Repurposing Entailment for Multi-Hop Question Answering Tasks

@inproceedings{Trivedi2019RepurposingEF,
  title={Repurposing Entailment for Multi-Hop Question Answering Tasks},
  author={H. Trivedi and Heeyoung Kwon and Tushar Khot and A. Sabharwal and Niranjan Balasubramanian},
  booktitle={NAACL-HLT},
  year={2019}
}
  • H. Trivedi, Heeyoung Kwon, +2 authors Niranjan Balasubramanian
  • Published in NAACL-HLT 2019
  • Computer Science
  • Question Answering (QA) naturally reduces to an entailment problem, namely, verifying whether some text entails the answer to a question. [...] Key Method Multee uses (i) a local module that helps locate important sentences, thereby avoiding distracting information, and (ii) a global module that aggregates information by effectively incorporating importance weights. Importantly, we show that both modules can use entailment functions pre-trained on a large scale NLI datasets. We evaluate performance on MultiRC…Expand Abstract
    15 Citations
    Multi-hop Question Answering via Reasoning Chains
    • 17
    • PDF
    Unsupervised Alignment-based Iterative Evidence Retrieval for Multi-hop Question Answering
    • 2
    • PDF
    Looking Beyond Sentence-Level Natural Language Inference for Downstream Tasks
    Asking Crowdworkers to Write Entailment Examples: The Best of Bad Options
    Answer Ranking for Product-Related Questions via Multiple Semantic Relations Modeling
    • 3
    • PDF
    OCNLI: Original Chinese Natural Language Inference

    References

    SHOWING 1-10 OF 30 REFERENCES
    SciTaiL: A Textual Entailment Dataset from Science Question Answering
    • 159
    An Entailment-Based Approach to the QA4MRE Challenge
    • 12
    • Highly Influential
    • PDF
    Answering Science Exam Questions Using Query Rewriting with Background Knowledge
    • 5
    • PDF
    Constructing Datasets for Multi-hop Reading Comprehension Across Documents
    • 208
    • PDF
    Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
    • 149
    • PDF
    Question Answering by Reasoning Across Documents with Graph Convolutional Networks
    • 84
    • PDF
    Looking Beyond the Surface: A Challenge Set for Reading Comprehension over Multiple Sentences
    • 114
    • Highly Influential
    • PDF
    Methods for Using Textual Entailment in Open-Domain Question Answering
    • 221
    • PDF
    Improving Language Understanding by Generative Pre-Training
    • 1,540
    • PDF