融合词性、语义及词序因子的中文短文本相似度计算方法  

Computing Method of Chinese Short Text Similarity Based on Part of Speech,Semantic and Word Order Factors

作　　者：祖月芳 凌海风 汤润之 翟仕奇 王涛 ZU Yuefang;LING Haifeng;TANG Runzhi;ZHAI Shiqi;WANG Tao(No.96761 Troops of PLA,Sanmenxia 472100;College of Field Engineering,Army Engineering University,Nanjing 210004;No.32228 Troops of PLA,Nanjing 210004)

机构地区：[1]96761部队,三门峡472100 [2]陆军工程大学野战工程学院,南京210004 [3]32228部队,南京210004

出　　处：《计算机与数字工程》2024年第8期2420-2424,2468,共6页Computer & Digital Engineering

摘　　要：论文针对中文短文本特性,综合考虑词性、词序和语义等因素提出了一种新的文本相似度计算方法[1]。这种方法是在余弦相似度的基础上计算中文短文本的语义相似度,并通过加权词性、词序权重优化相似度计算结果。实验证明,论文的方法与其他方法相比,准确率和召回率有了显著提高,获得的相似度结果更具说服力。According to the characteristics of Chinese short texts,a method of calculating text similarity is proposed,which combines parts of speech,semantics and word order factors.This method relates the part of speech,meaning and position of words in Chinese short text,and on the basis of cosine formula,through the correlation between the similarity of words of text vectors and the weight of part of speech,this paper improves the method of Chinese short text similarity calculation,and introduces word order similarity to optimize text similarity.The experimental results show that this method has better accuracy and recall than other methods,and is more in line with people's subjective judgment.

关 键 词：中文短文本相似度 词性 词序 语义 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]