Information extraction method, model training method and related equipment

Abstract

An embodiment of the present application provides an information extraction method, a model training method, and related equipment, the method including: obtaining text to be processed; inputting the text to be processed into an entity object recognition model, and outputting N pieces of the text to be processed Entity words, the N is a positive integer; each entity word in the N entity words and the text to be processed are input to the emotional information extraction model as input, and the N entity words are output in one-to-one correspondence The N emotional information of . By adopting the method provided in the embodiment of the present application, the accuracy rate of extracting emotional information from the text is improved.

Description

technical field [0001] The embodiments of the present application relate to the technical field of natural language processing, and in particular, to an information extraction method, a model training method, and related equipment. Background technique [0002] With the development of Internet technology, people can not only obtain information resources through the Internet, but also share some valuable information resources for some people, events, products, etc., for the reference of others. For example, after a user purchases a certain product on the Internet, he or she can publish some content about the product, such as product evaluation and usage experience, so as to facilitate other people to have a more comprehensive understanding of the product. Or, express some of your own opinions on current hot events. These subjective information can usually reflect the public opinion on a certain thing or product to a certain extent, so the sentiment analysis of these informat...

AI Technical Summary

Problems solved by technology

[0004] However, existing methods for extracting sentiment information rely on entity dictionaries and sentiment dictionaries, and only consider the dependency between entity words and the part of speech of each word in the text. When there are entity words and new emotional words, or when the text does not contain entity targets, the effective emotional information corresponding to entity targets cannot be extracted from the text or the accuracy of emotional information extraction is very low.

Images