Affiliation:
1. School of Foreign Language, Henan University of Chinese Medicine, Zhengzhou 450046, China
2. School of International Studies, Zhengzhou University, Zhengzhou 45001, China
Abstract
English is now widely used in the world as an international language. As a symbol of the development of human civilization, English characters provide an important medium and tool for mankind. In the current information age, the vocabulary of English words is more quantitative, and it is almost everywhere. Under the background of the multiquantification of English words and the quantification of the relationship between words, the similarity measurement analysis and calculation of English words and the classification of vocabulary measurement calculation are carried out by integrating the characteristics of language. The experimental results are as follows: (1) the development situation of English words is analyzed, the research direction of the experiment is determined, the concept of English character features is proposed, and the similarity calculation method is selected according to different features, in order to simplify the complex and difficult-to-understand word meaning relationship between English words; (2) the text features are extracted through the similarity feature selection of language and text. The extraction of features indirectly affects the effectiveness of classification. The similarity word embedding vector is used to map English words into the vector for analysis and comparison, calculate the distance between the similarity numerical variables between English words and their similarity coefficient, measure the distance between them, and evaluate the similarity between them, including the angle cosine method and correlation coefficient method which are the two main methods for calculating the similarity coefficient.
Funder
Henan University of Chinese Medicine
Subject
Computer Networks and Communications,Computer Science Applications