Papers of 2021 — page 1263 papers · all years1 2 3"I'll be there for you": The One with Understanding Indirect AnswersCathrine Damgaard, Paulina Toborek, Trine Eriksen, et al.English"Talk to me with left, right, and angles": Lexical entrainment in spoken Hebrew dialogueAndreas Weise, Vered Silber-Varod, Anat Lerner, et al.Modern Hebrew'Between' constructions in Biblical HebrewJoost ZwartsAncient Hebrew8-bit Optimizers via Block-wise QuantizationTim Dettmers, Mike Lewis, Sam Shleifer, et al.arXiv:2110.02861A Closer Look into the Robustness of Neural Dependency Parsers Using Better Adversarial ExamplesYuxuan Wang, Wanxiang Che, Ivan Titov, et al.EnglishA Dataset of Information-Seeking Questions and Answers Anchored in Research PapersPradeep Dasigi, Kyle Lo, Iz Beltagy, et al.Proceedings of the 2021 Conference of the North…A Fine-Grained Analysis of BERTScoreMichael Hanna, Ondřej BojarProceedings of the Sixth Conference on Machine…A General Language Assistant as a Laboratory for AlignmentAmanda Askell, Yuntao Bai, Anna Chen, et al.arXiv:2112.00861A practical introduction to the Rational Speech Act modeling frameworkGregory Scontras, Michael Henry Tessler, Michael FrankeEnglishA Recipe For Arbitrary Text Style Transfer with Large Language ModelsEmily Reif, Daphne Ippolito, Ann Yuan, et al.arXiv:2109.03910A Robustly Optimized BERT Pre-training Approach with Post-trainingLiu Zhuang, Lin Wayne, Shi Ya, et al.Proceedings of the 20th Chinese National…A Survey of Data Augmentation Approaches for NLPSteven Y. Feng, Varun Gangal, Jason Wei, et al.arXiv:2105.03075A Survey on Recent Approaches for Natural Language Processing in Low-Resource ScenariosMichael A. Hedderich, Lukas Lange, Heike Adel, et al.Proceedings of the 2021 Conference of the North…A unified approach to sentence segmentation of punctuated text in many languagesRachel Wicks, Matt PostEnglishA Unified Generative Framework for Various NER SubtasksHang Yan, Tao Gui, Junqi Dai, et al.Proceedings of the 59th Annual Meeting of the…Acquiring a Formality-Informed Lexical Resource for Style AnalysisElisabeth Eder, Ulrike Krieg-Holz, Udo HahnMachine translationAdapterDrop: On the Efficiency of Adapters in TransformersAndreas Rücklé, Gregor Geigle, Max Glockner, et al.Proceedings of the 2021 Conference on Empirical…Adjectival polarity and the processing of scalar inferencesBob van Tiel, Elizabeth PankratzEnglishAlephBERT: A Hebrew Large Pre-Trained Language Model to Start-off your Hebrew NLP Application WithAmit Seker, Elron Bandel, Dan Bareket, et al.Modern HebrewAmnesic Probing: Behavioral Explanation with Amnesic CounterfactualsYanai Elazar, Shauli Ravfogel, Alon Jacovi, et al.Transactions of the Association for…An Error Analysis Framework for Shallow Surface RealizationAnastasia Shimorina, Yannick Parmentier, Claire GardentMachine translationAn Explanation of In-context Learning as Implicit Bayesian InferenceSang Michael Xie, Aditi Raghunathan, Percy Liang, et al.arXiv:2111.02080Anatomy of OntoGUM—Adapting GUM to the OntoNotes Scheme to Evaluate Robustness of SOTA Coreference AlgorithmsYilun Zhu, Sameer Pradhan, Amir ZeldesEnglishAnnotating and Modeling Fine-grained Factuality in SummarizationTanya Goyal, Greg DurrettProceedings of the 2021 Conference of the North…Annotation guidelines of UD and SUD treebanks for spoken corpora: A proposalSylvain Kahane, Bernard Caron, Emmett Strickland, et al.EnglishApplying