Entity recognition model generation method, entity recognition method, device and apparatus

Abstract

Embodiments of the invention disclose an entity recognition model generation method, an entity recognition method, device and apparatus. The method comprises the steps of performing training by utilizing standard text data to obtain a mapping model of segmented words and word vectors; performing word segmentation on the first training text to obtain first segmented words included in the first training text; determining an approximate word of the first segmented word through the mapping model of the segmented word and the word vector, and generating an approximate sentence corresponding to thefirst training text through the approximate word of the first segmented word; obtaining feature representation of each character in the first training text and feature representation of each characterin an approximate sentence corresponding to the first training text; and training to generate an entity recognition model by utilizing the feature representation of each character in the first training text, the feature representation of each character in the approximate sentence corresponding to the first training text and the entity category label and the character sequence label of each character in the first training text.

Description

technical field [0001] The present application relates to the technical field of data processing, and in particular, to a method, device, and device for generating an entity recognition model, and a method, device, and device for entity recognition. Background technique [0002] In the process of building an entity recognition model using named entity recognition technology, a supervised model training method is usually used, and a corresponding entity recognition model is obtained by training a large amount of labeled training data. Among them, the amount of training data has an important impact on the performance of the trained entity recognition model. [0003] However, in some fields, it is difficult to obtain a large amount of training data with labels. When the training data is small and cannot meet the needs of entity recognition model training, the performance of the trained entity recognition model will be poor. The entity recognition result obtained by recognizing...

AI Technical Summary

Problems solved by technology

[0003] However, in some fields, it is difficult to obtain a large amount of training data with labels. When the training data is small and cannot meet the needs of entity recognition model training in quantity, it will lead to poor performance of the trained entity recognition model. The entity recognition result obtained by recognizing the text is not accurate enough

Images