基于局部增强的中文医疗命名实体识别模型  

Chinese medical named entity recognition model based on local enhancement

作　　者：陈晶 邢珂萱 孟伟伦 郭景峰[3] 冯建周[3] CHEN Jing;XING Kexuan;MENG Weilun;GUO Jingfeng;FENG Jianzhou(College of Mathematics and Computer Science,Guangdong Ocean University,Zhanjiang 524088,China;The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province,Qinhuangdao 066004,China;College of Information Science and Engineering,Yanshan University,Qinhuangdao 066004,China)

机构地区：[1]广东海洋大学数学与计算机学院,广东湛江524088 [2]河北省计算机虚拟技术与系统集成重点实验室,河北秦皇岛066004 [3]燕山大学信息科学与工程学院,河北秦皇岛066004

出　　处：《通信学报》2024年第7期171-183,共13页Journal on Communications

基　　金：国家自然科学基金资助项目(No.62172352,No.42306218);中央省部共建基金资助项目(No.226Z0102G,No.226Z0305G);广东海洋大学科研启动基金资助项目(No.060302102304)。

摘　　要：医学实体的识别往往受到其相邻上下文的影响,目前的命名实体识别方法通常依赖于BiLSTM捕捉文本中的全局依赖关系,缺乏对字符之间局部依赖关系的建模。针对这一问题,提出了一种基于局部增强的中文医疗命名实体识别模型LENER。首先,LENER使用包括字音、字形和语义在内的多源信息来丰富底层字符表征。然后,结合相对位置编码对滑动窗口划分出的序列片段进行局部注意力计算,并通过非线性计算融合局部信息和BiLSTM得到的全局信息。最后,对识别出的实体头部和尾部进行组合,进而提取出实体。实验结果表明,LENER模型具有良好的实体识别能力,与其他模型相比,LENER模型的F1值提升了0.5%~2.0%。In the medical field,the recognition of medical entities is often influenced by their adjacent context,the current named entity recognition methods typically rely on BiLSTM to capture the global dependency relationships within text,lacking modeling of local dependencies between characters.To resolve this problem,a Chinese medical named entity recognition model LENER based on local enhancement was proposed.Firstly,the representation of characters was enriched by LENER utilizing multi-source information,including phonetic,graphic and semantic features.Secondly,relative position encoding was combined to perform local attention calculations on sequence segments divided by sliding windows,and local information was fused with global information obtained from BiLSTM through nonlinear computation.Finally,the recognized entity heads and tails were combined by LENER to extract the entities.The experimental results show that the LENER model has excellent entity recognition capabilities,and the F1 value is improved by 0.5%to 2%compared with other models.

关 键 词：中文命名实体识别 上下文环境 注意力机制 多源信息 滑动窗口 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]