CoverageArshdeep Sekhon, Yangfeng Ji, Matthew B. Dwyer, Yanjun Qi. 1547-1558 [doi]
• Hierarchical Transformers Are More Efficient Language ModelsPiotr Nawrot, Szymon Tworkowski, Michal Tyrolski, Lukasz Kaiser, Yuhuai Wu, Christian Szegedy, Henryk Michalewski. 1559-1571 [doi]
• DISARM: Detecting the Victims Targeted by Harmful MemesShivam Sharma, Md. Shad Akhtar, Preslav Nakov, Tanmoy Chakraborty 0002. 1572-1588 [doi]
• KD-VLP: Improving End-to-End Vision-and-Language Pretraining with Object Knowledge DistillationYongfei Liu, Chenfei Wu, Shao-Yen Tseng, Vasudev Lal, Xuming He 0001, Nan Duan. 1589-1600 [doi]
• Dependency Position Encoding for Relation ExtractionQiushi Guo, Xin Wang, Dehong Gao. 1601-1606 [doi]
• Good Visual Guidance Make A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation ExtractionXiang Chen, Ningyu Zhang, Lei Li, Yunzhi Yao, Shumin Deng, Chuanqi Tan, Fei Huang, Luo Si, Huajun Chen. 1607-1618 [doi]
• The Role of Context in Detecting Previously Fact-Checked ClaimsShaden Shaar, Firoj Alam, Giovanni Da San Martino, Preslav Nakov. 1619-1631 [doi]
• Pruning Adatperfusion with Lottery Ticket HypothesisJiarun Wu, Qingliang Chen, Zeguan Xiao, Yuliang Gu, Mengsi Sun. 1632-1646 [doi]
• EVI: Multilingual Spoken Dialogue Tasks and Dataset for Knowledge-Based Enrolment, Verification, and IdentificationGeorgios Spithourakis, Ivan Vulic, Michal Lis, Iñigo Casanueva, Pawel Budzianowski. 1647-1659 [doi]
• Post-Training Dialogue Summarization using Pseudo-ParaphrasingQi Jia 0003, Yizhu Liu, Haifeng Tang, Kenny Q. Zhu. 1660-1669 [doi]
• A Dual-Channel Framework for Sarcasm Recognition by Detecting Sentiment ConflictYiyi Liu, Yequan Wang, Aixin Sun, Xuying Meng, Jing Li, Jiafeng Guo. 1670-1680 [doi]
• Zero-shot Entity Linking with Less DataG. P. Shrivatsa Bhargav, Dinesh Khandelwal, Saswati Dana, Dinesh Garg, Pavan Kapanipathi, Salim Roukos, Alexander G. Gray, L. Venkata Subramaniam. 1681-1697 [doi]
• GraphCache: Message Passing as Caching for Sentence-Level Relation ExtractionYiwei Wang, Muhao Chen, Wenxuan Zhou, Yujun Cai, Yuxuan Liang, Bryan Hooi. 1698-1708 [doi]
• Revisiting Generative Commonsense Reasoning: A Pre-Ordering ApproachChao Zhao, Faeze Brahman, Tenghao Huang, Snigdha Chaturvedi. 1709-1718 [doi]
• Identifying and Mitigating Spurious Correlations for Improving Robustness in NLP ModelsTianlu Wang, Rohit Sridhar, Diyi Yang, Xuezhi Wang 0002. 1719-1729 [doi]
• $Great Truths are Always Simple: $ A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained ModelsJinhao Jiang, Kun Zhou, Ji-Rong Wen, Xin Zhao. 1730-1741 [doi]
• Analyzing the Intensity of Complaints on Social MediaMing Fang, Shi Zong, Jing Li, Xinyu Dai, Shujian Huang, Jiajun Chen. 1742-1754 [doi]
• Detecting Narrative Elements in Informational TextEffi Levi, Guy Mor, Tamir Sheafer, Shaul R. Shenhav. 1755-1765 [doi]
• When do Contrastive Word Alignments Improve Many-to-many Neural Machine Translation?Zhuoyuan Mao, Chenhui Chu, Raj Dabre, Haiyue Song, Zhen Wan, Sadao Kurohashi. 1766-1775 [doi]
