What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering

  title={What's Missing: A Knowledge Gap Guided Approach for Multi-hop Question Answering},
  author={Tushar Khot and A. Sabharwal and P. Clark},
  • Tushar Khot, A. Sabharwal, P. Clark
  • Published 2019
  • Computer Science
  • ArXiv
  • Multi-hop textual question answering requires combining information from multiple sentences. [...] Key Method The model, GapQA, learns to fill this gap by determining the relationship between the span and an answer choice, based on retrieved knowledge targeting this gap. We propose jointly training a model to simultaneously fill this knowledge gap and compose it with the provided partial knowledge. On the OpenBookQA dataset, given partial knowledge, explicitly identifying what's missing substantially…Expand Abstract
    10 Citations

    Figures, Tables, and Topics from this paper.

    QASC: A Dataset for Question Answering via Sentence Composition
    • 29
    • PDF
    Knowledge Fusion and Semantic Knowledge Ranking for Open Domain Question Answering
    • 6
    • Highly Influenced
    • PDF
    Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering
    • 2
    • Highly Influenced
    • PDF
    A Survey on Explainability in Machine Reading Comprehension
    • 1
    • PDF


    Constructing Datasets for Multi-hop Reading Comprehension Across Documents
    • 209
    • Highly Influential
    • PDF
    Careful Selection of Knowledge to Solve Open Book Question Answering
    • 19
    • PDF
    Improving Question Answering with External Knowledge
    • 22
    • PDF
    HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
    • 316
    • PDF
    Understanding Dataset Design Choices for Multi-hop Reasoning
    • 34
    • PDF
    Combining Natural Logic and Shallow Reasoning for Question Answering
    • 16
    • PDF
    Question Answering via Integer Programming over Semi-Structured Knowledge
    • 71
    • PDF
    Semantic Parsing on Freebase from Question-Answer Pairs
    • 982
    • PDF
    Looking Beyond the Surface: A Challenge Set for Reading Comprehension over Multiple Sentences
    • 114
    • Highly Influential
    • PDF
    Compositional Semantic Parsing on Semi-Structured Tables
    • 261
    • PDF