计算机应用与软件2025，Vol.42Issue(4)：122-128,134,8.DOI:10.3969/j.issn.1000-386x.2025.04.019
基于GCN的异构句法驱动汉语语义角色标注
HETEROGENEOUS SYNTAX-AWARE SEMANTIC ROLE LABELING BASED ON GRAPH CONVOLUTIONAL NETWORKS
摘要
Abstract
Recently,syntax-aware neural semantic role labeling(SRL)has received much attention.However,most of previous syntax-aware SRL works exploit homogeneous syntactic knowledge from a single syntactic treebank.Considering several high-quality publicly available Chinese syntactic treebanks,this paper proposes to extend graph convolutional networks(GCNs)for encoding heterogeneous syntactic knowledge in the heterogeneous dependency trees and makes a through comparison on various encoding methods to improve SRL performance.This model achieved 84.16 and 85.30 F1 on CPB 1.0 and CONLL-2009 Chinese data sets,respectively,both outperforming the corresponding homogeneous syntax-aware SRL models and significantly improving the performance of previous methods.关键词
语义角色标注/异构句法树库/图卷积网络Key words
Semantic role labeling/Heterogeneous dependency treebanks/GCNs分类
信息技术与安全科学引用本文复制引用
杨浩苹,夏庆荣,李正华,王睿..基于GCN的异构句法驱动汉语语义角色标注[J].计算机应用与软件,2025,42(4):122-128,134,8.基金项目
国家自然科学基金项目(61876116). （61876116）
