Papers

Learn more about AI2's Lasting Impact Award
Viewing 1-10 of 144 papers
  • BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief

    Nora Kassner, Oyvind Tafjord, H. Schutze, P. ClarkEMNLP2021 Although pretrained language models (PTLMs) have been shown to contain significant amounts of world knowledge, they can still produce inconsistent answers to questions when probed, even after using specialized training techniques to reduce inconsistency. As a…
  • Explaining Answers with Entailment Trees

    Bhavana Dalvi, Peter A. Jansen, Oyvind Tafjord, Zhengnan Xie, Hannah Smith, Leighanna Pipatanangkura, Peter ClarkEMNLP2021 Our goal, in the context of open-domain textual question-answering (QA), is to explain answers by not just listing supporting textual evidence (“rationales”), but also showing how such evidence leads to the answer in a systematic way. If this could be done…
  • GooAQ: Open Question Answering with Diverse Answer Types

    Daniel Khashabi, Amos Ng, Tushar Khot, Ashish Sabharwal, Hanna Hajishirzi, Chris Callison-BurchFindings of EMNLP2021 While day-to-day questions come with a variety of answer types, the current questionanswering (QA) literature has failed to adequately address the answer diversity of questions. To this end, we present GOOAQ, a large-scale dataset with a variety of answer…
  • proScript: Partially Ordered Scripts Generation

    Keisuke Sakaguchi, Chandra Bhagavatula, R. L. Bras, Niket Tandon, P. Clark, Yejin ChoiFindings of EMNLP2021 Scripts standardized event sequences describing typical everyday activities have been shown to help understand narratives by providing expectations, resolving ambiguity, and filling in unstated information. However, to date they have proved hard to author or…
  • Ethical-Advice Taker: Do Language Models Understand Natural Language Interventions?

    Jieyu Zhao, Daniel Khashabi, Tushar Khot, Ashish Sabharwal and Kai-Wei Chang ACL-IJCNLP2021 Is it possible to use natural language to intervene in a model’s behavior and alter its prediction in a desired way? We investigate the effectiveness of natural language interventions for reading-comprehension systems, studying this in the context of social…
  • Investigating Transfer Learning in Multilingual Pre-trained Language Models through Chinese Natural Language Inference

    Hai Hu, He Zhou, Zuoyu Tian, Yiwen Zhang, Yina Ma, Yanting Li, Yixin Nie, Kyle RichardsonFindings of ACL2021 Multilingual transformers (XLM, mT5) have been shown to have remarkable transfer skills in zero-shot settings. Most transfer studies, however, rely on automatically translated resources (XNLI, XQuAD), making it hard to discern the particular linguistic…
  • ReadOnce Transformers: Reusable Representations of Text for Transformers

    Shih-Ting Lin, Ashish Sabharwal, Tushar KhotACL2021 While large-scale language models are extremely effective when directly fine-tuned on many end-tasks, such models learn to extract information and solve the task simultaneously from end-task supervision. This is wasteful, as the general problem of gathering…
  • Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies

    Mor Geva, Daniel Khashabi, Elad Segal, Tushar Khot, Dan Roth, Jonathan BerantTACL2021 A key limitation in current datasets for multi-hop reasoning is that the required steps for answering the question are mentioned in it explicitly. In this work, we introduce STRATEGYQA, a question answering (QA) benchmark where the required reasoning steps…
  • MuSiQue: Multi-hop Questions via Single-hop Question Composition

    H. Trivedi, Niranjan Balasubramanian, Tushar Khot, Ashish Sabharwal arXiv2021 To build challenging multi-hop question answering datasets, we propose a bottom-up semi-automatic process of constructing multihop question via composition of single-hop questions. Constructing multi-hop questions as composition of single-hop questions allows…
  • ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language

    Oyvind Tafjord, B. D. Mishra, P. ClarkFindings of ACL2021 Transformers have been shown to emulate logical deduction over natural language theories (logical rules expressed in natural language), reliably assigning true/false labels to candidate implications. However, their ability to generate implications of a theory…