Occam's Razor to Transformer-Based Dependency Parsing: What Works, What Doesn't, and What is Really NecessaryStefan Grünewald, Annemarie Friedrich, Jonas KuhnMova's core listApproximation derived from a scalar exclusive particle associating with covert focus: The case of Hebrew be-sax ha-kolDina Orenstein, Yael GreenbergModern HebrewARBERT & MARBERT: Deep Bidirectional Transformers for ArabicMuhammad Abdul-Mageed, AbdelRahim Elmadany, El Moatez Billah NagoudiarXiv:2101.01785 · ACL-2021 camera ready versionAre Ellipses Important for Machine Translation?Payal KhullarEnglishAre NLP Models really able to Solve Simple Math Word Problems?Arkil Patel, Satwik Bhattamishra, Navin GoyalMova's core listAre References Really Needed? Unbabel-IST 2021 Submission for the Metrics Shared TaskRicardo Rei, Ana C Farinha, Chrysoula Zerva, et al.Proceedings of the Sixth Conference on Machine…Aspect Sentiment Quad Prediction as Paraphrase GenerationWenxuan Zhang, Yang Deng, Xin Li, et al.Proceedings of the 2021 Conference on Empirical…Automated Extraction of Sentencing Decisions from Court Cases in the Hebrew LanguageMohr Wenger, Tom Kalir, Noga Berger, et al.Modern HebrewBARTScore: Evaluating Generated Text as Text GenerationWeizhe Yuan, Graham Neubig, Pengfei LiuarXiv:2106.11520BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval ModelsNandan Thakur, Nils Reimers, Andreas Rücklé, et al.NeurIPS 2021 Datasets and BenchmarksBitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelsElad Ben-Zaken, Shauli Ravfogel, Yoav GoldbergarXiv:2106.10199Calibrate Before Use: Improving Few-Shot Performance of Language ModelsTony Z. Zhao, Eric Wallace, Shi Feng, et al.arXiv:2102.09690Can predicate-argument relationships be extracted from UD trees?Adam Ek, Jean-Philippe Bernardy, Stergios ChatzikyriakidisEnglishCarbon Emissions and Large Neural Network TrainingDavid Patterson, Joseph Gonzalez, Quoc Le, et al.arXiv:2104.10350Causation (and Some Other) Paraphrasing Patterns in L1 English. A Case StudyJasmina MilićevićEnglishCLIFF: Contrastive Learning for Improving Faithfulness and Factuality in Abstractive SummarizationShuyang Cao, Lu WangProceedings of the 2021 Conference on Empirical…CLIPScore: A Reference-free Evaluation Metric for Image CaptioningJack Hessel, Ari Holtzman, Maxwell Forbes, et al.Proceedings of the 2021 Conference on Empirical…Combined discourse representations: Coherence relations and questions under DiscussionArndt Riester, Amalia Canes Nápoles, Jet HoekEnglishConSERT: A Contrastive Framework for Self-Supervised Sentence Representation TransferYuanmeng Yan, Rumei Li, Sirui Wang, et al.Proceedings of the 59th Annual Meeting of the…Contrastive Learning for Many-to-many Multilingual Neural Machine TranslationXiao Pan, Mingxuan Wang, Liwei Wu, et al.Proceedings of the 59th Annual Meeting of the…Controllable Text Simplification with Explicit ParaphrasingMounica Maddela, Fernando Alva-Manchego, Wei XuProceedings of the 2021 Conference of the North…Coordinate Constructions in English Enhanced Universal Dependencies: Analysis and Computational ModelingStefan Grünewald, Prisca Piccirilli, Annemarie FriedrichMova's core listCoreference meets Universal Dependencies – a pilot experiment on harmonizing coreference datasets for 11 languagesAnna Nedoluzhko, Michal Novák, Martin Popel, et al.EnglishCoreference Resolution without Span RepresentationsYuval Kirstain, Ori