• Minimally-Supervised Relation Induction from Pre-trained Language ModelLu Sun, Yongliang Shen 0001, Weiming Lu 0001. 1776-1786 [doi]
• Crake: Causal-Enhanced Table-Filler for Question Answering over Large Scale Knowledge BaseMinhao Zhang, Ruoyu Zhang, Yanzeng Li, Lei Zou 0001. 1787-1798 [doi]
• Exploring the Universal Vulnerability of Prompt-based Learning ParadigmLei Xu 0040, Yangyi Chen, Ganqu Cui, Hongcheng Gao, Zhiyuan Liu 0001. 1799-1810 [doi]
• Exploiting Numerical-Contextual Knowledge to Improve Numerical Reasoning in Question AnsweringJeonghwan Kim, Junmo Kang, Kyung Min Kim, Giwon Hong, Sung-Hyon Myaeng. 1811-1821 [doi]
• Learn from Relation Information: Towards Prototype Representation Rectification for Few-Shot Relation ExtractionYang Liu, Jinpeng Hu, Xiang Wan, Tsung-Hui Chang. 1822-1831 [doi]
• HUE: Pretrained Model and Dataset for Understanding Hanja Documents of Ancient KoreaHaneul Yoo, Jiho Jin, Juhee Son, JinYeong Bak, KyungHyun Cho, Alice Oh. 1832-1844 [doi]
• SeaD: End-to-end Text-to-SQL Generation with Schema-aware DenoisingKuan Xu, Yongbo Wang, Yongliang Wang, Zihao Wang, Zujie Wen, Yang Dong. 1845-1853 [doi]
• Cross-Lingual Cross-Modal Consolidation for Effective Multilingual Video Corpus Moment RetrievalJiaheng Liu, Tan Yu, Hanyu Peng, Mingming Sun, Ping Li. 1854-1862 [doi]
• Delving Deep into Regularity: A Simple but Effective Method for Chinese Named Entity RecognitionYingjie Gu, Xiaoye Qu, Zhefeng Wang, Yi Zheng, Baoxing Huai, Nicholas Jing Yuan. 1863-1873 [doi]
• CRUSH: Contextually Regularized and User anchored Self-supervised Hate speech DetectionSouvic Chakraborty, Parag Dutta, Sumegh Roychowdhury, Animesh Mukherjee 0001. 1874-1886 [doi]
• METGEN: A Module-Based Entailment Tree Generation Framework for Answer ExplanationRuixin Hong, Hongming Zhang, Xintong Yu, Changshui Zhang. 1887-1905 [doi]
• A Timestep aware Sentence Embedding and Acme Coverage for Brief but Informative Title GenerationQuanbin Wang, Xiexiong Lin, Feng Wang. 1906-1918 [doi]
• Make The Most of Prior Data: A Solution for Interactive Text Summarization with Preference FeedbackDuy-Hung Nguyen, Nguyen-Viet-Dung Nghiem, Bao-Sinh Nguyen, Dung Tien Le, Shahab Sabahi, Minh-Tien Nguyen, Hung Le. 1919-1930 [doi]
• XLTime: A Cross-Lingual Knowledge Transfer Framework for Temporal Expression ExtractionYuwei Cao, William Groves, Tanay Kumar Saha, Joel R. Tetreault, Alejandro Jaimes, Hao Peng, Philip S. Yu. 1931-1942 [doi]
• BehancePR: A Punctuation Restoration Dataset for Livestreaming Video TranscriptViet Dac Lai, Amir Pouran Ben Veyseh, Franck Dernoncourt, Thien Nguyen. 1943-1951 [doi]
• Event Detection for Suicide UnderstandingLuis Guzman-Nateras, Viet Dac Lai, Amir Pouran Ben Veyseh, Franck Dernoncourt, Thien Nguyen. 1952-1961 [doi]
• Great Power, Great Responsibility: Recommendations for Reducing Energy for Training Language ModelsJoseph McDonald, Baolin Li, Nathan C. Frey, Devesh Tiwari, Vijay Gadepally, Siddharth Samsi. 1962-1970 [doi]
• What kinds of errors do reference resolution models make and what can we learn from them?Jorge Sánchez, Mauricio Mazuecos, Hernán Maina, Luciana Benotti. 1971-1986 [doi]
