Named entity identification method and system, electronic equipment and storage medium

Abstract

The embodiment of the invention relates to the field of natural language processing, and discloses a named entity recognition method and system, electronic equipment and a storage medium. The method comprises the following setps: obtaining the first lable sequence and the second lable sequence, wherein the first label sequence is a result of identifying the text by using a word vector, and the second label sequence is a result of identifying the text by using a word vector; and selecting a tag sequence with higher text recognition accuracy in the first tag sequence and the second tag sequenceas an output tag sequence. According to the method, the text is represented by the word vector and the word vector respectively, the first label sequence and the second label sequence are generated, and the label sequence with higher recognition accuracy in the first label sequence and the second label sequence is selected as the output label sequence. Because the word vector mode and the character vector mode respectively have better recognition effects on certain sentence patterns, the recognition effect of the Chinese named entity can be improved to a certain extent by combining the advantages of the word vector mode and the character vector mode for representing the text.

Description

technical field [0001] The embodiments of the present invention relate to the field of natural language processing, and in particular to a named entity recognition method and system, electronic equipment, and a storage medium. Background technique [0002] Using natural language to communicate with computers has been pursued by people for a long time. In the field of natural language processing developed on the basis of this idea, named entity recognition is a very basic and important task, which includes Chinese naming Entity recognition is an important step in the construction of a multi-round dialogue system, but it has difficulties such as word segmentation, ambiguity, word nesting and complex structure that need to be solved urgently. [0003] The current Chinese named entity recognition technology uses word vectors or word vectors to represent Chinese texts, and uses a two-way long-short-term memory network with conditional random fields to improve accuracy. If only t...

AI Technical Summary

Problems solved by technology

If only the word vector method is used to represent the Chinese text, the words in the sentence need to be divided, and the accuracy of the word division will directly affect the representation effect of the word vector method, but it is more complicated to improve the accuracy of the word division algorithm; if only word vectors are used to represent Chinese text, although its

Images