Chinese named entity recognition method based on BERT-BiGRU-CRF

Abstract

The invention discloses a Chinese named entity recognition method based on BERT-BiGRU-CRF. The method comprises three stages: in the first stage, preprocessing mass text corpora, and pre-training a BERT language model; in the second stage, preprocessing the named entity recognition corpus, and encoding the named entity recognition corpus through the trained BERT language model; and at the third stage, inputting the encoded corpus into a BiGRU+CRF model for training, and performing named entity recognition on the to-be-recognized statement by using the trained model. Construction of the Chinesenamed entity recognition method based on BERT-BiGRU-CRF is carried out, semantic representation of characters is enhanced through a BERT pre-training language model, semantic vectors are dynamicallygenerated according to contexts of the characters, and the ambiguity of the characters is effectively represented. Compared with a method based on fine tuning of a language model, the method has the advantages that training parameters are reduced, and the training time is saved.

Description

technical field [0001] The invention belongs to the field of named entity recognition, and in particular relates to a Chinese named entity recognition method based on a BERT-BiGRU-CRF model. Background technique [0002] Named entity recognition aims to identify specific entity information in text, such as person names, place names, organization names, etc. It is widely used in information extraction, information retrieval, intelligent question answering, and machine translation, and is one of the foundations of natural language processing. Traditional named entity recognition methods can be divided into dictionary-based named entity recognition methods, rule-based named entity recognition methods, traditional machine learning-based named entity recognition methods, neural network-based named entity recognition methods and language model-based fine-tuning Methods. [0003] A dictionary-based named entity recognition method, which first constructs a large-scale entity dictio...

AI Technical Summary

Problems solved by technology

[0009] 1. The dictionary-based named entity recognition method relies heavily on the dictionary database, cannot identify unregistered words, and cannot identify nested entities

[0010] 2. The rule-based named entity recognition method requires linguistic background knowledge when constructing rules. Chinese expressions are diverse, and rules are difficult to enumerate and easy to conflict. Another disadvantage is that they are not transferable and the work is cumbersome and complicated.

[0012] 4. The method of named entity recognition based on neural network, which cannot characterize the polysemy of words or words

[0013] 5. The fine-tuning method based on the language model has the disadvantages of a large amount of parameters and a long training time

Images