Viewing 1-10 of 35 papers
  • Abductive Commonsense Reasoning

    Chandra Bhagavatula, Ronan Le Bras, Chaitanya Malaviya, Keisuke Sakaguchi, Ari Holtzman, Hannah Rashkin, Doug Downey, Scott Wen-tau Yih, Yejin ChoiICLR2020Abductive reasoning is inference to the most plausible explanation. For example, if Jenny finds her house in a mess when she returns from work, and remembers that she left a window open, she can hypothesize that a thief broke into her house and caused the mess, as the most plausible explanation… more
  • Adversarial Filters of Dataset Biases

    Ronan Le Bras, Swabha Swayamdipta, Chandra Bhagavatula, Rowan Zellers, Matthew E. Peters, Ashish Sabharwal, Yejin Choi arXiv2020Large neural models have demonstrated humanlevel performance on language and vision benchmarks such as ImageNet and Stanford Natural Language Inference (SNLI). Yet, their performance degrades considerably when tested on adversarial or out-of-distribution samples. This raises the question of whether… more
  • WinoGrande: An Adversarial Winograd Schema Challenge at Scale

    Keisuke Sakaguchi, Ronan Le Bras, Chandra Bhagavatula, Yejin ChoiAAAI2020The Winograd Schema Challenge (WSC), proposed by Levesque et al. (2011) as an alternative to the Turing Test, was originally designed as a pronoun resolution problem that cannot be solved based on statistical patterns in large text corpora. However, recent studies suggest that current WSC datasets… more
  • Commonsense Knowledge Base Completion with Structural and Semantic Context

    Chaitanya Malaviya, Chandra Bhagavatula, Antoine Bosselut, Yejin ChoiAAAI2019Automatic KB completion for commonsense knowledge graphs (e.g., ATOMIC and ConceptNet) poses unique challenges compared to the much studied conventional knowledge bases (e.g., Freebase). Commonsense knowledge graphs use free-form text to represent nodes, resulting in orders of magnitude more nodes… more
  • BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle

    Peter West, Ari Holtzman, Jan Buys, Yejin ChoiEMNLP2019The principle of the Information Bottleneck (Tishby et al. 1999) is to produce a summary of information X optimized to predict some other relevant information Y. In this paper, we propose a novel approach to unsupervised sentence summarization by mapping the Information Bottleneck principle to a… more
  • COSMOS QA: Machine Reading Comprehension with Contextual Commonsense Reasoning

    Lifu Huang, Ronan Le Bras, Chandra Bhagavatula, Yejin ChoiEMNLP2019Understanding narratives requires reading between the lines, which in turn, requires interpreting the likely causes and effects of events, even when they are not mentioned explicitly. In this paper, we introduce Cosmos QA, a large-scale dataset of 35,600 problems that require commonsense-based… more
  • Counterfactual Story Reasoning and Generation

    Lianhui Qin, Antoine Bosselut, Ari Holtzman, Chandra Bhagavatula, Elizabeth Clark, Yejin ChoiEMNLP2019Counterfactual reasoning requires predicting how alternative events, contrary to what actually happened, might have resulted in different outcomes. Despite being considered a necessary component of AI-complete systems, few resources have been developed for evaluating counterfactual reasoning in… more
  • Efficient Navigation with Language Pre-training and Stochastic Sampling

    Xiujun Li, Chunyuan Li, Qiaolin Xia, Yonatan Bisk, Asli Celikyilmaz, Jianfeng Gao, Noah Smith, Yejin ChoiEMNLP2019Core to the vision-and-language navigation (VLN) challenge is building robust instruction representations and action decoding schemes, which can generalize well to previously unseen instructions and environments. In this paper, we report two simple but highly effective methods to address these… more
  • SocialIQA: Commonsense Reasoning about Social Interactions

    Maarten Sap, Hannah Rashkin, Derek Chen, Ronan LeBras, Yejin ChoiEMNLP2019We introduce Social IQa, the first largescale benchmark for commonsense reasoning about social situations. Social IQa contains 38,000 multiple choice questions for probing emotional and social intelligence in a variety of everyday situations (e.g., Q: "Jordan wanted to tell Tracy a secret, so… more
  • COMET: Commonsense Transformers for Automatic Knowledge Graph Construction

    Antoine Bosselut, Hannah Rashkin, Maarten Sap, Chaitanya Malaviya, Asli Celikyilmaz, Yejin ChoiACL2019We present the first comprehensive study on automatic knowledge base construction for two prevalent commonsense knowledge graphs: ATOMIC (Sap et al., 2019) and ConceptNet (Speer et al., 2017). Contrary to many conventional KBs that store knowledge with canonical templates, commonsense KBs only… more