Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering

Jing Zhang, Xiaokang Zhang, Jifan Yu, Jian Tang, Jie Tang, Cuiping Li, Hong Chen


Abstract
Recent works on knowledge base question answering (KBQA) retrieve subgraphs for easier reasoning. The desired subgraph is crucial as a small one may exclude the answer but a large one might introduce more noises. However, the existing retrieval is either heuristic or interwoven with the reasoning, causing reasoning on the partial subgraphs, which increases the reasoning bias when the intermediate supervision is missing. This paper proposes a trainable subgraph retriever (SR) decoupled from the subsequent reasoning process, which enables a plug-and-play framework to enhance any subgraph-oriented KBQA model. Extensive experiments demonstrate SR achieves significantly better retrieval and QA performance than existing retrieval methods. Via weakly supervised pre-training as well as the end-to-end fine-tuning, SR achieves new state-of-the-art performance when combined with NSM (He et al., 2021), a subgraph-oriented reasoner, for embedding-based KBQA methods. Codes and datasets are available online (https://github.com/RUCKBReasoning/SubgraphRetrievalKBQA)
Anthology ID:
2022.acl-long.396
Original:
2022.acl-long.396v1
Version 2:
2022.acl-long.396v2
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long 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:
5773–5784
Language:
URL:
https://aclanthology.org/2022.acl-long.396
DOI:
10.18653/v1/2022.acl-long.396
Bibkey:
Cite (ACL):
Jing Zhang, Xiaokang Zhang, Jifan Yu, Jian Tang, Jie Tang, Cuiping Li, and Hong Chen. 2022. Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5773–5784, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Subgraph Retrieval Enhanced Model for Multi-hop Knowledge Base Question Answering (Zhang et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.396.pdf
Code
 ruckbreasoning/subgraphretrievalkbqa