一种基于span的实体和关系联合抽取方法  

A span-based joint entity and relation extraction method

作　　者：余杰[1] 纪斌 吴宏明 任意 李莎莎[1] 马俊[1] 吴庆波[1] YU Jie;JI Bin;WU Hong-ming;REN Yi;LI Sha-sha;MA Jun;WU Qing-bo(College of Computer Science and Technology,National University of Defense Technology,Changsha 410073;Equipment Project Management Center of Equipment Development Department,Central Military Commission,Beijing 100034;Project Management Center of Army,Beijing 100071,China)

机构地区：[1]国防科技大学计算机学院,湖南长沙410073 [2]中央军委装备发展部装备项目管理中心,北京100034 [3]陆军项目管理中心,北京100071

出　　处：《计算机工程与科学》2022年第3期502-508,共7页Computer Engineering & Science

摘　　要：基于span的联合抽取模型在命名实体识别和关系抽取上取得了优异的效果。这些模型将文本span作为候选实体,并将span元组视为候选关系元组。span的语义表示在实体识别和关系分类中共享。然而现有基于span的模型无法很好地捕获这些候选实体和关系的语义,为了解决这些问题,提出了一种融合attention机制的span的联合抽取模型。特别地,attention用于计算相关语义表示,包括span特定特征语义表示和句子上下文的语义表示。实验结果表明,所提出的模型优于以前的模型,并在ACE2005、CoNLL2004和ADE 3个基准数据集上达到了当前最优的结果。Span-based joint extraction models have achieved excellent results in named entity recognition and relation extraction.These models regard text spans as candidate entities and span tuples as candidate relation tuples.span semantic representations are shared in both entity recognition and relation extraction,while existing models cannot well capture semantics of these candidate entities and relations.To address these problems,a span-based joint extraction framework with attention-based semantic re-presentations is proposed.Specially,attentions are utilized to calculate semantic representations,includ-ing span-specific and contextual ones.Experiments show that our model outperforms previous systems and achieves state-of-the-art results on ACE2005,CoNLL2004 and ADE.

关 键 词：SPAN 实体识别 关系抽取 联合抽取 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]