Type
Conference PaperKAUST Department
Computer Science ProgramComputer, Electrical and Mathematical Science and Engineering (CEMSE) Division
Date
2020Permanent link to this record
http://hdl.handle.net/10754/667823
Metadata
Show full item recordAbstract
Multi-hop relation reasoning over knowledge base is to generate effective and interpretable relation prediction through reasoning paths. The current methods usually require sufficient training data (fact triples) for each query relation, impairing their performances over few-shot relations (with limited triples) which are common in knowledge base. To this end, we propose FIRE, a novel few-shot multi-hop relation learning model. FIRE applies reinforcement learning to model the sequential steps of multi-hop reasoning, besides performs heterogeneous structure encoding and knowledge-aware search space pruning. The meta-learning technique is employed to optimize model parameters that could quickly adapt to few-shot relations. Empirical study on two datasets demonstrate that FIRE outperforms state-of-the-art methodsCitation
Zhang, C., Yu, L., Saebi, M., Jiang, M., & Chawla, N. (2020). Few-Shot Multi-Hop Relation Reasoning over Knowledge Bases. Findings of the Association for Computational Linguistics: EMNLP 2020. doi:10.18653/v1/2020.findings-emnlp.51Sponsors
This work was supported in part by National Science Foundation grants CCI-1925607 and IIS1849816. We also thank the anonymous reviewers for their valuable comments and helpful suggestions.Conference/Event name
Association for Computational LinguisticsAdditional Links
https://www.aclweb.org/anthology/2020.findings-emnlp.51ae974a485f413a2113503eed53cd6c53
10.18653/v1/2020.findings-emnlp.51