MedRelNet:基于关系融合的中文医学文本实体关系联合抽取模型

MedRelNet:a joint model for entity-relation extraction in Chinese medical text based on relation fusion

盛西方 ¹赵俊东 ¹陶青川 ¹余艳梅¹

扫码查看

作者信息

1. 四川大学电子信息学院,成都 610065
折叠

摘要

为解决传统的实体关系抽取模型在中文医学文本上效果不佳的问题,提出了MedRelNet网络,采用多层次语义融合策略.MedRelNet的核心是新颖的关系融合模块(RelFuse),将关系信息融合到句子表示中,实现实体和关系的充分交互.同时,引入双向长短时记忆网络(BiLSTM),全面捕捉句子特征.实验结果显示,MedRelNet相对于基线模型在CMeIE中文医学数据集、DuIE和WebNLG通用数据集上分别取得了1.0、0.7和0.8个百分点的F1值提升,这不仅表明了MedRelNet在提取医学关系三元组方面的出色表现,还突显了其较强的泛化性能.

Abstract

To address the issue of traditional entity-relation extraction models performing poorly on Chinese medical texts,the MedRelNet model based on Onerel is proposed.The core of MedRelNet is a novel relation fusion module(RelFuse),which inte-grates relation information into sentence representations to enable thorough interactions between entities and relations.Addition-ally,it incorporates bidirectional Long Short-Term Memory networks(BiLSTM)to comprehensively capture sentence features.Ex-perimental results show that MedRelNet improves F1 scores by 1,0.7,and 0.8 percentage point over baseline models on the CMeIE,DuIE,and WebNLG datasets,especially excelling in handling complex scenarios involving multiple relations and entity overlaps.

关键词

BiLSTM/中文医学文本/实体关系抽取/知识图谱

Key words

BiLSTM/Chinese medical text/entity-relation extraction/knowledge graph

引用本文复制引用

出版年

2024

现代计算机

中大控股

现代计算机

影响因子：0.292

ISSN：1007-1423

段落导航