基于后缀向量拼接的军事装备命名实体识别

Military Equipment Named Entity Recognition Based on Suffix Vector Splicing

军事命名实体识别是军事知识图谱构建和装备实体画像的基础性和关键技术,该技术进一步为军事文本智能化处理、辅助决策和情报分析等任务提供支撑。基于后缀向量拼接的军事装备命名实体识别方法,针对中英文文本结构构成具有天然差异,中文文本缺少天然分割,加之军事装备别称较多,可能会造成识别的缺失等问题,提出利用文本字向量、词向量拼接实体后缀向量的方法,对军事装备实体进行识别和发现。通过实验验证方法的合理性和先进性。

Military named entity recognition is the foundation and key technology of military knowledge graph construction and equipment entity portrait,which further provides support for intelligent processing of military text,auxiliary decision-making and information analysis.This paper studies the military equipment named entity recognition method based on suffix vector splicing.In view of the natural differences in the structure of Chinese and English texts,such as the lack of natural segmentation of Chinese texts and the existence of many nicknames for military equipment,these conditions may cause problems such as the lack of recognition,this paper proposes a method to recognize and discover military equipment entities by splicing entity suffix vectors through text word vectors and word vectors.The rationality and progressiveness of the method are verified by experiments.