Named entity recognition method and named entity recognition model training method and device

Abstract

The embodiment of the invention provides a named entity recognition method. The method comprises the steps of obtaining a target text to be subjected to named entity recognition; inputting the targettext into a preset named entity recognition model to obtain a named entity recognition result of the target text, wherein the named entity recognition model is obtained by training a training sample and label information of the training sample; the named entity recognition model comprises a long short-term memory network LSTM layer; the LSTM layer is used for processing each character except the first two characters in the training sample, and the processing process of the LSTM layer comprises the step of carrying out feature extraction on a character vector of the character, an initial feature vector of a previous character of the character and a word vector of the existing word to obtain an initial feature vector of the character if a word exists in the content in front of the characterin the training sample. Compared with the prior art, when the method provided by the embodiment of the invention is applied to perform named entity recognition on the text, the accuracy of the obtained recognition result can be improved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a named entity recognition method, a training method and a device for a named entity recognition model. Background technique [0002] Currently, there are more and more demands for named entity recognition tasks, such as question answering systems, machine translation systems, etc. The so-called named entity recognition (Named Entity Recognition, NER), also known as "proper name recognition", refers to the recognition of entities with specific meanings in the text, mainly including names of people, places, institutions, and proper nouns. [0003] Among them, performing named entity recognition tasks based on the trained named entity recognition model is a common method. The named entity recognition model may include an LSTM (LongShort-Term Memory, long-term short-term memory network) layer for extracting the feature vectors of each word in the text, and an intermediate layer f...

AI Technical Summary

Problems solved by technology

[0005] However, in the above-mentioned related technologies, since the word order information of each word included in the training samples is ignored during the processing of the LSTM layer, the overall characteristics of the training samples are not learned. Therefore, the named entity recognition obtained by training in the above-mentioned related technologies is used When the model performs named entity recognition on text, the accuracy of the recognition results obtained is low

Images