KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering

Donghan Yu, Chenguang Zhu, Yuwei Fang, Wenhao Yu, Shuohang Wang, Yichong Xu, Xiang Ren, Yiming Yang, Michael Zeng


Abstract
Current Open-Domain Question Answering (ODQA) models typically include a retrieving module and a reading module, where the retriever selects potentially relevant passages from open-source documents for a given question, and the reader produces an answer based on the retrieved passages. The recently proposed Fusion-in-Decoder (FiD) framework is a representative example, which is built on top of a dense passage retriever and a generative reader, achieving the state-of-the-art performance. In this paper we further improve the FiD approach by introducing a knowledge-enhanced version, namely KG-FiD. Our new model uses a knowledge graph to establish the structural relationship among the retrieved passages, and a graph neural network (GNN) to re-rank the passages and select only a top few for further processing. Our experiments on common ODQA benchmark datasets (Natural Questions and TriviaQA) demonstrate that KG-FiD can achieve comparable or better performance in answer prediction than FiD, with less than 40% of the computation cost.
Anthology ID:
2022.acl-long.340
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4961–4974
Language:
URL:
https://aclanthology.org/2022.acl-long.340
DOI:
10.18653/v1/2022.acl-long.340
Bibkey:
Cite (ACL):
Donghan Yu, Chenguang Zhu, Yuwei Fang, Wenhao Yu, Shuohang Wang, Yichong Xu, Xiang Ren, Yiming Yang, and Michael Zeng. 2022. KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4961–4974, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answering (Yu et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.340.pdf
Video:
 https://aclanthology.org/2022.acl-long.340.mp4
Data
Natural QuestionsTriviaQA