Natural language processing co-reference resolution method, device, equipment and medium

Abstract

The present invention provides a method, device, device and medium for co-reference resolution in natural language processing, including: obtaining the character code of each character or word in the text; encoding each character in the text with at least one adjacent character code Splicing to obtain candidate referent vectors; splicing each of the candidate referent vectors with the remaining candidate referent vectors in pairs to obtain candidate coreference tensors; judging the two candidate coreference tensors corresponding to each of the candidate coreference tensors Whether the referring vector is a coreference relationship, and coreference resolution is completed according to the coreference relationship. The present invention can obtain whether there is a coreference relationship between a phrase at any position and other phrases. On the one hand, it does not need to analyze the syntactic structure and semantic structure of the input text, nor does it need to analyze named entities; on the other hand, it can be embedded in various other natural The tasks and models of language processing have a wide range of applications; thus, coreference resolution 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