Semantic classification method for Chinese question

Abstract

The invention discloses a semantic category method of Chinese problem based on Chinese problem semantic category system and Chinese problem multi-type category model. It is formed by Chinese problem semantic category system constructing, Chinese problem character vector representation and Chinese problem multi-type category based on uniformity loss; the Chinese problem semantic category system constructs a problem semantic category system including the definition and the quoting method of all of the semantic category, the problem category result is one of the problem semantic category; the Chinese problem character vector uses some characters to represent the problem text into the character vector which the category model can identify; the Chinese problem multi-type category based on uniformity loss maps the inputted problem character vector to one category of the problem semantic category system.

Description

technical field [0001] The invention belongs to the field of computer software, relates to the fields of computer software, natural language processing, machine learning, and Chinese linguistics, and particularly relates to a semantic classification method for Chinese questions. Background technique [0002] The semantic classification of Chinese questions is to establish a semantic classification system, automatically mark the questions with the categories in the classification system, and then understand the intention of the question, and provide effective information for further processing of the question and obtaining the answer to the question. The semantic classification of questions is widely used in the fields of question answering system (Question Answering System), knowledge acquisition and so on. [0003] The applicant retrieved the following related documents: [0004] (1) 3 relevant domestic documents (title, author or institution, source): [0005] 1) Title: ...

AI Technical Summary

Problems solved by technology

The main problem of the first algorithm is that the implementation of the algorithm is not intuitive, and the time and space overhead when training the model is large; for the second algorithm, because it uses a combination of multiple classifiers to achieve multi-class classification, These two-class classifiers are independent of each other, and their respective objective functions are optimized during learning, so that there may be inseparable regions during classification, which affects the accuracy of classification

Images