Table of Contents

• Frontmatter [doi]
• BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelsElad Ben Zaken, Yoav Goldberg, Shauli Ravfogel. 1-9 [doi]
• Are Shortest Rationales the Best Explanations for Human Understanding?Hua Shen, Tongshuang Wu, Wenbo Guo 0002, Ting-Hao Kenneth Huang. 10-19 [doi]
• Analyzing Wrap-Up Effects through an Information-Theoretic LensClara Meister, Tiago Pimentel, Thomas Hikaru Clark, Ryan Cotterell, Roger Levy. 20-28 [doi]
• Have my arguments been replied to? Argument Pair Extraction as Machine Reading ComprehensionJianzhu Bao, Jingyi Sun, Qinglin Zhu, Ruifeng Xu. 29-35 [doi]
• High probability or low information? The probability-quality paradox in language generationClara Meister, Gian Wiher, Tiago Pimentel, Ryan Cotterell. 36-45 [doi]
• Disentangled Knowledge Transfer for OOD Intent Discovery with Unified Contrastive LearningYutao Mou, Keqing He, Yanan Wu, Zhiyuan Zeng, Hong Xu, Huixing Jiang, Wei Wu, Weiran Xu. 46-53 [doi]
• Voxel-informed Language GroundingRodolfo Corona, Shizhan Zhu, Dan Klein, Trevor Darrell. 54-60 [doi]
• P-Tuning: Prompt Tuning Can Be Comparable to Fine-tuning Across Scales and TasksXiao Liu, Kaixuan Ji, Yicheng Fu, Weng Tam, Zhengxiao Du, Zhilin Yang, Jie Tang 0001. 61-68 [doi]
• On Efficiently Acquiring Annotations for Multilingual ModelsJoel Ruben Antony Moniz, Barun Patra, Matthew R. Gormley. 69-85 [doi]
• Automatic Detection of Entity-Manipulated Text using Factual KnowledgeGanesh Jawahar, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan. 86-93 [doi]
• Does BERT Know that the IS-A Relation Is Transitive?Ruixi Lin, Hwee Tou Ng. 94-99 [doi]
• Buy Tesla, Sell Ford: Assessing Implicit Stock Market Preference in Pre-trained Language ModelsChengyu Chuang, Yi Yang. 100-105 [doi]
• Pixie: Preference in Implicit and Explicit ComparisonsAmanul Haque, Vaibhav Garg, Hui Guo, Munindar P. Singh. 106-112 [doi]
• Counterfactual Explanations for Natural Language InterfacesGeorge Tolkachev, Stephen Mell, Steve Zdancewic, Osbert Bastani. 113-118 [doi]
• Predicting Difficulty and Discrimination of Natural Language QuestionsMatthew Byrd, Shashank Srivastava. 119-130 [doi]
• How does the pre-training objective affect what large language models learn about linguistic properties?Ahmed Alajrami, Nikolaos Aletras. 131-147 [doi]
• The Power of Prompt Tuning for Low-Resource Semantic ParsingNathan Schucher, Siva Reddy, Harm de Vries. 148-156 [doi]
• Data Contamination: From Memorization to ExploitationInbal Magar, Roy Schwartz 0001. 157-165 [doi]
• Detecting Annotation Errors in Morphological Data with the TransformerLing Liu, Mans Hulden. 166-174 [doi]
• Estimating the Entropy of Linguistic DistributionsAryaman Arora, Clara Meister, Ryan Cotterell. 175-195 [doi]
• Morphological Reinflection with Multiple Arguments: An Extended Annotation schema and a Georgian Case StudyDavid Guriel, Omer Goldman, Reut Tsarfaty. 196-202 [doi]
• DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and QuantizationZheng Li, Zijian Wang, Ming Tan, Ramesh Nallapati, Parminder Bhatia, Andrew O. Arnold, Bing Xiang, Dan Roth. 203-211 [doi]
• Learning-by-Narrating: Narrative Pre-Training for Zero-Shot Dialogue ComprehensionChao Zhao, Wenlin Yao, Dian Yu 0001, Kaiqiang Song, Dong Yu 0001, Jianshu Chen. 212-218 [doi]
• Kronecker Decomposition for GPT CompressionAli Edalati, Marzieh S. Tahaei, Ahmad Rashid, Vahid Partovi Nia, James J. Clark, Mehdi Rezagholizadeh. 219-226 [doi]
• Simple and Effective Knowledge-Driven Query Expansion for QA-Based Product Attribute ExtractionKeiji Shinzato, Naoki Yoshinaga 0001, Yandi Xia, Wei-Te Chen. 227-234 [doi]
