Research on Chinese Semantic Similarity Algorithm
Xinlin Liu, Wei Deng, Jian Zhang · 2023
The rapid development of information technology and the rapid popularization of mobile terminals have promoted the transmission of information, and the growing amount of text data has become an important source of information for people to understand. This article studies the use of Word2vec to calculate word vectors to improve semantic similarity between texts, overcoming the shortcomings of traditional methods that rely on background knowledge bases, dictionaries, etc. to calculate similarity between texts. The accuracy of similarity calculation is compared with traditional cosine similarity and editing distance similarity. The implementation shows that the similarity calculation method based on Word2vec improvement proposed in this article has higher computational accuracy.