Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

3-2021

Abstract

Multi-hop Knowledge Base Question Answering (KBQA) aims to find the answer entities that are multiple hops away in the Knowledge Base (KB) from the entities in the question. A major challenge is the lack of supervision signals at intermediate steps. Therefore, multi-hop KBQA algorithms can only receive the feedback from the final answer, which makes the learning unstable or ineffective. To address this challenge, we propose a novel teacher-student approach for the multi-hop KBQA task. In our approach, the student network aims to find the correct answer to the query, while the teacher network tries to learn intermediate supervision signals for improving the reasoning capacity of the student network. The major novelty lies in the design of the teacher network, where we utilize both forward and backward reasoning to enhance the learning of intermediate entity distributions. By considering bidirectional reasoning, the teacher network can produce more reliable intermediate supervision signals, which can alleviate the issue of spurious reasoning. Extensive experiments on three benchmark datasets have demonstrated the effectiveness of our approach on the KBQA task.

Keywords

intermediate supervision signals, knowledge base question answering, teacher-student network

Discipline

Databases and Information Systems | Theory and Algorithms

Research Areas

Data Science and Engineering

Publication

WSDM '21: Proceedings of the 14th ACM International Conference on Web Search and Data Mining, March 8-12, Israel and Virtual

First Page

553

Last Page

561

ISBN

9781450382977

Identifier

10.1145/3437963.3441753

Publisher

ACM

City or Country

New York

Embargo Period

4-15-2021

Copyright Owner and License

LARC and Authors

Comments

The code is available at https://github.com/RichardHGL/WSDM2021_NSM

Additional URL

https://doi.org/10.1145/3437963.3441753

Share

COinS