• Event-Event Relation Extraction using Probabilistic Box EmbeddingEunJeong Hwang, Jay Yoon Lee, Tianyi Yang, Dhruvesh Patel, Dongxu Zhang, Andrew McCallum. 235-244 [doi]
• Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech TranslationTsz Kin Lam, Shigehiko Schamoni, Stefan Riezler. 245-254 [doi]
• Predicting Sentence Deletions for Text Simplification Using a Functional Discourse StructureBohan Zhang, Prafulla Kumar Choubey, Ruihong Huang. 255-261 [doi]
• Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style TransferHuiyuan Lai, Antonio Toral, Malvina Nissim. 262-271 [doi]
• When to Use Multi-Task Learning vs Intermediate Fine-Tuning for Pre-Trained Encoder Transfer LearningOrion Weller, Kevin D. Seppi, Matt Gardner 0001. 272-282 [doi]
• Leveraging Explicit Lexico-logical Alignments in Text-to-SQL ParsingRunxin Sun, Shizhu He, Chong Zhu, Yaohan He, Jinlong Li, Jun Zhao 0001, Kang Liu 0001. 283-289 [doi]
• Complex Evolutional Pattern Learning for Temporal Knowledge Graph ReasoningZixuan Li, Saiping Guan, Xiaolong Jin, Weihua Peng, Yajuan Lyu, Yong Zhu 0004, Long Bai 0002, Wei Li 0176, Jiafeng Guo, Xueqi Cheng. 290-296 [doi]
• Mismatch between Multi-turn Dialogue and its Evaluation Metric in Dialogue State TrackingTakyoung Kim, Hoonsang Yoon, Yukyung Lee, Pilsung Kang 0001, Misuk Kim. 297-309 [doi]
• LM-BFF-MS: Improving Few-Shot Fine-tuning of Language Models based on Multiple Soft Demonstration MemoryEunhwan Park, Dong Hyeon Jeon, Seonhoon Kim, Inho Kang, Seung-Hoon Na. 310-317 [doi]
• Towards Fair Evaluation of Dialogue State Tracking by Flexible Incorporation of Turn-level PerformancesSuvodip Dey, Ramamohan Kummara, Maunendra Sankar Desarkar. 318-324 [doi]
• Exploiting Language Model Prompts Using Similarity Measures: A Case Study on the Word-in-Context TaskMohsen Tabasi, Kiamehr Rezaee, Mohammad Taher Pilehvar. 325-332 [doi]
• Hierarchical Curriculum Learning for AMR ParsingPeiyi Wang, Liang Chen, Tianyu Liu, Damai Dai, Yunbo Cao, Baobao Chang, Zhifang Sui. 333-339 [doi]
• PARE: A Simple and Strong Baseline for Monolingual and Multilingual Distantly Supervised Relation ExtractionKartikeya Badola Vipul Rathore, Mausam, Parag Singla. 340-354 [doi]
• To Find Waldo You Need Contextual Cues: Debiasing Who's WaldoYiran Luo, Pratyay Banerjee, Tejas Gokhale, Yezhou Yang, Chitta Baral. 355-361 [doi]
• Translate-Train Embracing Translationese ArtifactsSicheng Yu, Qianru Sun, Hao Zhang, Jing Jiang. 362-370 [doi]
• C-MORE: Pretraining to Answer Open-Domain Questions by Consulting Millions of ReferencesXiang Yue, Xiaoman Pan, Wenlin Yao, Dian Yu 0001, Dong Yu 0001, Jianshu Chen. 371-377 [doi]
• k-Rater Reliability: The Correct Unit of Reliability for Aggregated Human AnnotationsKa Wong, Praveen K. Paritosh. 378-384 [doi]
• An Embarrassingly Simple Method to Mitigate Undesirable Properties of Pretrained Language Model TokenizersValentin Hofmann, Hinrich Schütze, Janet B. Pierrehumbert. 385-393 [doi]
• SCD: Self-Contrastive Decorrelation of Sentence EmbeddingsTassilo Klein, Moin Nabi. 394-400 [doi]
• Problems with Cosine as a Measure of Embedding Similarity for High Frequency WordsKaitlyn Zhou, Kawin Ethayarajh, Dallas Card, Dan Jurafsky. 401-423 [doi]
• Revisiting the Compositional Generalization Abilities of Neural Sequence ModelsArkil Patel, Satwik Bhattamishra, Phil Blunsom, Navin Goyal. 424-434 [doi]
• A Copy-Augmented Generative Model for Open-Domain Question AnsweringShuang Liu, Dong Wang, Xiaoguang Li, Minghui Huang, Meizhen Ding. 435-441 [doi]
• Augmenting Document Representations for Dense Retrieval with Interpolation and PerturbationSoyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, Jong C. Park. 442-452 [doi]
