Papers

Learn more about AI2's Lasting Impact Award
Viewing 21-30 of 55 papers
  • IIRC: A Dataset of Incomplete Information Reading Comprehension Questions

    James Ferguson, Matt Gardner. Hannaneh Hajishirzi, Tushar Khot, Pradeep DasigiEMNLP2020 Humans often have to read multiple documents to address their information needs. However, most existing reading comprehension (RC) tasks only focus on questions for which the contexts provide all the information required to answer them, thus not evaluating a…
  • Improving Compositional Generalization in Semantic Parsing

    Inbar Oren, Jonathan Herzig, Nitish Gupta, Matt Gardner, Jonathan BerantFindings of EMNLP2020 Generalization of models to out-of-distribution (OOD) data has captured tremendous attention recently. Specifically, compositional generalization, i.e., whether a model generalizes to new structures built of components observed during training, has sparked…
  • Is Multihop QA in DiRe Condition? Measuring and Reducing Disconnected Reasoning

    H. Trivedi, N. Balasubramanian, Tushar Khot, A. SabharwalEMNLP2020 Has there been real progress in multi-hop question-answering? Models often exploit dataset artifacts to produce correct answers, without connecting information across multiple supporting facts. This limits our ability to measure true progress and defeats the…
  • Learning from Task Descriptions

    Orion Weller, Nick Lourie, Matt Gardner, Matthew PetersEMNLP2020 Typically, machine learning systems solve new tasks by training on thousands of examples. In contrast, humans can solve new tasks by reading some instructions, with perhaps an example or two. To take a step toward closing this gap, we introduce a framework…
  • Learning to Explain: Datasets and Models for Identifying Valid Reasoning Chains in Multihop Question-Answering.

    Harsh Jhamtani, P. ClarkEMNLP2020 Despite the rapid progress in multihop question-answering (QA), models still have trouble explaining why an answer is correct, with limited explanation training data available to learn from. To address this, we introduce three explanation datasets in which…
  • MedICaT: A Dataset of Medical Images, Captions, and Textual References

    Sanjay Subramanian, Lucy Lu Wang, Sachin Mehta, Ben Bogin, Madeleine van Zuylen, Sravanthi Parasa, Sameer Singh, Matt Gardner, Hannaneh HajishirziFindings of EMNLP2020 Understanding the relationship between figures and text is key to scientific document understanding. Medical figures in particular are quite complex, often consisting of several subfigures (75% of figures in our dataset), with detailed text describing their…
  • MOCHA: A Dataset for Training and Evaluating Generative Reading Comprehension Metrics

    Anthony Chen, Gabriel Stanovsky, S. Singh, Matt GardnerEMNLP2020 Posing reading comprehension as a generation problem provides a great deal of flexibility, allowing for open-ended questions with few restrictions on possible answers. However, progress is impeded by existing generation metrics, which rely on token overlap…
  • More Bang for Your Buck: Natural Perturbation for Robust Question Answering

    Daniel Khashabi, Tushar Khot, Ashish SabharwalEMNLP2020 While recent models have achieved human-level scores on many NLP datasets, we observe that they are considerably sensitive to small changes in input. As an alternative to the standard approach of addressing this issue by constructing training sets of…
  • Multilevel Text Alignment with Cross-Document Attention

    Xuhui Zhou, Nikolaos Pappas, Noah A. SmithEMNLP2020 Text alignment finds application in tasks such as citation recommendation and plagiarism detection. Existing alignment methods operate at a single, predefined level and cannot learn to align texts at, for example, sentence and document levels. We propose a…
  • Multi-Step Inference for Reasoning over Paragraphs

    Jiangming Liu, Matt Gardner, Shay B. Cohen, Mirella LapataEMNLP2020 Complex reasoning over text requires understanding and chaining together free-form predicates and logical connectives. Prior work has largely tried to do this either symbolically or with black-box transformers. We present a middle ground between these two…