Ram, Omer LevyProceedings of the 59th Annual Meeting of the…Counting the Jeremiahs: Machine Learning and the Jeremiah NarrativesNicholas J. CampbellAncient HebrewCross-linguistically Consistent Semantic and Syntactic Annotation of Child-directed SpeechIda Szubert, Omri Abend, Nathan Schneider, et al.Modern HebrewCUAD: An Expert-Annotated NLP Dataset for Legal Contract ReviewDan Hendrycks, Collin Burns, Anya Chen, et al.arXiv:2103.06268Datasets: A Community Library for Natural Language ProcessingQuentin Lhoest, Albert Villanova del Moral, Yacine Jernite, et al.arXiv:2109.02846DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding SharingPengcheng He, Jianfeng Gao, Weizhu ChenarXiv:2111.09543Deciphering Undersegmented Ancient Scripts Using Phonetic PriorJiaming Luo, Frederik Hartmann, Enrico Santus, et al.Semitic languagesDeCLUTR: Deep Contrastive Learning for Unsupervised Textual RepresentationsJohn Giorgi, Osvald Nitski, Bo Wang, et al.Proceedings of the 59th Annual Meeting of the…Defining Definiteness in TuroyoMiriam Yifrach, Elizabeth CoppockAramaicDependency Parsing Evaluation for Low-resource Spontaneous SpeechZoey Liu, Emily Prud'hommeauxEnglishDExperts: Decoding-Time Controlled Text Generation with Experts and Anti-ExpertsAlisa Liu, Maarten Sap, Ximing Lu, et al.Proceedings of the 59th Annual Meeting of the…DialogSum: A Real-Life Scenario Dialogue Summarization DatasetYulong Chen, Yang Liu, Liang Chen, et al.Findings of the Association for Computational…Differential Object Marking in Modern Hebrew: Definiteness and partitivityAviya Hacohen, Olga Kagan, Dana PlautModern HebrewDo UD Trees Match Mention Spans in Coreference Annotations?Martin Popel, Zdeněk Žabokrtský, Anna Nedoluzhko, et al.EnglishDocNLI: A Large-scale Dataset for Document-level Natural Language InferenceWenpeng Yin, Dragomir Radev, Caiming XiongFindings of the Association for Computational…Document-Level Event Argument Extraction by Conditional GenerationSha Li, Heng Ji, Jiawei HanProceedings of the 2021 Conference of the North…Domain-Aware Dependency Parsing for QuestionsAparna Garimella, Laura Chiticariu, Yunyao LiEnglishEfficient Attentions for Long Document SummarizationLuyang Huang, Shuyang Cao, Nikolaus Parulian, et al.Proceedings of the 2021 Conference of the North…Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware SamplingSebastian Hofstatter, Sheng-Chieh Lin, Jheng-Hong Yang, et al.arXiv:2104.06967Ellipsis Resolution as Question Answering: An EvaluationRahul Aralikatte, Matthew Lamm, Daniel Hardt, et al.EnglishEmerging Properties in Self-Supervised Vision TransformersMathilde Caron, Hugo Touvron, Ishan Misra, et al.arXiv:2104.14294English Machine Reading Comprehension Datasets: A SurveyDaria Dzendzik, Jennifer Foster, Carl VogelEnglishEntity-Based Knowledge Conflicts in Question AnsweringShayne Longpre, Kartik Perisetla, Anthony Chen, et al.arXiv:2109.05052ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and GenerationYu Sun, Shuohuan Wang, Shikun Feng, et al.arXiv:2107.02137Ethical and social risks of harm from Language ModelsLaura Weidinger, John Mellor, Maribeth Rauh, et al.arXiv:2112.04359Evaluating Large Language Models Trained on CodeMark Chen, Jerry Tworek, Heewoo Jun, et al.arXiv:2107.03374Evaluating Text Generation from Discourse Representation StructuresChunliu Wang, Rik van Noord, Arianna Bisazza, et al.Machine translationEvaluating the Evaluation