Chinese query extension method based on deep learning and extension word mining intersection fusion

Abstract

The invention provides a Chinese query extension method based on deep learning and extension word mining intersection fusion. The method comprises the following steps: carrying out word embedding semantic learning training on an initial detection document set by adopting a deep learning tool; obtaining a word embedding extension word set with rich context semantic information; then, mining an association rule mode for the initially-detected front-column pseudo-correlation feedback document set by utilizing a Copulas-theory-based pseudo-correlation feedback extension word mining method; and obtaining a rule extension word set containing feature inter-word association information based on statistical analysis, and finally embedding words into the extension word set and the rule extension word set for intersection fusion to obtain a final extension word set so as to improve the extension word quality. According to the method, deep learning and extension word mining intersection are fused,high-quality extension words related to original query are mined, the problems of query topic drifting and word mismatching can be restrained, the text information retrieval performance is improved,and the method has good application value and popularization prospects.

Description

technical field [0001] The invention relates to a Chinese query expansion method integrating the intersection of deep learning and expanded word mining, and belongs to the technical field of information retrieval. Background technique [0002] Query expansion is one of the key technologies to solve the problem of query subject drift and word mismatch in information retrieval. Query expansion refers to modifying the original query weight or adding words related to the original query to obtain a new query that is longer than the original query. , in order to more completely and accurately describe the semantics or themes implied by the original query, make up for the lack of user query information, and improve the retrieval performance of the information retrieval system. The core problem of query expansion is the source of expansion words and the design of expansion model. With the development of network technology and the arrival of the era of big data, network users have m...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to propose a Chinese query expansion method for the intersection fusion of deep learning and expanded word mining, and use the method in the field of information retrieval, such as actual Chinese search engines and web information retrieval systems, to improve and enhance the performance of information retrieval systems Query performance, reducing query subject drift and word mismatch problems in information retrieval

Images