• WLASL-LEX: a Dataset for Recognising Phonological Properties in American Sign LanguageFederico Tavella, Viktor Schlegel, Marta Romeo, Aphrodite Galata, Angelo Cangelosi. 453-463 [doi]
• Investigating person-specific errors in chat-oriented dialogue systemsKoh Mitsuda, Ryuichiro Higashinaka, Tingxuan Li, Sen Yoshida. 464-469 [doi]
• Direct parsing to sentiment graphsDavid Samuel, Jeremy Barnes, Robin Kurtz, Stephan Oepen, Lilja Øvrelid, Erik Velldal. 470-478 [doi]
• XDBERT: Distilling Visual Information to BERT from Cross-Modal Systems to Improve Language UnderstandingChan-Jan Hsu, Hung-yi Lee, Yu Tsao 0001. 479-489 [doi]
• As Little as Possible, as Much as Necessary: Detecting Over- and Undertranslations with Contrastive ConditioningJannis Vamvas, Rico Sennrich. 490-500 [doi]
• How Distributed are Distributed Representations? An Observation on the Locality of Syntactic Information in Verb Agreement TasksBingzhi Li, Guillaume Wisniewski, Benoît Crabbé. 501-507 [doi]
• Machine Translation for Livonian: Catering to 20 SpeakersMatiss Rikters, Marili Tomingas, Tuuli Tuisk, Valts Ernstreits, Mark Fishel. 508-514 [doi]
• Fire Burns, Sword Cuts: Commonsense Inductive Bias for Exploration in Text-based GamesDongwon Ryu, Ehsan Shareghi, Meng Fang, Yunqiu Xu, Shirui Pan, Reza Haf. 515-522 [doi]
• A Simple but Effective Pluggable Entity Lookup Table for Pre-trained Language ModelsDeming Ye, Yankai Lin, Peng Li 0030, Maosong Sun, Zhiyuan Liu 0001. 523-529 [doi]
• S$^4$-Tuning: A Simple Cross-lingual Sub-network Tuning MethodRunxin Xu, Fuli Luo, Baobao Chang, Songfang Huang, Fei Huang. 530-537 [doi]
• Region-dependent temperature scaling for certainty calibration and application to class-imbalanced token classificationHillary Dawkins, Isar Nejadgholi. 538-544 [doi]
• Developmental Negation Processing in Transformer Language ModelsAntonio Laverghetta Jr., John Licato. 545-551 [doi]
• Canary Extraction in Natural Language Understanding ModelsRahil Parikh, Christophe Dupuy, Rahul Gupta. 552-560 [doi]
• On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language RepresentationsYang Trista Cao, Yada Pruksachatkun, Kai-Wei Chang, Rahul Gupta, Varun Kumar, Jwala Dhamala, Aram Galstyan. 561-570 [doi]
• Sequence-to-sequence AMR Parsing with Ancestor InformationChen Yu, Daniel Gildea. 571-577 [doi]
• Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum LearningMiryam de Lhoneux, Sheng Zhang 0022, Anders Søgaard. 578-587 [doi]
• PriMock57: A Dataset Of Primary Care Mock ConsultationsAlex Papadopoulos-Korfiatis, Francesco Moramarco, Radmila Sarac, Aleksandar Savkov. 588-598 [doi]
• UniGDD: A Unified Generative Framework for Goal-Oriented Document-Grounded DialogueChang Gao, Wenxuan Zhang, Wai Lam. 599-605 [doi]
• DMix: Adaptive Distance-aware Interpolative MixupRamit Sawhney, Megh Thakkar, Shrey Pandit, Ritesh Soun, Di Jin, Diyi Yang, Lucie Flek. 606-612 [doi]
• Sub-Word Alignment is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine TranslationMinhan Xu, Yu Hong. 613-619 [doi]
• HYPHEN: Hyperbolic Hawkes Attention For Text StreamsShivam Agarwal, Ramit Sawhney, Sanchit Ahuja, Ritesh Soun, Sudheer Chava. 620-627 [doi]
• A Risk-Averse Mechanism for Suicidality Assessment on Social MediaRamit Sawhney, Atula Tejaswi Neerkaje, Manas Gaur. 628-635 [doi]
• When classifying grammatical role, BERT doesn't care about word order... except when it mattersIsabel Papadimitriou, Richard Futrell, Kyle Mahowald. 636-643 [doi]
• Triangular Transfer: Freezing the Pivot for Triangular Machine TranslationMeng Zhang, Liangyou Li, Qun Liu 0001. 644-650 [doi]
