摘要
基于span的联合抽取模型在实体和关系抽取(RE)任务中共享实体span的语义表示,能有效降低流水线模型带来的级联误差,但现有模型无法充分地将上下文信息融入实体和关系的表示中。针对上述问题,提出一个基于上下文语义增强的实体关系联合抽取(JERCE)模型。首先通过对比学习的方法获取句子级文本和实体间文本的语义特征表示;然后,将该表示加入实体和关系的表示中,对实体关系进行联合预测;最后,动态调整两个任务的损失以使联合模型的整体性能最优化。在公共数据集CoNLL04、ADE和ACE05上进行实验,结果显示JERCE模型与触发器感知记忆流框架(TriMF)相比,实体识别F1值分别提升了1.04、0.13和2.12个百分点,RE的F1值则分别提升了1.19、1.14和0.44个百分点。实验结果表明,JERCE模型可以充分获取上下文中的语义信息。
Span-based joint extraction model shares the semantic representation of entity spans in entity and Relation Extraction(RE)tasks,which effectively reduces the cascade error caused by pipeline models.However,the existing models cannot adequately integrate contextual information into the representation of entities and relations.To solve this problem,a Joint Entity and Relation extraction model based on Contextual semantic Enhancement(JERCE)was proposed.Firstly,the semantic feature representations of sentence-level text and inter-entity text were obtained by contrastive learning method.Then,the representations were added into the representations of entity and relation to predict entities and relations jointly.Finally,the loss values of the two tasks were adjusted dynamically to optimize the overall performance of the joint model.In experiments on public datasets CoNLL04,ADE and ACE05,compared with Trigger-sense Memory Flow framework(TriMF),the proposed JERCE model has the F1 scores of entity recognition improved by 1.04,0.13 and 2.12 percentage points respectively,and the F1 scores of RE increased by 1.19,1.14 and 0.44 percentage points respectively.Experimental results show that the JERCE model can fully obtain semantic information in context.
作者
雷景生
剌凯俊
杨胜英
吴怡
LEI Jingsheng;LA Kaijun;YANG Shengying;WU Yi(School of Information and Electronic Engineering,Zhejiang University of Science and Technology,Hangzhou Zhejiang 310023,China;Zhejiang Cancer Hospital,Hangzhou Zhejiang 310022,China)
出处
《计算机应用》
CSCD
北大核心
2023年第5期1438-1444,共7页
journal of Computer Applications
基金
国家自然科学基金资助项目(61972357)
浙江省重点研发计划项目(2019C03135)
浙江省医药卫生科技计划项目(2022KY104)。
关键词
命名实体识别
关系抽取
对比学习
文本span
加权损失
Named Entity Recognition(NER)
Relation Extraction(RE)
contrastive learning
text span
weighted loss