Conditional random field-based automatic Chinese personal name recognition method

A conditional random field and automatic identification technology, which is applied in the fields of instruments, calculations, electrical digital data processing, etc., can solve the problems that the identification effect needs to be improved, and achieve the effect of reducing identification errors and improving the identification effect

Inactive Publication Date: 2014-12-03
EAST CHINA NORMAL UNIV
View PDF1 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The solution to the problem of Chinese name recognition is a prerequisite for improving the acc...

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
  • Conditional random field-based automatic Chinese personal name recognition method
  • Conditional random field-based automatic Chinese personal name recognition method
  • Conditional random field-based automatic Chinese personal name recognition method

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0051] figure 1 A flow chart of a method for automatic recognition of Chinese personal names based on conditional random fields according to the first embodiment of the present invention is shown. Such as figure 1 Shown, a kind of Chinese name automatic recognition method based on conditional random field of the present invention comprises the following steps:

[0052] Step S101: Construct a conditional random field model.

[0053] Step S102: Obtain the rule set of personal names. First, use the tagger in the initial state to tag the text, and then use the conversion template and the objective function to obtain multiple candidate conversion templates by comparing them with the reference corpus that has been correctly tagged, and then find After applying a conversion template, the conversion formula that can produce the least number of labeling errors is applied to the labeling corpus as a new labeling rule until no such rule is found.

[0054] Step S103: Use the conditiona...

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 provides a conditional random field-based automatic Chinese personal name recognition method. An automatic Chinese personal name recognition system is constructed by studying Chinese personal name characteristics and combining a statistical probability model; text messages are subjected to segmentation, the conditional random field is based, a context rule and credibility method is combined, and candidate personal names are obtained; personal names with boundary recognition errors are corrected by means of a local statistical algorithm, and recognition results of a system are finally obtained. The recognition errors generated through segmentation are greatly reduced, the problem that other named entities are recognized as Chinese personal names is better solved, and the recognition effect is improved.

Description

technical field [0001] The invention relates to the field of natural language processing, in particular to the Chinese name recognition technology in named entity recognition. Background technique [0002] Chinese names mainly include Chinese names, Japanese names, and foreign transliterated names. The recognition of Chinese names is an important part of Chinese named entity recognition, and it is also an important basic work in the research fields of information mining, information extraction, machine translation, and text classification. In addition, in the field of word segmentation, the vast majority of unregistered words are personal names, and the recognition effect of Chinese personal names directly affects the effect of word segmentation. The solution to the problem of Chinese name recognition is a prerequisite for improving the accuracy of automatic word segmentation of Chinese text, and the recognition effect needs to be improved. [0003] In view of this, the in...

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
IPC IPC(8): G06F17/30
CPCG06F16/335G06F16/3349
Inventor 吕钊高维维
Owner EAST CHINA NORMAL UNIV
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