English

Towards Interpretable Reasoning over Paragraph Effects in Situation

Computation and Language 2020-10-06 v1

Abstract

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 modules. In particular, five reasoning modules are designed and learned in an end-to-end manner, which leads to a more interpretable model. Experimental results on the ROPES dataset demonstrate the effectiveness and explainability of our proposed approach.

Keywords

Cite

@article{arxiv.2010.01272,
  title  = {Towards Interpretable Reasoning over Paragraph Effects in Situation},
  author = {Mucheng Ren and Xiubo Geng and Tao Qin and Heyan Huang and Daxin Jiang},
  journal= {arXiv preprint arXiv:2010.01272},
  year   = {2020}
}

Comments

14 pages. Accepted as EMNLP2020 Long paper

R2 v1 2026-06-23T18:59:33.327Z