 Reference-based Weak Supervision for Answer Sentence Selection using Web
DataConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 On the Influence of Masking Policies in Intermediate Pre-trainingConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 SciCo: Hierarchical Cross-Document Coreference for Scientific ConceptsConference on Automated Knowledge Base Construction (AKBC), 2021 |
 Documenting Large Webtext Corpora: A Case Study on the Colossal Clean
Crawled CorpusConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 Crossing the Conversational Chasm: A Primer on Natural Language
Processing for Multilingual Task-Oriented Dialogue SystemsJournal of Artificial Intelligence Research (JAIR), 2021 |
 The challenges of temporal alignment on Twitter during crisesConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 Moving on from OntoNotes: Coreference Resolution Model TransferConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 Sequential Cross-Document Coreference ResolutionConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 On the Importance of Effectively Adapting Pretrained Language Models for
Active LearningAnnual Meeting of the Association for Computational Linguistics (ACL), 2021 |
 Capturing Row and Column Semantics in Transformer Based Question
Answering over TablesNorth American Chapter of the Association for Computational Linguistics (NAACL), 2021 |
 AMMU : A Survey of Transformer-based Biomedical Pretrained Language
ModelsJournal of Biomedical Informatics (JBI), 2021 |
 What to Pre-Train on? Efficient Intermediate Task SelectionConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 Temporal Adaptation of BERT and Performance on Downstream Document
Classification: Insights from Social MediaConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 Paul Röttger J. Pierrehumbert |
 To Share or not to Share: Predicting Sets of Sources for Model Transfer
LearningConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 A Million Tweets Are Worth a Few Points: Tuning Transformers for
Customer Service TasksNorth American Chapter of the Association for Computational Linguistics (NAACL), 2021 |
 Probing Across Time: What Does RoBERTa Know and When?Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 Cross-Domain Label-Adaptive Stance DetectionConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 Pseudo Zero Pronoun Resolution Improves Zero Anaphora ResolutionConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 Multitasking Inhibits Semantic DriftNorth American Chapter of the Association for Computational Linguistics (NAACL), 2021 |
 Modeling Human Mental States with an Entity-based Narrative GraphNorth American Chapter of the Association for Computational Linguistics (NAACL), 2021 |
 UDALM: Unsupervised Domain Adaptation through Language ModelingNorth American Chapter of the Association for Computational Linguistics (NAACL), 2021 |
 TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for
Unsupervised Sentence Embedding LearningConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 Detoxifying Language Models Risks Marginalizing Minority VoicesNorth American Chapter of the Association for Computational Linguistics (NAACL), 2021 |
 SpartQA: : A Textual Question Answering Benchmark for Spatial ReasoningNorth American Chapter of the Association for Computational Linguistics (NAACL), 2021 |
 On the Inductive Bias of Masked Language Modeling: From Statistical to
Syntactic DependenciesNorth American Chapter of the Association for Computational Linguistics (NAACL), 2021 Tianyi Zhang Tatsunori Hashimoto |
 Fine-tuning Encoders for Improved Monolingual and Zero-shot Polylingual
Neural Topic ModelingNorth American Chapter of the Association for Computational Linguistics (NAACL), 2021 |
 TAPAS at SemEval-2021 Task 9: Reasoning over tables with intermediate
pre-trainingInternational Workshop on Semantic Evaluation (SemEval), 2021 |
 Self-Supervised Pretraining Improves Self-Supervised PretrainingIEEE Workshop/Winter Conference on Applications of Computer Vision (WACV), 2021 |
 Improving and Simplifying Pattern Exploiting TrainingConference on Empirical Methods in Natural Language Processing (EMNLP), 2021 |
 MasakhaNER: Named Entity Recognition for African LanguagesTransactions of the Association for Computational Linguistics (TACL), 2021 |
 AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive
SummarizationNorth American Chapter of the Association for Computational Linguistics (NAACL), 2021 |
 Self-Supervised Test-Time Learning for Reading ComprehensionNorth American Chapter of the Association for Computational Linguistics (NAACL), 2021 |
 Structure Inducing Pre-TrainingNature Machine Intelligence (Nat. Mach. Intell.), 2021 |
 Modeling the Second Player in Distributionally Robust OptimizationInternational Conference on Learning Representations (ICLR), 2021 |
 Self-supervised Regularization for Text ClassificationTransactions of the Association for Computational Linguistics (TACL), 2021 |
 Large Pre-trained Language Models Contain Human-like Biases of What is
Right and Wrong to DoNature Machine Intelligence (Nat. Mach. Intell.), 2021 |
 "Sharks are not the threat humans are": Argument Component Segmentation
in School Student EssaysWorkshop on Innovative Use of NLP for Building Educational Applications (UNBEA), 2021 |
 OAG-BERT: Towards A Unified Backbone Language Model For Academic
Knowledge ServicesKnowledge Discovery and Data Mining (KDD), 2021 |
 ToxCCIn: Toxic Content Classification with InterpretabilityWorkshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (WASSA), 2021 |
 Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based
Bias in NLPTransactions of the Association for Computational Linguistics (TACL), 2021 |
