词嵌入模型研究综述  

A review of research on word vectors

作　　者：陈萌 和志强[1] 王梦雪 CHEN Meng;HE Zhi-qiang;WANG Meng-xue(College of Information Technology,Hebei University of Economics and Business, Shijiazhuang Hebei 050061, China)

机构地区：[1]河北经贸大学信息技术学院,河北石家庄050061

出　　处：《河北省科学院学报》2021年第2期8-16,共9页Journal of The Hebei Academy of Sciences

基　　金：河北省高新技术企业培育及云服务平台研建项目(19945332G);2020年度河北经贸大学研究生创新计划项目。

摘　　要：随着深度学习的快速发展,词嵌入模型研究不断深入,自然语言处理技术取得了巨大的突破。本文首先阐述词嵌入的由来,并从静态词嵌入模型、动态词嵌入模型两个方面对词嵌入模型进行梳理,最后对词嵌入模型进行进行总结并对其未来的发展趋势进行展望。With the rapid development of deep learning,the research on word vector model has been deepened constantly,and the natural language processing technology has made great breakthroughs.This paper first describes the origin of the word vector,and from the static word vector pre-training model,dynamic word vector pre-training model two aspects of the word vector model to comb,finally,the word vector model is summarized and its future development trend is prospected.

关 键 词：深度学习 词嵌入 预训练 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]