Training method and device for sequence labeling model

Abstract

The invention relates to the field of natural language processing, and particularly relates to a training method and device of a sequence labeling model. The method is used for effectively training asequence labeling model under the condition of insufficient sample data volume. The method comprises the following steps of: training a sequence labeling model based on the sample training statement set; obtaining first loss information, determining an adversarial disturbance factor according to the model parameters; and obtaining second loss information based on the sample training statement setadded with the adversarial disturbance factor, adjusting model parameters of the sequence labeling model based on target loss information obtained through calculation of the first loss information andthe second loss information, performing iterative training, and determining that a convergence condition is satisfied. Thus, by adding the anti-disturbance factor, different loss information can be obtained based on one sample training statement, the generalization ability of the sequence labeling model obtained through training is higher, the precision is higher, introduction of unnecessary noise interference is avoided, and resource consumption is reduced.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to a training method and device for a sequence labeling model. Background technique [0002] The sequence labeling problem is an important and widely used problem in the field of natural language processing. After people complete the training of the sequence labeling model based on the training samples, they can use the trained sequence labeling model to realize the input sentences. Sequence labeling. However, when training sequence labeling models, there are insufficient samples in many scenarios. [0003] In the prior art, in order to obtain a sufficient sample size, data enhancement processing is usually used to obtain multiple sample data from one sample data, and then sequence labeling model training is performed through the obtained multiple sample data. However, when the sample data generated by data enhancement processing is used for training, the noise caused by...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a training method and device for a sequence labeling model, which is used to solve the problem in the prior art that an effective sequence labeling model cannot be obtained due to insufficient sample data when training the labeling model

Images