Entity Linking Method for Chinese Short Texts with Multiple Embedded Representations

Abstract

Entity linking, a crucial task in the realm of natural language processing, aims to link entity mentions in a text to their corresponding entities in the knowledge base. While long documents provide abundant contextual information, facilitating feature extraction for entity identification and disambiguation, entity linking in Chinese short texts presents significant challenges. This study introduces an innovative approach to entity linking within Chinese short texts, combining multiple embedding representations. It integrates embedding representations from both entities and relations in the knowledge graph triples, as well as embedding representations from the descriptive text of entities and relations, to enhance the performance of entity linking. The method also incorporates external semantic supplements to strengthen the model’s feature learning capabilities. The Multi-Embedding Representation–Bidirectional Encoder Representation from Transformers–Bidirectional Gated Recurrent Unit (MER-BERT-BiGRU) neural network model is employed for embedding learning. The precision, recall, and F1 scores reached 89.73%, 92.18%, and 90.94% respectively, demonstrating the effectiveness of our approach.

Robust Chinese Short Text Entity Disambiguation Method Based on Feature Fusion and Contrastive Learning

“…Zhang et al [10] utilized features similar to those of twin networks to deeply analyze semantic relationships in texts and fully utilized the feature information of the texts to be disambiguated. Shi et al [11] combined multiple embedding representations for entity linking in Chinese short texts to improve the performance of entity linking.…”

“…Consequently, these methods struggle to effectively capture text features in short-text scenarios, resulting in a substantial decline in disambiguation performance. Additionally, current entity disambiguation approaches, especially for short-text disambiguation [10,11], heavily rely on a large volume of training samples to ensure model generalization and disambiguation effectiveness. However, acquiring sufficient data and conducting model training for various tasks can be costly in real-world applications.…”