•  
  •  
 

Scientific Information Research

Keywords

named entity recognition， BERT， boundary-aware， GAT， syntax enhancement

Abstract

[Purpose/significance]This study addresses the issue of inadequate perception of entity boundaries in traditional character-level modeling-based named entity recognition models by integrating syntax information containing entity boundary features into the task using a multi-head graph attention network with dense connections. This integration enhances the effectiveness of named entity recognition. [Method/process]This study proposes a Syntax-enhanced Boundary-aware Named Entity Recognition Model (SynBNER), which utilizes BERT for text semantic representation and integrates syntax information using a dense-connected graph attention network. This integration incorporates implicit entity boundary information from syntax information into word representations, thereby enhancing the model's entity boundary perception capability. [Result/conclusion]Empirical studies are conducted on the ACE2005, MSRA, and People's Daily datasets, the F1 scores of the SynBNER model are respectively 86.11%, 96.03%, and 95.81%. The experimental results demonstrate that the method of enhancing entity boundary awareness with syntax information can significantly improve the effectiveness of named entity recognition.

Digital Object Identifier (DOI)

10.19809/j.cnki.kjqbyj.2025.03.002

Download

Share

COinS