• Uncertainty-Aware Cross-Lingual Transfer with Pseudo Partial LabelsShuo Lei, Xuchao Zhang, Jianfeng He, Fanglan Chen, Chang-Tien Lu. 1987-1997 [doi]
• NLU++: A Multi-Label, Slot-Rich, Generalisable Dataset for Natural Language Understanding in Task-Oriented DialogueIñigo Casanueva, Ivan Vulic, Georgios Spithourakis, Pawel Budzianowski. 1998-2013 [doi]
• Challenges in Generalization in Open Domain Question AnsweringLinqing Liu, Patrick Lewis, Sebastian Riedel 0001, Pontus Stenetorp. 2014-2029 [doi]
• Beyond Distributional Hypothesis: Let Language Models Learn Meaning-Text CorrespondenceM. j Jang, Frank Mtumbuka, Thomas Lukasiewicz. 2030-2042 [doi]
• Por Qué Não Utiliser Alla Språk? Mixed Training with Gradient Optimization in Few-Shot Cross-Lingual TransferHaoran Xu, Kenton Murray. 2043-2059 [doi]
• Learning to Execute Actions or Ask Clarification QuestionsZhengxiang Shi, Yue Feng, Aldo Lipani. 2060-2070 [doi]
• Capturing Conversational Interaction for Question Answering via Global History ReasoningJin Qian, Bowei Zou, Mengxing Dong, Xiao Li, AiTi Aw, Yu Hong. 2071-2078 [doi]
• Learning Structural Information for Syntax-Controlled Paraphrase GenerationErguang Yang, Chenglin Bai, Deyi Xiong, Yujie Zhang, Yao Meng, Jinan Xu, Yufeng Chen 0005. 2079-2090 [doi]
• Controllable Sentence Simplification via Operation ClassificationLiam Cripwell, Joël Legrand, Claire Gardent. 2091-2103 [doi]
• Balancing Multi-Domain Corpora Learning for Open-Domain Response GenerationYujie Xing, Jinglun Cai, Nils Barlaug, Peng Liu 0025, Jon Atle Gulla. 2104-2120 [doi]
• Semantic-Preserving Abstractive Text Summarization with Siamese Generative Adversarial NetXin Sheng, Linli Xu, Yinlong Xu, Deqiang Jiang, Bo Ren. 2121-2132 [doi]
• Towards Job-Transition-Tag Graph for a Better Job Title Representation LearningJun Zhu, Céline Hudelot. 2133-2140 [doi]
• CL-ReLKT: Cross-lingual Language Knowledge Transfer for Multilingual Retrieval Question AnsweringPeerat Limkonchotiwat, Wuttikorn Ponwitayarat, Can Udomcharoenchaikit, Ekapol Chuangsuwanich, Sarana Nutanong. 2141-2155 [doi]
• BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented DialogHaipeng Sun, Junwei Bao 0001, Youzheng Wu, Xiaodong He 0002. 2156-2170 [doi]
• Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity MatchingKunbo Ding, Weijie Liu 0002, Yuejian Fang, Zhe Zhao, Qi Ju, Xuefeng Yang, Rong Tian, Zhu Tao, Haoyan Liu, Han Guo, Xingyu Bai, Weiquan Mao, Yudong Li, Weigang Guo, Taiqiang Wu, Ningyuan Sun. 2171-2181 [doi]
• On the Limitations of Dataset Balancing: The Lost Battle Against Spurious CorrelationsRoy Schwartz 0001, Gabriel Stanovsky. 2182-2194 [doi]
• Specializing Pre-trained Language Models for Better Relational Reasoning via Network PruningSiyu Ren, Kenny Q. Zhu. 2195-2207 [doi]
• D2GCLF: Document-to-Graph Classifier for Legal Document ClassificationQiqi Wang, Kaiqi Zhao, Robert Amor, Benjamin Liu, Ruofan Wang. 2208-2221 [doi]
• A Label-Aware Autoregressive Framework for Cross-Domain NERJinpeng Hu, He Zhao, Dan Guo, Xiang Wan, Tsung-Hui Chang. 2222-2232 [doi]
