Cross-Language Information Matching Technology Based on Term Extraction

摘要

Based on the analysis and summary of current achievements on terms extraction, this paper puts forward a method of term extraction based on multi feature fusion. This method firstly uses term word formation rules to filter words depending on the result of preprocessing, and then determines the boundaries of words according to information entropy. The paper introduces the concept of word co-occurrence according to the features of field terms, and uses bag of words model to align terms in both English and Chinese, and obtains the corresponding translation terms in one field. Finally, it establishes the link between Chinese and English by using the term alignment results in both English and Chinese retrieval model. This paper carries out repeated experiments on sets of policy documents. The experiments test and verify the availability of the method by the analysis and comparison between the method introduced in this paper and the traditional methods.