Enhancing zero-shot relation extraction with a dual contrastive learning framework and a cross-attention module

• Published in: Complex & intelligent systems 2025-01, Vol.11 (1), p.42-15, Article 42
• Main Authors: Li, Diyou, Zhang, Lijuan, Huang, Jie, Xiong, Neal, Zhang, Lei, Wan, Jian
• Format: Article
• Language: English
• Subjects: Attention; Complexity; Computational Intelligence; Computer vision; Cross-attention network; Data integration; Data Structures and Information Theory; Dual contrastive learning; Engineering; Intelligent systems; Language; Learning; Modules; Natural language processing; Original Article; Semantics; Zero-shot relation extraction
• ISSN: 2199-4536; 2198-6053
• DOI: 10.1007/s40747-024-01642-6

Zero-shot relation extraction (ZSRE) is essential for improving the understanding of natural language relations and enhancing the accuracy and efficiency of natural language processing methods in practical applications. However, the existing ZSRE models ignore the importance of semantic information fusion and possess limitations when used for zero-shot relation extraction tasks. Thus, this paper proposes a dual contrastive learning framework and a cross-attention network module for ZSRE. First, our model designs a dual contrastive learning framework to compare the input sentences and relation descriptions from different perspectives; this process aims to achieve better separation between different relation categories in the representation space. Moreover, the cross-attention network of our model is introduced from the computer vision field to enhance the attention paid by the input instance to the relevant information of the relation description. The experimental results obtained on the Wiki-ZSL and FewRel datasets fully demonstrate the effectiveness of our approach.