Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 131-140 of 214 papers
QASC: A Dataset for Question Answering via Sentence Composition
Tushar Khot, Peter Clark, Michal Guerquin, Paul Edward Jansen, Ashish Sabharwal AAAI • 2019 Composing knowledge from multiple pieces of texts is a key challenge in multi-hop question answering. We present a multi-hop reasoning dataset, Question Answering via Sentence Composition (QASC), that requires retrieving facts from a large corpus and…QuaRel: A Dataset and Models for Answering Questions about Qualitative Relationships
Oyvind Tafjord, Peter Clark, Matt Gardner, Wen-tau Yih, Ashish SabharwalAAAI • 2019 Many natural language questions require recognizing and reasoning with qualitative relationships (e.g., in science, economics, and medicine), but are challenging to answer with corpus-based methods. Qualitative modeling provides tools that support such…On the Capabilities and Limitations of Reasoning for Natural Language Understanding
Daniel Khashabi, Erfan Sadeqi Azer, Tushar Khot, Ashish Sabharwal, Dan RotharXiv • 2019 Recent systems for natural language understanding are strong at overcoming linguistic variability for lookup style reasoning. Yet, their accuracy drops dramatically as the number of reasoning steps increases. We present the first formal framework to study…Expanding Holographic Embeddings for Knowledge Completion
Yexiang Xue, Yang Yuan, Zhitian Xu, Ashish SabharwalNeurIPS • 2018 Neural models operating over structured spaces such as knowledge graphs require a continuous embedding of the discrete elements of this space (such as entities) as well as the relationships between them. Relational embeddings with high expressivity, however…Bridging Knowledge Gaps in Neural Entailment via Symbolic Models
Dongyeop Kang, Tushar Khot, Ashish Sabharwal and Peter ClarkEMNLP • 2018 Most textual entailment models focus on lexical gaps between the premise text and the hypothesis, but rarely on knowledge gaps. We focus on filling these knowledge gaps in the Science Entailment task, by leveraging an external structured knowledge base (KB…Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
Todor Mihaylov, Peter Clark, Tushar Khot, Ashish SabharwalEMNLP • 2018 We present a new kind of question answering dataset, OpenBookQA, modeled after open book exams for assessing human understanding of a subject. The open book that comes with our questions is a set of 1329 elementary level science facts. Roughly 6000 questions…Reasoning about Actions and State Changes by Injecting Commonsense Knowledge
Niket Tandon, Bhavana Dalvi Mishra, Joel Grus, Wen-tau Yih, Antoine Bosselut, Peter ClarkEMNLP • 2018 Comprehending procedural text, e.g., a paragraph describing photosynthesis, requires modeling actions and the state changes they produce, so that questions about entities at different timepoints can be answered. Although several recent systems have shown…Adaptive Stratified Sampling for Precision-Recall Estimation
Ashish Sabharwal, Yexiang XueUAI • 2018 We propose a new algorithm for computing a constant-factor approximation of precision-recall (PR) curves for massive noisy datasets produced by generative models. Assessing validity of items in such datasets requires human annotation, which is costly and must…Adversarial Training for Textual Entailment with Knowledge-Guided Examples
Tushar Khot, Ashish Sabharwal and Dongyeop KangACL • 2018 We consider the problem of learning textual entailment models with limited supervision (5K-10K training examples), and present two complementary approaches for it. First, we propose knowledge-guided adversarial example generators for incorporating large…Deep Communicating Agents For Abstractive Summarization
Asli Celikyilmaz, Antoine Bosselut, Xiaodong He and Yejin ChoiNAACL • 2018 We present deep communicating agents in an encoder-decoder architecture to address the challenges of representing a long document for abstractive summarization. With deep communicating agents, the task of encoding a long text is divided across multiple…