Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 201-210 of 241 papers
COMET: Commonsense Transformers for Automatic Knowledge Graph Construction
Antoine Bosselut, Hannah Rashkin, Maarten Sap, Chaitanya Malaviya, Asli Celikyilmaz, Yejin ChoiACL • 2019 We 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…HellaSwag: Can a Machine Really Finish Your Sentence?
Rowan Zellers, Ari Holtzman, Yonatan Bisk, Ali Farhadi, Yejin ChoiACL • 2019 Recent work by Zellers et al. (2018) introduced a new task of commonsense natural language inference: given an event description such as "A woman sits at a piano," a machine must select the most likely followup: "She sets her fingers on the keys." With the…The Risk of Racial Bias in Hate Speech Detection
Maarten Sap, Dallas Card, Saadia Gabriel, Yejin Choi, Noah A. SmithACL • 2019 We investigate how annotators’ insensitivity to differences in dialect can lead to racial bias in automatic hate speech detection models, potentially amplifying harm against minority populations. We first uncover unexpected correlations between surface…Robust Navigation with Language Pretraining and Stochastic Sampling
Xiujun Li, Chunyuan Li, Qiaolin Xia, Yonatan Bisk, Asli Celikyilmaz, Jianfeng Gao, Noah A. Smith, Yejin ChoiEMNLP • 2019 Core 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…Do Neural Language Representations Learn Physical Commonsense?
Maxwell Forbes, Ari Holtzman, Yejin ChoiCogSci • 2019 Humans understand language based on the rich background knowledge about how the physical world works, which in turn allows us to reason about the physical world through language. In addition to the properties of objects (e.g., boats require fuel) and their…Cooperative Generator-Discriminator Networks for Abstractive Summarization with Narrative Flow
Saadia Gabriel, Antoine Bosselut, Ari Holtzman, Kyle Lo, Asli Çelikyilmaz, Yejin ChoiarXiv • 2019 We introduce Cooperative Generator-Discriminator Networks (Co-opNet), a general framework for abstractive summarization with distinct modeling of the narrative flow in the output summary. Most current approaches to abstractive summarization, in contrast, are…Efficient Adaptation of Pretrained Transformers for Abstractive Summarization
Andrew Pau Hoang, Antoine Bosselut, Asli Çelikyilmaz, Yejin ChoiarXiv • 2019 Large-scale learning of transformer language models has yielded improvements on a variety of natural language understanding tasks. Whether they can be effectively adapted for summarization, however, has been less explored, as the learned representations are…From Recognition to Cognition: Visual Commonsense Reasoning
Rowan Zellers, Yonatan Bisk, Ali Farhadi, Yejin ChoiCVPR • 2019 Visual understanding goes well beyond object recognition. With one glance at an image, we can effortlessly imagine the world beyond the pixels: for instance, we can infer people’s actions, goals, and mental states. While this task is easy for humans, it is…Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading
Lianhui Qin, Michel Galley, Chris Brockett, Xiaodong Liu, Xiang Gao, W. Dolan, Yejin Choi, Jianfeng GaoACL • 2019 Although neural conversational models are effective in learning how to produce fluent responses, their primary challenge lies in knowing what to say to make the conversation contentful and non-vacuous. We present a new end-to-end approach to contentful neural…Benchmarking Hierarchical Script Knowledge
Yonatan Bisk, Jan Buys, Karl Pichotta, Yejin ChoiNAACL • 2019 Understanding procedural language requires reasoning about both hierarchical and temporal relations between events. For example, “boiling pasta” is a sub-event of “making a pasta dish”, typically happens before “draining pasta,” and requires the use of…