Named entity identification method and device

Abstract

The invention provides a named entity identification method and device. After first entity probability distribution of a train document and second entity probability distribution of a test document are obtained by utilizing an initially constructed first sequence annotation model, features, such as the first context similarity of the train document and the first object similarity of the train document and the second context similarity of the test document and the second object similarity of the test document, can be extracted from social network information; therefore, a second sequence annotation model is obtained by training the first context similarity of the train document and the first object similarity of the train document, such that the second sequence annotation model is more suitable for a social network; and in addition, the named entity identification result, which is obtained by performing sequence annotation of the test document based on the second sequence annotation model suitable for the social network, is more accurate.

Description

technical field [0001] The present invention belongs to the technical field of named entities, and more specifically, relates to a named entity recognition method and device. Background technique [0002] Named entities refer to entities with specific meanings, such as the name Li San, and named entity recognition is to identify entities with specific meanings in the text, mainly including personal names, place names, organization names, and proper nouns. These identified entities are used as follow-up The input of information extraction tasks, such as relationship extraction, event extraction, and fine-grained sentiment analysis, can be used as the input of information extraction tasks. Therefore, the quality of named entity recognition results directly affects the effect of subsequent information extraction tasks. [0003] At present, there are many named entity recognition methods, such as the recognition method with the patent number 201310201310674046.7. The process is:...

AI Technical Summary

Problems solved by technology

[0003] At present, there are many named entity recognition methods, such as the recognition method with the patent number 201310201310674046.7. The process is: recognize the special words in the text to be processed; Process the replacement of special words identified as model entities in the text, and then identify entities such as commodity entities, commodity classification entities, brand entities, commodity attribute name entities, and commodity attribute value entities on this basis. This recognition method is mainly for General texts, while the texts in social networks are mainly short texts. In social networks such as Weibo or QQ, most of the texts posted by users are short texts, and users in social networks will follow each other. However, the current named entity recognition method It is not based on this feature, so there is an urgent need for a named entity recognition method suitable for social networks such as Weibo or QQ

Images