Corpus ID: 199577708

Reasoning-Driven Question-Answering for Natural Language Understanding

@article{Khashabi2019ReasoningDrivenQF,
  title={Reasoning-Driven Question-Answering for Natural Language Understanding},
  author={Daniel Khashabi},
  journal={ArXiv},
  year={2019},
  volume={abs/1908.04926}
}
  • Daniel Khashabi
  • Published 2019
  • Computer Science
  • ArXiv
  • Natural language understanding (NLU) of text is a fundamental challenge in AI, and it has received significant attention throughout the history of NLP research. [...] Key Method We propose a formulation for abductive reasoning in natural language and show its effectiveness, especially in domains with limited training data. Additionally, to help reasoning systems cope with irrelevant or redundant information, we create a supervised approach to learn and detect the essential terms in questions. In the second…Expand Abstract

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 244 REFERENCES
    MCTest: A Challenge Dataset for the Open-Domain Machine Comprehension of Text
    • 453
    • Highly Influential
    • PDF
    BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
    • 10,068
    • Highly Influential
    • PDF
    SQuAD: 100, 000+ Questions for Machine Comprehension of Text
    • 2,160
    • PDF
    WikiQA: A Challenge Dataset for Open-Domain Question Answering
    • 449
    • PDF
    Bidirectional Attention Flow for Machine Comprehension
    • 1,146
    • PDF
    Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
    • 136
    • PDF
    Question Answering via Integer Programming over Semi-Structured Knowledge
    • 66
    • PDF