基于注意力机制的命名实体识别模型研究——以军事文本为例  

Study on Named Entity Recognition Model Based on Attention Mechanism——Taking Military Text as Example

作　　者：单义栋 王衡军[1] 黄河 闫倩 SHAN Yi-dong;WANG Heng-jun;HUANG He;YAN Qian(The Third Institute,PLA Information Engineering University,Zhengzhou 450001,China;61660 Army,Beijing 100000,China;Shandong Military District,Jinan 250000,China)

机构地区：[1]解放军信息工程大学三院,郑州450001 [2]61660部队,北京100000 [3]山东省军区,济南250000

出　　处：《计算机科学》2019年第B06期111-114,119,共5页Computer Science

摘　　要：针对双向长短时记忆网络模型提取特征不充分的特点,将字向量和词向量同时作为双向长短时记忆网络的输入,并利用注意力机制分别提取两者对当前输出有用的特征,用维特比算法约束最终输出的标签序列,构建一种新的命名实体识别模型。实验结果表明,在军事文本的命名实体识别中,该模型取得了较优的识别率。Due to the insufficiency of extracting features by bi-directional long-short term memory network model,the character vector and the word vector are used as the input and the attention mechanism is used to extract the features that are useful for the current output.In this paper,a new named entity recognition model was constructed by constraining the final output tag sequence with the Viterbi algorithm.The experimental results show that the model has achieved a better recognition rate in the identification of military texts.

关 键 词：注意力机制 字向量 词向量 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]