Method and device for determining relationship category between entities and computer equipment

Abstract

The embodiment of the invention discloses a method and device for determining a relationship category between entities and computer equipment. The method comprises the steps of obtaining a target wordvector corresponding to each word in a to-be-recognized text according to a preliminary word vector corresponding to the word, a weight between the word and an adjacent word corresponding to the wordand a preliminary word vector of the adjacent word corresponding to the word, the adjacent word being a word adjacent to the word in the to-be-recognized text; obtaining an entity labeling result corresponding to each character in the to-be-recognized text according to the target character vector corresponding to each character in the to-be-recognized text; obtaining a feature vector corresponding to each entity in the to-be-recognized text according to the entity labeling result corresponding to each character in the to-be-recognized text and the target character vector, and determining a relationship classification result of at least two entities in the to-be-recognized text according to the feature vector corresponding to each entity in the to-be-recognized text. According to the invention, the accuracy of relationship classification can be improved.

Description

technical field [0001] The invention relates to the technical field of information extraction, in particular to a method, device and computer equipment for determining the relationship category between entities. Background technique [0002] Entity extraction refers to extracting entities from text. Existing entity extraction methods mainly train entity extraction models, and then input text into the trained entity extraction model to obtain entities output by the entity extraction model. Generally, entity extraction models include machine learning models and deep learning models. [0003] After the entities are extracted, if the text contains multiple entities, it is also necessary to determine the relationship category between the multiple entities. For example, the relationship category between entity "Jay Chou" and entity "Taiwan" is "born in"; the relationship category between entity "Kobe" and "Lakers" is "worked in". Usually, the relationship classification model ne...

AI Technical Summary

Problems solved by technology

[0004] However, the existing entity extraction model simply extracts the features of the entity, and does not fully mine the context information involved in the entity, resulting in inaccurate extracted entity features, which in turn leads to the final determination of the relationship category. low accuracy

Images