Named entity identification method and device

Abstract

Embodiments of the invention provide a named entity identification method and device. The method comprises the steps that: a first character sequence matrix of a to-be-identified text is input into afirst training model, a first character feature matrix of the to-be-identified text is obtained; a first word sequence matrix of the to-be-recognized text is input into a second training model, a first word feature matrix of the to-be-recognized text is obtained, the dimension of the first character feature matrix is the same as that of the first word feature matrix; the first character feature matrix and the first word feature matrix are processed, a first character and word fusion feature matrix is obtained; and the first character and word fusion feature matrix is processed through a thirdtraining model, a named entity recognition result of the to-be-recognized text is obtained. According to the method, the character feature matrix and the word feature matrix are fused, and the character and word fusion feature matrix is processed, so that the accuracy of the recognition result of the to-be-recognized text is further improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a named entity recognition method and device. Background technique [0002] Named Entity Recognition (NER for short), also known as "proper name recognition", refers to the recognition of entities with specific meanings in text, mainly including names of people, places, institutions, and proper nouns. NER technology refers to marking the position and type of related entities from a piece of natural language text, and extracting the required entities, such as the identification of some institution names, person names, diseases, and symptoms in the medical field. It is widely used in tasks such as knowledge map construction, information extraction, information retrieval, machine translation, automatic question answering, and public opinion monitoring, and is the basis of natural language processing. [0003] NER usually uses sequence labeling to combine entity boundari...

AI Technical Summary

Problems solved by technology

However, in order to strengthen the correlation between words or words in this process, a lot of manual intervention is required to construct the characteristics of words or words, which is very time-consuming and laborious.

And the above method is difficult to guarantee the accuracy of named entity recognition in practice

Especially for sentences with long entities, it is more difficult to identify the boundaries of entities, resulting in lower accuracy of named entity recognition

Images