• Can Visual Dialogue Models Do Scorekeeping? Exploring How Dialogue Representations Incrementally Encode Shared KnowledgeBrielen Madureira, David Schlangen. 651-664 [doi]
• Focus on the Target's Vocabulary: Masked Label Smoothing for Machine TranslationLiang Chen, Runxin Xu, Baobao Chang. 665-671 [doi]
• Contrastive Learning-Enhanced Nearest Neighbor Mechanism for Multi-Label Text ClassificationXi'ao Su, Ran Wang, Xinyu Dai. 672-679 [doi]
• NoisyTune: A Little Noise Can Help You Finetune Pretrained Language Models BetterChuhan Wu, Fangzhao Wu, Tao Qi, Yongfeng Huang 0001. 680-685 [doi]
• Adjusting the Precision-Recall Trade-Off with Align-and-Predict Decoding for Grammatical Error CorrectionXin Sun 0013, Houfeng Wang. 686-693 [doi]
• On the Effect of Isotropy on VAE Representations of TextLan Zhang, Wray L. Buntine, Ehsan Shareghi. 694-701 [doi]
• Efficient Classification of Long Documents Using TransformersHyunji Hayley Park, Yogarshi Vyas, Kashif Shah. 702-709 [doi]
• Rewarding Semantic Similarity under Optimized Alignments for AMR-to-Text GenerationLisa Jin, Daniel Gildea. 710-715 [doi]
• An Analysis of Negation in Natural Language Understanding CorporaMd Mosharaf Hossain, Dhivya Chinnappa, Eduardo Blanco 0002. 716-723 [doi]
• Primum Non Nocere: Before working with Indigenous data, the ACL must confront ongoing colonialismLane Schwartz. 724-731 [doi]
• Unsupervised multiple-choice question generation for out-of-domain Q&A fine-tuningGuillaume Le Berre, Christophe Cerisara, Philippe Langlais, Guy Lapalme. 732-738 [doi]
• Can a Transformer Pass the Wug Test? Tuning Copying Bias in Neural Morphological Inflection ModelsLing Liu, Mans Hulden. 739-749 [doi]
• Probing the Robustness of Trained Metrics for Conversational Dialogue SystemsJan Deriu, Don Tuggener, Pius von Däniken, Mark Cieliebak. 750-761 [doi]
• Rethinking and Refining the Distinct MetricSiyang Liu, Sahand Sabour, Yinhe Zheng, Pei Ke, Xiaoyan Zhu 0001, Minlie Huang. 762-770 [doi]
• How reparametrization trick broke differentially-private text representation learningIvan Habernal. 771-777 [doi]
• Towards Consistent Document-level Entity Linking: Joint Models for Entity Linking and Coreference ResolutionKlim Zaporojets, Johannes Deleu, Yiwei Jiang, Thomas Demeester, Chris Develder. 778-784 [doi]
• A Flexible Multi-Task Model for BERT ServingTianwen Wei, Jianwei Qi, Shenghuan He. 785-796 [doi]
• Understanding Game-Playing Agents with Natural Language AnnotationsNicholas Tomlin, Andre He, Dan Klein. 797-807 [doi]
• Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic ICD CodingZheng Yuan 0002, Chuanqi Tan, Songfang Huang. 808-814 [doi]
• CoDA21: Evaluating Language Understanding Capabilities of NLP Models With Context-Definition AlignmentLütfi Kerem Senel, Timo Schick, Hinrich Schütze. 815-824 [doi]
• On the Importance of Effectively Adapting Pretrained Language Models for Active LearningKaterina Margatina, Loïc Barrault, Nikolaos Aletras. 825-836 [doi]
• A Recipe for Arbitrary Text Style Transfer with Large Language ModelsEmily Reif, Daphne Ippolito, Ann Yuan, Andy Coenen, Chris Callison-Burch, Jason Wei. 837-848 [doi]
• DiS-ReX: A Multilingual Dataset for Distantly Supervised Relation ExtractionAbhyuday Bhartiya, Kartikeya Badola, Mausam. 849-863 [doi]
• (Un)solving Morphological Inflection: Lemma Overlap Artificially Inflates Models' PerformanceOmer Goldman, David Guriel, Reut Tsarfaty. 864-870 [doi]
• Text Smoothing: Enhance Various Data Augmentation Methods on Text Classification TasksXing Wu 0002, Chaochen Gao, Meng Lin, Liangjun Zang, Songlin Hu. 871-875 [doi]