Abstract
Multi-hop reasoning approaches over knowledge graphs infer a missing relationship between entities with a multi-hop rule, which corresponds to a chain of relationships. We extend existing works to consider a generalized form of multi-hop rules, where each rule is a set of relation chains. To learn such generalized rules efficiently, we propose a two-step approach that first selects a small set of relation chains as a rule and then evaluates the confidence of the target relationship by jointly scoring the selected chains. A game-theoretical framework is proposed to this end to simultaneously optimize the rule selection and prediction steps. Empirical results show that our multi-chain multi-hop (MCMH) rules result in superior results compared to the standard single-chain approaches, justifying both our formulation of generalized rules and the effectiveness of the proposed learning framework.- Anthology ID:
- 2020.findings-emnlp.351
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2020
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Editors:
- Trevor Cohn, Yulan He, Yang Liu
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3948–3954
- Language:
- URL:
- https://aclanthology.org/2020.findings-emnlp.351
- DOI:
- 10.18653/v1/2020.findings-emnlp.351
- Cite (ACL):
- Lu Zhang, Mo Yu, Tian Gao, and Yue Yu. 2020. MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3948–3954, Online. Association for Computational Linguistics.
- Cite (Informal):
- MCMH: Learning Multi-Chain Multi-Hop Rules for Knowledge Graph Reasoning (Zhang et al., Findings 2020)
- PDF:
- https://preview.aclanthology.org/naacl24-info/2020.findings-emnlp.351.pdf
- Data
- NELL, NELL-995