A Copy-Augmented Generative Model for Open-Domain Question Answering

Shuang Liu, Dong Wang, Xiaoguang Li, Minghui Huang, Meizhen Ding


Abstract
Open-domain question answering is a challenging task with a wide variety of practical applications. Existing modern approaches mostly follow a standard two-stage paradigm: retriever then reader. In this article, we focus on improving the effectiveness of the reader module and propose a novel copy-augmented generative approach that integrates the merits of both extractive and generative readers. In particular, our model is built upon the powerful generative model FiD (CITATION). We enhance the original generative reader by incorporating a pointer network to encourage the model to directly copy words from the retrieved passages. We conduct experiments on the two benchmark datasets, Natural Questions and TriviaQA, and the empirical results demonstrate the performance gains of our proposed approach.
Anthology ID:
2022.acl-short.47
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
435–441
Language:
URL:
https://aclanthology.org/2022.acl-short.47
DOI:
10.18653/v1/2022.acl-short.47
Bibkey:
Cite (ACL):
Shuang Liu, Dong Wang, Xiaoguang Li, Minghui Huang, and Meizhen Ding. 2022. A Copy-Augmented Generative Model for Open-Domain Question Answering. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 435–441, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
A Copy-Augmented Generative Model for Open-Domain Question Answering (Liu et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-short.47.pdf
Data
Natural QuestionsTriviaQA