Training method and system of named entity recognition model and electronic device

Abstract

The invention relates to a natural language processing technology, and provides a training method of a named entity recognition model. The method comprises the following steps: obtaining unlabeled corpus data from a corpus; pre-tagging the corpus data based on a category thesaurus; modifying the pre-labeling result to obtain a training text; training the named entity recognition model based on thetraining text, and repeating the above steps until the accuracy of the named entity recognition model reaches a preset threshold. Based on the training method provided by the embodiment of the invention, the recognition result of the named entity recognition model is more accurate and meets the actual requirement. In addition, the invention also provides a training system of a named entity recognition model.

Description

technical field [0001] The invention relates to natural language processing technology, in particular to a training method, system and electronic equipment for a named entity recognition model. Background technique [0002] Named entities refer to names of people, institutions, places, and all other entities identified by names. In natural language processing technology, word segmentation annotations also include named entity annotations. [0003] Specifically, in the process of natural language processing, supervised learning is often required to obtain the desired results, such as information extraction. In information extraction, named entity recognition is first required. In different fields, the entities to be extracted are often very different. Even in the same field, if the purpose or intention is different, the entity recognition templates will also be different. [0004] However, in the existing technology, named entity labeling basically relies on manual processi...

AI Technical Summary

Problems solved by technology

[0004] However, in the existing technology, named entity labeling basically relies on manual processing, and entity labeling needs to be based on a large amount of corpus data analysis, which often consumes a lot of manpower and material resources; more closely, in a specific application scenario , due to different application fields and different analysis purposes, the named entities that need to be annotated will also be different, so that it is impossible to achieve accurate annotation of the corpus

Images