Method and device for automatically constructing field word list based on classification system

Abstract

The invention relates to the technical field of automatic construction of domain word lists, in particular to a method and device for automatically constructing a domain word list based on a classification system, and the method comprises the steps: obtaining data; determining a father node and each child node of the field node, and obtaining a plurality of associated words corresponding to the field node; determining the occurrence probability of the associated words in the average thousand words in the field nodes and the occurrence probability of the associated words in the average thousand words in the child node fields; determining the reciprocal of the average probability of the associated word appearing in each article in the field node and the reciprocal of the average probability of the associated word appearing in each article in the father node field; determining a first intermediate score and a second intermediate score of each associated word; determining a total score of the associated words according to the first intermediate score and the second intermediate score; and obtaining a preset score threshold, and determining a professional word list according to the associated words of which the total scores are greater than the preset score threshold. By adopting the method and the device, the professional word list can be simply, efficiently and automatically constructed.

Description

technical field [0001] The present invention relates to the technical field of automatic construction of domain vocabulary, in particular to a method and device for automatic construction of domain vocabulary based on a classification system. Background technique [0002] In recent years, domain vocabulary is an important resource for professional and vocational education, and it is also widely used in industries, such as solving classification problems. There are usually two ways to obtain the vocabulary in the current field: generating a vocabulary through word frequency statistics and expert identification, or constructing a classification model through machine learning, and using the model to classify a large amount of data. However, both of these two methods have the disadvantages of low efficiency, and a large amount of calculation, and the accuracy cannot be guaranteed. Contents of the invention [0003] The embodiment of the present invention provides a method and...

AI Technical Summary

Problems solved by technology

But both of these two methods have the disadvantages of low efficiency, and the amount of calculation is large, and the accuracy cannot be guaranteed.

Images