Complementary Evidence Identification in Open-Domain Question Answering

EACL

Cite Paper

Authors

Xiangyang Mou
Mo Yu
Shiyu Chang
Yufei Feng
Li Zhang
Hui Su

Published on

03/22/2021

Categories

EACL

This paper proposes a new problem of complementary evidence identification for open-domain question answering (QA). The problem aims to efficiently find a small set of passages that covers full evidence from multiple aspects as to answer a complex question. To this end, we proposes a method that learns vector representations of passages and models the sufficiency and diversity within the selected set, in addition to the relevance between the question and passages. Our experiments demonstrate that our method considers the dependence within the supporting evidence and significantly improves the accuracy of complementary evidence selection in QA domain.

This paper has been published at EACL 2021

Please cite our work using the BibTeX below.

@misc{mou2021complementary,
      title={Complementary Evidence Identification in Open-Domain Question Answering}, 
      author={Xiangyang Mou and Mo Yu and Shiyu Chang and Yufei Feng and Li Zhang and Hui Su},
      year={2021},
      eprint={2103.11643},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}