English

Reference Knowledgeable Network for Machine Reading Comprehension

Computation and Language 2022-03-29 v3 Artificial Intelligence

Abstract

Multi-choice Machine Reading Comprehension (MRC) as a challenge requires models to select the most appropriate answer from a set of candidates with a given passage and question. Most of the existing researches focus on the modeling of specific tasks or complex networks, without explicitly referring to relevant and credible external knowledge sources, which are supposed to greatly make up for the deficiency of the given passage. Thus we propose a novel reference-based knowledge enhancement model called Reference Knowledgeable Network (RekNet), which simulates human reading strategies to refine critical information from the passage and quote explicit knowledge in necessity. In detail, RekNet refines finegrained critical information and defines it as Reference Span, then quotes explicit knowledge quadruples by the co-occurrence information of Reference Span and candidates. The proposed RekNet is evaluated on three multi-choice MRC benchmarks: RACE, DREAM and Cosmos QA, obtaining consistent and remarkable performance improvement with observable statistical significance level over strong baselines. Our code is available at https://github.com/Yilin1111/RekNet.

Keywords

Cite

@article{arxiv.2012.03709,
  title  = {Reference Knowledgeable Network for Machine Reading Comprehension},
  author = {Yilin Zhao and Zhuosheng Zhang and Hai Zhao},
  journal= {arXiv preprint arXiv:2012.03709},
  year   = {2022}
}

Comments

Accepted by TASLP 2022

R2 v1 2026-06-23T20:46:55.231Z