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 methods
|Original language||English (US)|
|Title of host publication||Findings of the Association for Computational Linguistics: EMNLP 2020|
|Publisher||Association for Computational Linguistics (ACL)|
|State||Published - 2020|
Bibliographical noteKAUST Repository Item: Exported on 2021-04-14
Acknowledgements: 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.