Co-reference resolution method and device in natural language processing, equipment and medium

Abstract

The invention provides a co-reference resolution method and device in natural language processing, equipment and a medium. The method comprises the steps of obtaining a character code of each character or word in a text; splicing each character code in the text with at least one adjacent character code to obtain a candidate reference vector; splicing each candidate reference vector with the othercandidate reference vectors in pairs to obtain a candidate co-reference tensor; and judging whether the two candidate reference vectors corresponding to each candidate co-reference tensor are in a co-reference relationship or not, and completing co-reference resolution according to the co-reference relationship. Whether the phrases at any position and other phrases are in the co-reference relationship or not can be obtained, on one hand, a syntactic structure and a semantic structure of an input text do not need to be analyzed, and named entities do not need to be analyzed; on the other hand,the invention can be embedded into other various natural language processing tasks and models, and the application range is wide; further, the co-reference digestion can be quickly and accurately completed.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a natural language processing co-reference resolution method, device, equipment and medium. Background technique [0002] Entity recognition refers to identifying and extracting entities with specific meanings or strong references in unstructured text, such as person names, place names, organizational structure names, date and time, proper nouns, etc. [0003] A relationship is a certain connection between two or more entities. Relationship extraction is to detect and identify a certain semantic relationship between entities and entities from the text, such as the sentence "Beijing is the capital, political center and cultural center of China. Center", where the relationship expressed can be (China, capital, Beijing), (China, political center, Beijing) or (China, cultural center, Beijing). [0004] Coreference resolution is a special relationship extracti...

AI Technical Summary

Problems solved by technology

[0006] In view of the above-mentioned shortcomings of the prior art, the purpose of the present invention is to provide a method, device, equipment and medium for solving the problem of low accuracy in natural language processing in the prior art.

Images