Training method and training device of statement entity labeling model and electronic equipment

Abstract

The invention provides a statement entity labeling model training method and device and electronic equipment. The method comprises the steps: carrying out the word vector processing of sample statements in a plurality of obtained sample texts, and obtaining a plurality of sample matrixes; attention weighting processing is carried out on each sample matrix, and a plurality of processed sample weighting representation matrixes are determined; determining an auxiliary weighted representation matrix corresponding to each sample weighted representation matrix by training a constructed auxiliary classification model; and training a pre-constructed conditional random field model by taking the plurality of auxiliary weighted representation matrixes as input features and taking the obtained samplestatement label corresponding to each sample statement as an output feature to obtain a statement entity labeling model. Therefore, the labeling precision of the model in the use process can be further improved, the noise interference can be reduced, the entity can be accurately labeled, and the generalization ability of the model is improved.

Description

technical field [0001] The present application relates to the technical field of computer natural language processing, in particular to a training method, training device and electronic equipment for a sentence entity tagging model. Background technique [0002] Sentence entity recognition is a key task in natural language processing. The purpose is to identify specific types of thing names and meaningful quantitative phrases in sentences, including three categories of named entities, time, and numbers, which can be subdivided into seven categories. A subcategory: person name, place name, organization name, time, date, currency, percentage, etc. [0003] At present, when the existing sentence entity recognition methods are applied to Chinese sentence labeling, they are usually affected by noise such as irregular grammar sentences, new words / wrong words, cyberspeak / expressions, etc., which makes the accuracy of the labeling results low and the accuracy of the model If the de...

AI Technical Summary

Problems solved by technology

[0003] At present, when the existing sentence entity recognition methods are applied to Chinese sentence labeling, they are usually affected by noise such as irregular grammar sentences, new words / wrong words, cyberspeak / expressions, etc., which makes the accuracy of the labeling results low and the accuracy of the model The degree is low, the generalization effect of the model is not good

Images