Towards Interpretable Reasoning over Paragraph Effects in Situation

@article{Ren2020TowardsIR,
  title={Towards Interpretable Reasoning over Paragraph Effects in Situation},
  author={Mucheng Ren and Xiubo Geng and Tao Qin and He-yan Huang and Daxin Jiang},
  journal={ArXiv},
  year={2020},
  volume={abs/2010.01272}
}
  • Mucheng Ren, Xiubo Geng, +2 authors Daxin Jiang
  • Published 2020
  • Computer Science
  • ArXiv
  • We focus on the task of reasoning over paragraph effects in situation, which requires a model to understand the cause and effect described in a background paragraph, and apply the knowledge to a novel situation. Existing works ignore the complicated reasoning process and solve it with a one-step "black box" model. Inspired by human cognitive processes, in this paper we propose a sequential approach for this task which explicitly models each step of the reasoning process with neural network… CONTINUE READING

    Figures and Tables from this paper

    References

    SHOWING 1-10 OF 22 REFERENCES
    Reasoning Over Paragraph Effects in Situations
    • 26
    • Highly Influential
    • PDF
    Neural Module Networks for Reasoning over Text
    • 24
    • PDF
    HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
    • 359
    • PDF
    Heuristic and analytic processes in reasoning
    • 450
    Neural Module Networks
    • 544
    • PDF
    UnifiedQA: Crossing Format Boundaries With a Single QA System
    • 37
    • Highly Influential
    • PDF
    QuAC : Question Answering in Context
    • 242
    • PDF
    Evaluating NLP Models via Contrast Sets
    • 50
    • PDF
    ORB: An Open Reading Benchmark for Comprehensive Evaluation of Machine Reading Comprehension
    • 8
    • Highly Influential
    • PDF