Naming entity identification method

A technology for named entity recognition and person names, applied in the information field to achieve the effect of improving accuracy

Inactive Publication Date: 2019-02-19
KUNMING UNIV OF SCI & TECH
View PDF4 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved in the present invention is to provide a named entity recognition method for the limitations and deficiencies of the existing technology, and introduce the LSTM neural network to solve the problem that the single named entity recognition technology based on the statistical model is not accurate enough to recognize the boundary. The word recognition rate is low, so that the accuracy of named entity recognition results is low, so as to improve the accuracy of named entity recognition

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Naming entity identification method
  • Naming entity identification method
  • Naming entity identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] Embodiment 1: as Figure 1-2 As shown, a named entity recognition method, first establishes a named entity recognition corpus, uses the corpus to train the named entity recognition model that has been introduced into the LSTM neural network; then performs word segmentation on the text data to be recognized; then uses the CRF model to segment the words The text data is used for name recognition; finally, the trained named entity recognition model is used to recognize place names and organization names, and the final result of named entity recognition is obtained by combining the names of people.

[0028] The specific steps are:

[0029] ① Establish a named entity recognition corpus.

[0030] ② Segment the text data to be recognized.

[0031] ③ Use the corpus to train the named entity recognition model that has been introduced into the LSTM neural network.

[0032] ④ Use the CRF model to recognize the names of the text data that has been divided into words.

[0033] ⑤...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a naming entity identification method, belonging to the information technology field. Firstly, a named entity recognition corpus is established to train the named entity recognition model based on LSTM neural network. And then segmenting the text data to be recognized; Secondly, the CRF model is used to recognize the text data of the divided words. Finally, the trained named entity recognition model is used to recognize the place name and organization name, and the final result of named entity recognition is obtained by de-duplication of person name. By introducing theLSTM neural network, the invention solves the phenomenon that a single named entity recognition technology based on a statistical model is not accurate enough to recognize the boundary, and the recognition rate of new words is low, so that the recognition result of the named entity is low in accuracy, so as to improve the accuracy of the named entity recognition.

Description

technical field [0001] The invention relates to a named entity recognition method, which belongs to the field of information technology. Background technique [0002] With the rapid development of the Internet and the information industry, massive text data is constantly being generated. How to efficiently obtain useful information from massive text data has become a research hotspot. Information extraction technology has emerged as the times require, and named entity recognition is information extraction. A subtask of , whose purpose is to extract specified entities from massive text data. In the field of natural language processing applications, named entity recognition is the basic task of many natural language processing applications such as information retrieval, machine translation, and sentiment analysis. Therefore, its research is of great significance and value. [0003] Generally, there are various types of named entities and a large number, and new named entities...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06F17/27
CPCG06F40/295
Inventor 龙华吴睿熊新邵玉斌杜庆治
Owner KUNMING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap