基于上下文共指实体依赖的文档级关系抽取  

Document Level Relationship Extraction Based on Context Coreference Entity De⁃pendence

作　　者：夏正新 苏翀 刘勇[4] XIA Zhengxin;SU Chong;LIU Yong(College of Continuing Education,Nanjing University of Posts and Telecommunications,Nanjing 210042,China;College of Management,Nanjing University of Posts and Telecommunications,Nanjing 210042,China;Engineering Research Center of Medicine Information,Nanjing University of Posts and Telecommunications,Nanjing 210042,China;College of Computer,Sichuan University,Chengdu 610065,China)

机构地区：[1]南京邮电大学继续教育学院,南京210042 [2]南京邮电大学管理学院,南京210042 [3]南京邮电大学医疗信息工程研究中心,南京210042 [4]四川大学计算机学院,成都610065

出　　处：《数据采集与处理》2023年第5期1226-1234,共9页Journal of Data Acquisition and Processing

摘　　要：文档级关系提取(Document relationship extraction,DRE)旨在多条句子中识别实体间的关系,而实体可能对应于跨越句子边界的多次提及,其中代词实体提及是因句子之间连接而普遍存在的语法现象,也是影响句子推理的一个重要因素。然而,以往的研究大多侧重于普通实体提及之间的关系,却很少关注代词实体提及的共指和关系捕获。本文提出了基于上下文共指实体依赖(Contextual coreference entity dependency,CCED)的文档级关系抽取模型,即通过融合普通实体和代词实体表示来构建共指实体依赖关系的上下文图结构,并在图上进行实体对间的全局交互推理,从而对实体关系的相互依赖进行建模。分别在公共数据集DocRED、DialogRE和MPDD上对CCED模型进行评估,结果显示在DocRED数据集上,与表现最好的基线模型DocuNet-BERT相比,CCED模型在测试集上的Ign F_(1)性能提高0.55%,F_(1)性能提高0.35%。在DialogRE和MPDD数据集上,与表现最好的基线模型COLN相比,CCED模型在DialogRE测试集上的F_(1)性能提高1.02%,在MPDD测试集上的ACC性能提高1.19%。实验结果验证了新模型对于文档级关系抽取的有效性。Document relationship extraction(DRE)is designed to identify the relationship between entities in multiple sentences,and entities may correspond to multiple mentions across sentence boundaries,in which the pronoun entity mention is a common grammatical phenomenon due to the connection between sentences,and is also an important factor affecting sentence reasoning.However,most of the previous studies focused on the relationship between common entity references,but paid little attention to the coreference and relational capture of pronoun entity references.Therefore,we propose a contextual coreference entity dependency(CCED)model,that is,by integrating common entity and pronoun entity representation to build a context graph structure of co-referring entity dependency,and carry out global interactive reasoning between entity pairs on the graph,so as to model the interdependence of entity relations.We evaluated the CCED model in the public datasets DocRED,DialogRE and MPDD,respectively.The results showed that the CCED model improved Ign F_(1) performance by 0.55%on the DocRED dataset compared with DocuNet-BERT,the best baseline model.And F_(1) score performance increased by 0.35%.In terms of the DialogRE and MPDD datasets,the CCED model improved F_(1) performance by 1.02%in DialogRE test sets and ACC performance by 1.19%in MPDD test sets compared with COLN,the best-performing baseline model.The experimental results verify the effectiveness of the new model for document-level relationship extraction.

关 键 词：关系提取 实体提及 共指消解 图推理 上下文图结构 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]