 XMD: An End-to-End Framework for Interactive Explanation-Based Debugging
of NLP ModelsAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Two is Better than Many? Binary Classification as an Effective Approach
to Multi-Choice Question AnsweringConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Analyzing Multi-Task Learning for Abstractive Text SummarizationIEEE Games Entertainment Media Conference (GEM), 2022 |
 Retrieval Augmentation for Commonsense Reasoning: A Unified ApproachConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Realistic Data Augmentation Framework for Enhancing Tabular ReasoningConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 DiscoSense: Commonsense Reasoning with Discourse ConnectivesConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 Prajjwal Bhargava Vincent Ng |
 Leveraging Large Language Models for Multiple Choice Question AnsweringInternational Conference on Learning Representations (ICLR), 2022 |
 Tempo: Accelerating Transformer-Based Model Training through Memory
Footprint ReductionNeural Information Processing Systems (NeurIPS), 2022 |
 JECC: Commonsense Reasoning Tasks Derived from Interactive FictionsAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Mitigating Covertly Unsafe Text within Natural Language SystemsConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 MICO: A Multi-alternative Contrastive Learning Framework for Commonsense
Knowledge RepresentationConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Can Language Representation Models Think in Bets?Royal Society Open Science (RSOS), 2022 |
 EduQG: A Multi-format Multiple Choice Dataset for the Educational DomainIEEE Access (IEEE Access), 2022 |
 Uncertainty Quantification with Pre-trained Language Models: A
Large-Scale Empirical AnalysisConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 State-of-the-art generalisation research in NLP: A taxonomy and reviewNature Machine Intelligence (Nat. Mach. Intell.), 2022 |
 Downstream Datasets Make Surprisingly Good Pretraining CorporaAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Efficient Methods for Natural Language Processing: A SurveyTransactions of the Association for Computational Linguistics (TACL), 2022 |
 On Reality and the Limits of Language Data: Aligning LLMs with Human
NormsAnnual Meeting of the Cognitive Science Society (CogSci), 2022 |
 Shortcut Learning of Large Language Models in Natural Language
UnderstandingCommunications of the ACM (CACM), 2022 |
 Few-shot Adaptation Works with UnpredicTable DataAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 RealTime QA: What's the Answer Right Now?Neural Information Processing Systems (NeurIPS), 2022 |
 WinoGAViL: Gamified Association Benchmark to Challenge
Vision-and-Language ModelsNeural Information Processing Systems (NeurIPS), 2022 |
 Language model compression with weighted low-rank factorizationInternational Conference on Learning Representations (ICLR), 2022 |
 KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in
Low-Resource NLPInternational Conference on Learning Representations (ICLR), 2022 |
 CoSe-Co: Text Conditioned Generative CommonSense ContextualizerNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 |
 Modularized Transfer Learning with Multiple Knowledge Graphs for
Zero-shot Commonsense ReasoningNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 |
 Making Large Language Models Better Reasoners with Step-Aware VerifierAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Learning as Conversation: Dialogue Systems Reinforced for Information
AcquisitionNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 |
 Eliciting and Understanding Cross-Task Skills with Task-Level
Mixture-of-ExpertsConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 Partial-input baselines show that NLI models can ignore context, but
they don'tNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 |
 On the Paradox of Learning to Reason from DataInternational Joint Conference on Artificial Intelligence (IJCAI), 2022 |
 Housekeep: Tidying Virtual Households using Commonsense ReasoningEuropean Conference on Computer Vision (ECCV), 2022 |
 FETA: A Benchmark for Few-Sample Task Transfer in Open-Domain DialogueConference on Empirical Methods in Natural Language Processing (EMNLP), 2022 |
 A Data Cartography based MixUp for Pre-trained Language ModelsNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 Seohong Park Cornelia Caragea |
 ElitePLM: An Empirical Study on General Language Ability Evaluation of
Pretrained Language ModelsNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 |
 ChapterBreak: A Challenge Dataset for Long-Range Language ModelsNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 |
 SalesBot: Transitioning from Chit-Chat to Task-Oriented DialoguesAnnual Meeting of the Association for Computational Linguistics (ACL), 2022 |
 Imagination-Augmented Natural Language UnderstandingNorth American Chapter of the Association for Computational Linguistics (NAACL), 2022 |
 What If: Generating Code to Answer Simulation QuestionsAnnual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2022 |
