Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method and system for automatic identification of relative words in complex sentence of modern Chinese language

A modern Chinese, automatic recognition technology, applied in the field of automatic recognition research and application, can solve the problems of research and application gaps in the automatic recognition of compound sentence relative words, and achieve the effect of promoting research

Inactive Publication Date: 2013-11-27
HUAZHONG NORMAL UNIV
View PDF1 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0017] Although fruitful results have been achieved in the research of rule-based application systems at home and abroad, the research and application of applying rules to the automatic recognition of relative words in complex sentences is still blank.

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
  • Method and system for automatic identification of relative words in complex sentence of modern Chinese language
  • Method and system for automatic identification of relative words in complex sentence of modern Chinese language
  • Method and system for automatic identification of relative words in complex sentence of modern Chinese language

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0103] Example 1: "'Electric Mattress' not only Can dispel cold and relieve fatigue, eliminate moisture, and still Ideal household medical appliance. "

[0104] The specific implementation steps for identifying relative words for the above-mentioned input complex sentences are as follows:

[0105] (1) The result after calling ICTCLAS for the word segmentation of the above-mentioned complex sentence S input is as follows:

[0106] " / w electric heating / n mattress / w" / w not only / c can / v drive cold / vrelieve fatigue / an, / w eliminate / vmoisture / n, / w but also / c / d is / videal / a / uHousehold / bMedical / nAppliance / n. / w

[0107] (2) Invoke the "word segmentation and quasi-relative word automatic recognition system", and analyze the characteristics of complex sentences, and mark the serial number, quasi-relative word, part of speech, initial character, termination character, and full stop of each participle, among which the quasi-relative word The relational words are obtained according ...

example 2

[0128] Example 2: According to the survey, the situation reflected in the letters from readers not only exists in the above-mentioned areas, but also in the three towns of Hankou, Wuchang, and Hanyang in this city, and even suburban counties and market towns also have such barbecue stalls.

[0129] (1) Segment the complex sentences and get the part-of-speech tagging results as follows:

[0130] / wAccording to / p investigation / vn, / w readers / n letters / n / u reflect / u’s / u situation / n of / v, / w not only / c the above / b location / n has / v, / w and / c This city / r Hankou / ns, / w Wuchang / ns, / w Hanyang / nr three / m towns / n each / r urban area / n all / d has / v, / w even / c suburban counties / ncounty / n And market towns / nr also / d have / vthis / r class / q barbecue / vn stalls / n. / w

[0131] (2) Call "participle and quasi-relative words automatic recognition system", and carry out complex sentence feature analysis, the sequence number, word form, part of speech, quasi-relative words, type, start charac...

example 3

[0145] Example 3: Regardless of whether it is windy or rainy, or snowy and icy, he does not change his own schedule and arrives at the construction site half an hour earlier.

[0146] (1) Segment the complex sentences and get the part-of-speech tagging results as follows:

[0147] No matter / c is / v windy / v raining / v, / w or / c snowing / v icing / v, / w he / r will / d not / d change / v from / p fixed / v / u schedule / n, / w arrive at / v construction site / n ahead of schedule / v half an hour / m / n. / w

[0148] (2) Call "participle and quasi-relative words automatic recognition system", and carry out complex sentence feature analysis, the sequence number, word form, part of speech, quasi-relative words, type, start character, end character, sentence index number of each participle , number of repetitions and whether they are related words etc. are marked out, wherein the quasi-related words (whether they are quasi-related words) are obtained according to the "relational word ontology knowledge bas...

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 method and system for automatic identification of relative words in a complex sentence of the modern Chinese language. The method for automatic identification of the relative words in the complex sentence of the modern Chinese language comprises the steps of (1) calling the automatic word segmentation software to carry out automatic word segmentation processing and part-of-speech tagging processing on the input complex sentence of the modern Chinese language; (2) carrying out identification of quasi-relative words on the complex sentence of the modern Chinese language, wherein word segmentation and part-of-speech tagging have been carried out on the complex sentence of the modern Chinese language; (3) searching for and calling related rules in a rule base in sequence according to the quasi-relative words, according to each called rule, firstly, extracting the constraint type and the constraint condition of each rule, and then carrying out characteristic analysis on the complex sentence with the quasi-relative words according to the constraint conditions; (4) determining whether the quasi-relative words are matched with the constraint conditions of the called rules or not according to the result of characteristic analysis judgment carried out on the complex sentence with the quasi-relative words; (5) judging whether the corresponding quasi-relative words are real relative words according to the conclusion parts of the corresponding rules when the quasi-relative words are completely matched with the constraint conditions of the called rules; (6) outputting the identification result of the relative words of the complex sentence of the modern Chinese language.

Description

technical field [0001] The invention relates to the technical field of automatic processing of Chinese information, in particular to the research and application of automatic recognition of relative words in modern Chinese complex sentences. Background technique [0002] Now people generally divide the process of Chinese information processing into three stages: word processing stage, word processing stage and sentence and discourse processing stage. [0003] At present, my country has made breakthroughs in the processing of characters and words, and Chinese information processing is struggling to move towards the stage of sentence and discourse processing. "Sentence processing" is mainly divided into single sentence processing and complex sentence processing. At present, more researches are on single sentence processing, such as the Language Technology Platform (LTP) of Harbin Institute of Technology, the Syntax Treebank of Peking University, and the Concept Hierarchy Netwo...

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
Inventor 胡泉胡金柱杨进才李源舒江波谢芳肖明邓沌华
Owner HUAZHONG NORMAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com