Unlock instant, AI-driven research and patent intelligence for your innovation.

A New Chinese Verb Recognition Method

A recognition method and verb technology, which are applied in the fields of Chinese natural language processing and Chinese verb automatic recognition, can solve the problems that recognition accuracy and recall rate cannot support the application, and achieve excellent recognition performance and the effect of solving recognition problems.

Active Publication Date: 2020-03-20
中科国力(镇江)智能技术有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, their method is based on purely statistical calculations, so neither the recognition accuracy nor the recall rate can support practical applications.

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
  • A New Chinese Verb Recognition Method
  • A New Chinese Verb Recognition Method
  • A New Chinese Verb Recognition Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] In order to describe the present invention more clearly, define and explain following terms below:

[0038](1) ICTCLAS system: a free, open-source word segmentation system, the present invention uses the ICTCLAS version in 2012. The ICTCLAS system takes text as input, and the output is the word segmentation sequence of the text. The website for downloading the ICTCLAS system is: http: / / ictclas.nlpir.org. After participle, each participle is marked with part of speech, where a means adjective, b means distinguishing word, c means conjunction, d means adverb, h means prefix, j means abbreviation, k means suffix, m means numeral, n means Nouns, p for prepositions, q for quantifiers, r for pronouns, u for particles, z for state words, and so on.

[0039] (2) Chinese seed dictionary: a dictionary composed of a group of words that people use in daily life. For example, "Xinhua Dictionary" and Kingsoft PowerWord are good examples. For the convenience of the following descr...

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 system and a method for Chinese new verb identification. The method comprises: performing word segmentation on an original training corpus CNCorpus, to form a word segmented corpus TCNCorpus; identifying possible new verbs in the word segmented corpus TCNCorpus, to form a result assembly Tmp_Verb; verifying new verbs in the Tmp_Verb, to form a result assembly VerbResult; outputting a new verb assembly VerbResult. The method uses information of words in a Chinese seed dictionary and identifies new verbs which are obtained from Chinese corpus. After test and verification of 160 GB plain text corpus, the system obtains 41012 new Chinese verbs. Through accuracy analysis, a result shows that 96.9% new verbs are correct Chinese verbs.

Description

technical field [0001] The invention relates to the fields of Chinese natural language processing and automatic recognition of Chinese verbs, in particular to a method for automatic recognition of new Chinese verbs. Background technique [0002] With the development of the Internet, especially the rapid development of the mobile Internet, netizens are often not satisfied with traditional Chinese dictionaries when using Chinese, but invent some new words by themselves. This brings new challenges to the development of Chinese application systems. [0003] On the other hand, almost all Chinese application systems involve verbs, that is, verbs are the key in language application. In fact, since the case grammar was proposed, various verb-centric methods and systems have emerged. For example, the development of the Chinese treebank in my country and the UPenn treebank in the United States are inseparable from the recognition of verbs. At the same time, in the process of supple...

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 Patents(China)
IPC IPC(8): G06F40/284G06F40/242
Inventor 王卫明符建辉
Owner 中科国力(镇江)智能技术有限公司