Abstract | ||
---|---|---|
Multihop knowledge reasoning aims to find missing entities for incomplete triples by finding paths on knowledge graphs. It is a fundamental and important task. In this article, we devise a hierarchical reinforcement learning algorithm to model the reasoning process more effectively. Unlike existing methods directly reason on entities and relations, we adopt a high-level reasoning layer to deal wit... |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/MIS.2021.3095055 | IEEE Intelligent Systems |
Keywords | DocType | Volume |
Cognition,Reinforcement learning,Intelligent systems,Concrete,Task analysis,Computational modeling,Training | Journal | 37 |
Issue | ISSN | Citations |
1 | 1541-1672 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zikang Wang | 1 | 0 | 0.34 |
Linjing Li | 2 | 39 | 12.91 |
Daniel Zeng | 3 | 2539 | 286.59 |