• A Dog Is Passing Over The Jet? A Text-Generation Dataset for Korean Commonsense Reasoning and EvaluationJaehyung Seo, Seounghoon Lee, Chanjun Park, Yoonna Jang, Hyeonseok Moon, Sugyeong Eo, Seonmin Koo, HeuiSeok Lim. 2233-2249 [doi]
• Improve Discourse Dependency Parsing with Contextualized RepresentationsYifei Zhou, Yansong Feng. 2250-2261 [doi]
• LiST: Lite Prompted Self-training Makes Parameter-efficient Few-shot LearnersYaqing Wang, Subhabrata Mukherjee, Xiaodong Liu 0003, Jing Gao, Ahmed Hassan Awadallah, Jianfeng Gao. 2262-2281 [doi]
• CLMLF: A Contrastive Learning and Multi-Layer Fusion Method for Multimodal Sentiment DetectionZhen Li, Bing Xu, Conghui Zhu, Tiejun Zhao. 2282-2294 [doi]
• Weakly Supervised Text Classification using Supervision Signals from a Language ModelZiqian Zeng, Weimin Ni, Tianqing Fang, Xiang Li, Xinran Zhao, Yangqiu Song. 2295-2305 [doi]
• Analytical Reasoning of TextWanjun Zhong, Siyuan Wang, Duyu Tang, Zenan Xu, Daya Guo, Yining Chen, Jiahai Wang, Jian Yin 0001, Ming Zhou 0001, Nan Duan. 2306-2319 [doi]
• Denoising Neural Network for News Recommendation with Positive and Negative Implicit FeedbackYunfan Hu, Zhaopeng Qiu, Xian Wu. 2320-2329 [doi]
• Continual Machine Reading Comprehension via Uncertainty-aware Fixed Memory and Adversarial Domain AdaptationZhijing Wu 0002, Hua Xu, Jingliang Fang, Kai Gao. 2330-2339 [doi]
• Jointly Learning Guidance Induction and Faithful Summary Generation via Conditional Variational AutoencodersWang Xu, Tiejun Zhao. 2340-2350 [doi]
• Context-Aware Language Modeling for Goal-Oriented Dialogue SystemsCharlie Snell, Sherry Yang, Justin Fu, Yi Su, Sergey Levine. 2351-2366 [doi]
• Am I Me or You? State-of-the-Art Dialogue Models Cannot Maintain an IdentityKurt Shuster 0001, Jack Urbanek, Arthur Szlam, Jason Weston. 2367-2387 [doi]
• Unsupervised Domain Adaptation for Question Generation with DomainData Selection and Self-trainingPeide Zhu, Claudia Hauff. 2388-2401 [doi]
• CCQA: A New Web-Scale Question Answering Dataset for Model Pre-TrainingPatrick Huber, Armen Aghajanyan, Barlas Oguz, Dmytro Okhonko, Scott Yih, Sonal Gupta, Xilun Chen. 2402-2420 [doi]
• The Case for a Single Model that can Both Generate Continuations and Fill-in-the-BlankDaphne Ippolito, Liam Dugan, Emily Reif, Ann Yuan, Andy Coenen, Chris Callison-Burch. 2421-2432 [doi]
• Learning Discriminative Representations for Open Relation Extraction with Instance Ranking and Label CalibrationShusen Wang, Bin Duan, Yanan Wu, Yajing Xu. 2433-2438 [doi]
• Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source LearningOscar Sainz, Itziar Gonzalez-Dios, Oier Lopez de Lacalle, Bonan Min, Eneko Agirre. 2439-2455 [doi]
• RCL: Relation Contrastive Learning for Zero-Shot Relation ExtractionShusen Wang, Bosen Zhang, Yajing Xu, Yanan Wu, Bo Xiao. 2456-2468 [doi]
• Latent Group Dropout for Multilingual and Multidomain Machine TranslationMinh Quang Pham, François Yvon, Josep Maria Crego. 2469-2481 [doi]
• ATP: AMRize Then Parse! Enhancing AMR Parsing with PseudoAMRsLiang Chen, Peiyi Wang, Runxin Xu, Tianyu Liu 0001, Zhifang Sui, Baobao Chang. 2482-2496 [doi]
