Entity Linking Model Based on Cascading Attention and Dynamic Graph
Electronics · 28.09.2024 · 13 (19) · 3845
DOI: 10.3390/electronics13193845 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 28.09.2024. Verfasst von Hongchan Li und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Research and Development Special Project of Henan Province of China, Science and Technology Breakthrough Project of Henan Province of China, Key Science Research Project of Colleges and Universities in Henan Province of China.
Abstract (Originalsprache)
The purpose of entity linking is to connect entity mentions in text to real entities in the knowledge base. Existing methods focus on using the text topic, entity type, linking order, and association between entities to obtain the target entities. Although these methods have achieved good results, they ignore the exploration of candidate entities, leading to insufficient semantic information among entities. In addition, the implicit relationship and discrimination within the candidate entities also affect the accuracy of entity linking. To address these problems, we introduce information about candidate entities from Wikipedia and construct a graph model to capture implicit dependencies between different entity decisions. Specifically, we propose a cascade attention mechanism and develop a novel local entity linkage model termed CAM-LEL. This model leverages the interaction between entity mentions and candidate entities to enhance the semantic representation of entities. Furthermore, a global entity linkage model termed DG-GEL based on a dynamic graph is established to construct an entity association graph, and a random walking algorithm and entity entropy are used to extract the implicit relationships within entities to increase the differentiation between entities. Experimental results and in-depth analyses of multiple datasets show that our model outperforms other state-of-the-art models.
Förderung
- Key Research and Development Special Project of Henan Province of China
- Science and Technology Breakthrough Project of Henan Province of China
- Key Science Research Project of Colleges and Universities in Henan Province of China
- Zhengzhou Innovation Entrepreneurship Team (Innovation Leadership Team) Project of Henan Province of China
Zitieren
APA
Li, H., Li, C., Sun, Z., & Zhu, H. (2024). Entity Linking Model Based on Cascading Attention and Dynamic Graph. Electronics, 13(19), 3845. https://doi.org/10.3390/electronics13193845
Vancouver
Li H, Li C, Sun Z, Zhu H. Entity Linking Model Based on Cascading Attention and Dynamic Graph. Electronics. 2024;13(19):3845. doi:10.3390/electronics13193845
BibTeX
@article{Li2024,
author = {Li, Hongchan and Li, Chunlei and Sun, Zhongchuan and Zhu, Haodong},
title = {Entity Linking Model Based on Cascading Attention and Dynamic Graph},
journal = {Electronics},
year = {2024},
volume = {13},
number = {19},
pages = {3845},
doi = {10.3390/electronics13193845}
}
EUVIMED