Metrics for Style Transfer: A Case Study in Multilingual Formality TransferEleftheria Briakou, Sweta Agrawal, Joel Tetreault, et al.Machine translationEvaluating Universal Dependency Parser Recovery of Predicate Argument Structure via CompChain AnalysisSagar Indurkhya, Beracah Yankama, Robert C. BerwickEnglishExpanding the JHU Bible Corpus for Machine Translation of the Indigenous Languages of North AmericaGarrett Nicolai, Edith Coates, Ming Zhang, et al.Machine translationExperts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine TranslationMarkus Freitag, George Foster, David Grangier, et al.Machine translationExplaining Answers with Entailment TreesBhavana Dalvi, Peter Jansen, Oyvind Tafjord, et al.arXiv:2104.08661Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language InferenceTimo Schick, Hinrich SchützeProceedings of the 16th Conference of the…Factual Probing Is [MASK]: Learning vs. Learning to RecallZexuan Zhong, Dan Friedman, Danqi ChenProceedings of the 2021 Conference of the North…False resultatives: The interaction of agreement and creation in Northern Galilee Levantine ArabicTova Rapoport, Aya ZarkaSemitic languagesFamiliar vs. unique in a diachronic perspective. Case study of the rise of the definite article in North GermanicAlicja Piotrowska, Dominika SkrzypekEnglishFew-NERD: A Few-shot Named Entity Recognition DatasetNing Ding, Guangwei Xu, Yulin Chen, et al.Proceedings of the 59th Annual Meeting of the…Few-shot Learning with Multilingual Language ModelsXi Victoria Lin, Todor Mihaylov, Mikel Artetxe, et al.arXiv:2112.10668Filling the Gaps in Ancient Akkadian Texts: A Masked Language Modelling ApproachKoren Lazar, Benny Saret, Asaf Yehudai, et al.Semitic languagesFinding Variants for Construction-Based Dialectometry: A Corpus-Based Approach to Regional CxGsJonathan DunnEnglishFindings of the 2021 Conference on Machine Translation (WMT21)Farhad Akhbardeh, Arkady Arkhangorodsky, Magdalena Biesialska, et al.Proceedings of the Sixth Conference on Machine…Findings of the WMT 2021 Shared Task on Quality EstimationLucia Specia, Frédéric Blain, Marina Fomicheva, et al.Proceedings of the Sixth Conference on Machine…FinQA: A Dataset of Numerical Reasoning over Financial DataZhiyu Chen, Wenhu Chen, Charese Smiley, et al.Proceedings of the 2021 Conference on Empirical…From polysemy to semantic change: remarks on the lexeme miṣwà in Biblical and Mishnaic HebrewRomina VergariAncient HebrewFrom Raw Text to Enhanced Universal Dependencies: The Parsing Shared Task at IWPT 2021Gosse Bouma, Djamé Seddah, Daniel ZemanEnglishFrozen by context: Pragmatic factors of syntactic freezingGouming MartensEnglishFUDGE: Controlled Text Generation With Future DiscriminatorsKevin Yang, Dan KleinProceedings of the 2021 Conference of the North…GeDi: Generative Discriminator Guided Sequence GenerationBen Krause, Akhilesh Deepak Gotmare, Bryan McCann, et al.Findings of the Association for Computational…Gender Bias in Machine TranslationBeatrice Savoldi, Marco Gaido, Luisa Bentivogli, et al.Transactions of the Association for…Generating Datasets with Pretrained Language ModelsTimo Schick, Hinrich SchutzearXiv:2104.07540Generic Oracles for Structured PredictionChristoph Teichmann, Antoine VenantEnglishGet Your Vitamin C! Robust Fact Verification with Contrastive EvidenceTal Schuster, Adam Fisch, Regina BarzilayProceedings of the 2021 Conference of the North…1 2 3