Named entity recognition method and device based on semi-supervised learning training

Abstract

The invention relates to a named entity recognition method and device based on semi-supervised learning training, computer equipment and a storage medium. The method comprises the steps of obtaining annotation data and non-annotation data; performing supervised training on a sequence labeling model by utilizing the labeling data; calculating semantic vectors corresponding to the annotation data and the unannotated data through a trained sequence annotation model, and identifying the unannotated data in the same distribution as the annotation data according to the semantic vectors; calling a semi-supervised learning model, wherein the semi-supervised learning model is composed of the trained sequence labeling model and an auxiliary prediction network with a limited input view angle; and training the semi-supervised learning model through unlabeled data in the same distribution, and outputting a corresponding named entity recognition result through Viterbi decoding. By adopting the method, the data annotation cost can be effectively reduced, and the named entity identification accuracy can be effectively improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a named entity recognition method, device, computer equipment and storage medium based on semi-supervised learning training. Background technique [0002] Named Entity Recognition (NER for short) refers to identifying entities with specific labels from data sequences, such as time, place, person name, organization name, etc. Named entity recognition is the basic task of relationship extraction, information retrieval, automatic question answering, dialogue systems, etc. Whether it can be accurately identified is related to whether the subsequent processing can be accurate. The model of named entity recognition is mainly trained through supervised learning and semi-supervised learning. Supervised learning training relies on labeled data, but the cost of data labeling is high. Semi-supervised learning training can use labeled data and unlabeled data. One semi-supervise...

AI Technical Summary

Problems solved by technology

But an important drawback of this pre-training is that the representation learning stage cannot use labeled data

Images