Named entity recognition method and device, storage medium and terminal device

Abstract

The invention discloses a named entity recognition method. The named entity recognition method comprises the steps of obtaining the unlabeled corpora; training a preset language model according to the unlabeled corpus; labeling the unlabeled corpora to obtain the labeled corpora; training a preset named entity recognition model according to the tagged corpus, wherein the named entity recognition model is constructed according to a trained language model; and identifying the named entity in the to-be-identified text according to the trained named entity identification model. Correspondingly, the invention further discloses a named entity recognition device, a computer readable storage medium and a terminal device. By adopting the technical scheme of the invention, the unlabeled corpus can be fully utilized to train the language model, and the context understanding capability of the language model is enhanced, so that the training cost is reduced, and the recognition effect is improved.

Description

technical field [0001] The present invention relates to the technical field of natural language processing, in particular to a named entity recognition method, device, computer-readable storage medium and terminal equipment. Background technique [0002] Natural Language Processing (NLP) is the field of interaction between computer and human language that computer science, artificial intelligence, and linguistics focus on. It is an important direction in the field of computer science and artificial intelligence. As a basic task in NLP, named entity recognition (Named Entity Recognition, NER) refers to the recognition of entities with specific categories from text, such as names, place names, organization names, proper nouns, etc. In artificial intelligence research, named entity recognition is a task that must be overcome, and the recognition effect of named entities has an important impact on a series of subsequent artificial intelligence technologies. [0003] The existin...

AI Technical Summary

Problems solved by technology

[0003]The existing technology generally builds a named entity recognition model, and recognizes the named entities in the text according to the trained named entity recognition model, and then trains the named entity recognition model However, manual labeling takes a lot of time and energy, and the available labeled corpus is less, resulting in The training cost is increased, and the recognition effect of the named entity recognition model obtained by training with a small amount of labeled corpus is poor

Images