Papers
See AI2's Award Winning Papers
Learn more about AI2's Lasting Impact Award
Viewing 141-150 of 214 papers
Discourse-Aware Neural Rewards For Coherent Text Generation
Antoine Bosselut, Asli Celikyilmaz, Xiaodong He, Jianfeng Gao, Po-Sen Huang and Yejin ChoiNAACL • 2018 In this paper, we investigate the use of discourse-aware rewards with reinforcement learning to guide a model to generate long, coherent text. In particular, we propose to learn neural rewards to model cross-sentence ordering as a means to approximate desired…Natural Language to Structured Query Generation via Meta-Learning
Po-Sen Huang, Chenglong Wang, Rishabh Singh, Wen-tau Yih, Xiaodong HeNAACL • 2018 In conventional supervised training, a model is trained to fit all the training examples. However, having a monolithic model may not always be the best strategy, as examples could vary widely. In this work, we explore a different learning protocol that treats…Tracking State Changes in Procedural Text: A Challenge Dataset and Models for Process Paragraph Comprehension
Bhavana Dalvi, Lifu Huang, Niket Tandon, Wen-tau Yih, Peter ClarkNAACL • 2018 We present a new dataset and models for comprehending paragraphs about processes (e.g., photosynthesis), an important genre of text describing a dynamic world. The new dataset, ProPara, is the first to contain natural (rather than machine-generated) text…VISIR: Visual and Semantic Image Label Refinement
Sreyasi Nag Chowdhury, Niket Tandon, Hakan Ferhatosmanoglu, Gerhard WeikumWSDM • 2018 The social media explosion has populated the Internet with a wealth of images. There are two existing paradigms for image retrieval: 1)content-based image retrieval (BIR), which has traditionally used visual features for similarity search (e.g., SIFT features…What Happened? Leveraging VerbNet to Predict the Effects of Actions in Procedural Text
Peter Clark, Bhavana Dalvi, Niket TandonarXiv • 2018 Our goal is to answer questions about paragraphs describing processes (e.g., photosynthesis). Texts of this genre are challenging because the effects of actions are often implicit (unstated), requiring background knowledge and inference to reason about the…Knowledge Completion for Generics Using Guided Tensor Factorization
Hanie Sedghi and Ashish SabharwalTACL • 2018 Given a knowledge base or KB containing (noisy) facts about common nouns or generics, such as "all trees produce oxygen" or "some animals live in forests", we consider the problem of inferring additional such facts at a precision similar to that of the…Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
Peter Clark, Isaac Cowhey, Oren Etzioni, Tushar Khot, Ashish Sabharwal, Carissa Schoenick, Oyvind TafjordarXiv • 2018 We present a new question set, text corpus, and baselines assembled to encourage AI research in advanced question answering. Together, these constitute the AI2 Reasoning Challenge (ARC), which requires far more powerful knowledge and reasoning than previous…Approximate Inference via Weighted Rademacher Complexity
Jonathan Kuck, Ashish Sabharwal, and Stefano ErmonAAAI • 2018 Rademacher complexity is often used to characterize the learnability of a hypothesis class and is known to be related to the class size. We leverage this observation and introduce a new technique for estimating the size of an arbitrary weighted set, defined…Question Answering as Global Reasoning over Semantic Abstractions
Daniel Khashabi, Tushar Khot, Ashish Sabharwal, and Dan RothAAAI • 2018 We propose a novel method for exploiting the semantic structure of text to answer multiple-choice questions. The approach is especially suitable for domains that require reasoning over a diverse set of linguistic constructs but have limited training data. To…SciTail: A Textual Entailment Dataset from Science Question Answering
Tushar Khot, Ashish Sabharwal, and Peter ClarkAAAI • 2018 We present a new dataset and model for textual entailment, derived from treating multiple-choice question-answering as an entailment problem. SCITAIL is the first entailment set that is created solely from natural sentences that already exist independently…