End-to-End Entity Linking with Hierarchical Reinforcement Learning
DOI:
https://doi.org/10.1609/aaai.v37i4.25534Keywords:
DMKM: Linked Open Data, Knowledge Graphs & KB Completion, ML: Reinforcement Learning Algorithms, SNLP: Learning & Optimization for SNLPAbstract
Entity linking (EL) is the task of linking the text segments to the referring entities in the knowledge graph, typically decomposed into mention detection, and entity disambiguation. Compared to traditional methods treating the two tasks separately, recent end-to-end entity linking methods exploit the mutual dependency between mentions and entities to achieve better performance. However, existing end-to-end EL methods have problems utilizing the dependency of mentions and entities in the task. To this end, we propose to model the EL task as a hierarchical decision-making process and design a hierarchical reinforcement learning algorithm to solve the problem. We conduct extensive experiments to show that the proposed method achieves state-of-the-art performance in several EL benchmark datasets. Our code is publicly available at https://github.com/lhlclhl/he2eel.Downloads
Published
2023-06-26
How to Cite
Chen, L., Zhu, T., Liu, J., Liang, J., & Xiao, Y. (2023). End-to-End Entity Linking with Hierarchical Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 37(4), 4173-4181. https://doi.org/10.1609/aaai.v37i4.25534
Issue
Section
AAAI Technical Track on Data Mining and Knowledge Management