Reasoning machine reading comprehension (R-MRC) aims to answer complex questions that require discrete reasoning based on text. To support discrete reasoning, evidence, typically the concise textual fragments that describe question-related facts, including topic entities and attribute values, are crucial clues from question to answer. However, previous end-to-end methods that achieve state-of-the-art performance rarely solve the problem by paying enough emphasis on the modeling of evidence, missing the opportunity to further improve the model's reasoning ability for R-MRC. To alleviate the above issue, in this paper, we propose an evidence-emphasized discrete reasoning approach (EviDR), in which sentence and clause level evidence is first detected based on distant supervision, and then used to drive a reasoning module implemented with a relational heterogeneous graph convolutional network to derive answers. Extensive experiments are conducted on DROP (discrete reasoning over paragraphs) dataset, and the results demonstrate the effectiveness of our proposed approach. In addition, qualitative analysis verifies the capability of the proposed evidence-emphasized discrete reasoning for R-MRC.
@article{arxiv.2108.07994,
title = {EviDR: Evidence-Emphasized Discrete Reasoning for Reasoning Machine Reading Comprehension},
author = {Yongwei Zhou and Junwei Bao and Haipeng Sun and Jiahui Liang and Youzheng Wu and Xiaodong He and Bowen Zhou and Tiejun Zhao},
journal= {arXiv preprint arXiv:2108.07994},
year = {2021}
}