• TaCL: Improving BERT Pre-training with Token-aware Contrastive LearningYixuan Su, Fangyu Liu 0001, Zaiqiao Meng, Tian Lan, Lei Shu, Ehsan Shareghi, Nigel Collier. 2497-2507 [doi]
• MTG: A Benchmark Suite for Multilingual Text GenerationYiran Chen 0013, Zhenqiao Song, Xianze Wu, Danqing Wang, Jingjing Xu, Jiaze Chen, Hao Zhou, Lei Li. 2508-2527 [doi]
• Weakly Supervised Text-to-SQL Parsing through Question DecompositionTomer Wolfson, Daniel Deutch, Jonathan Berant. 2528-2542 [doi]
• Detect Rumors in Microblog Posts for Low-Resource Domains via Adversarial Contrastive LearningHongzhan Lin, Jing Ma, Liangliang Chen, Zhiwei Yang, Mingfei Cheng, Guang Chen. 2543-2556 [doi]
• DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue GenerationMd. Rashad Al Hasan Rony, Ricardo Usbeck, Jens Lehmann 0001. 2557-2571 [doi]
• Zero-Shot Event Detection Based on Ordered Contrastive Learning and Prompt-Based PredictionSenhui Zhang, Tao Ji, Wendi Ji, Xiaoling Wang. 2572-2580 [doi]
• KETOD: Knowledge-Enriched Task-Oriented DialogueZhiYu Chen, Bing Liu, Seungwhan Moon, Chinnadhurai Sankar, Paul A. Crook, William Yang Wang. 2581-2593 [doi]
• TANet: Thread-Aware Pretraining for Abstractive Conversational SummarizationZe Yang, Christian Wang, Zhoujin Tian, Wei Wu 0014, Zhoujun Li 0001. 2594-2607 [doi]
• AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP TasksChin-Lun Fu, Zih-Ching Chen, Yun-Ru Lee, Hung-yi Lee. 2608-2621 [doi]
• Bridging the Gap between Training and Inference: Multi-Candidate Optimization for Diverse Neural Machine TranslationHuan Lin, Baosong Yang, Liang Yao, Dayiheng Liu, Haibo Zhang, Jun Xie, Min Zhang, Jinsong Su. 2622-2632 [doi]
• Learning from Bootstrapping and Stepwise Reinforcement Reward: A Semi-Supervised Framework for Text Style TransferZhengyuan Liu, Nancy F. Chen. 2633-2648 [doi]
• EA²E: Improving Consistency with Event Awareness for Document-Level Argument ExtractionQi Zeng, Qiusi Zhan, Heng Ji. 2649-2655 [doi]
• Label Refinement via Contrastive Learning for Distantly-Supervised Named Entity RecognitionHuaiyuan Ying, Shengxuan Luo, Tiantian Dang, Sheng Yu 0002. 2656-2666 [doi]
• Negative Sample is Negative in Its Own Way: Tailoring Negative Sentences for Image-Text RetrievalZhihao Fan, Zhongyu Wei, Zejun Li, Siyuan Wang, Xuanjing Huang, Jianqing Fan. 2667-2678 [doi]
• Explore More Guidance: A Task-aware Instruction Network for Sign Language Translation Enhanced with Data AugmentationYong Cao, Wei Li, Xianzhi Li, Min Chen, Guangyong Chen, Long Hu, Zhengdao Li, Kai Hwang 0001. 2679-2690 [doi]
• RoViST: Learning Robust Metrics for Visual StorytellingEileen Wang, Soyeon Caren Han, Josiah Poon. 2691-2702 [doi]
• Query2Particles: Knowledge Graph Reasoning with Particle EmbeddingsJiaxin Bai, Zihao Wang, Hongming Zhang, Yangqiu Song. 2703-2714 [doi]
• ID10M: Idiom Identification in 10 LanguagesSimone Tedeschi, Federico Martelli, Roberto Navigli. 2715-2726 [doi]
• Cross-Domain Classification of Moral ValuesEnrico Liscio, Alin Dondera, Andrei Geadau, Catholijn M. Jonker, Pradeep K. Murukannaiah. 2727-2745 [doi]