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

Method and system for eliminating ambiguity for word meaning by computer, and search method

A computer processing and word meaning technology, applied in the computer field, can solve problems such as high cost, high cost, and complexity, and achieve the effects of fast operation, reduced information volume, and reduced retrieval complexity

Active Publication Date: 2008-12-31
BEIJING XUEZHITU NETWORK TECH
View PDF0 Cites 27 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Moreover, the current existing word sense disambiguation technology is usually more complicated, and the implementation cost is high, and the cost is high.

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 eliminating ambiguity for word meaning by computer, and search method
  • Method and system for eliminating ambiguity for word meaning by computer, and search method

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0055] In order to disambiguate the meaning of words, first of all, the system core concern words in the article should be selected. The system core concerned words refer to the ambiguous words concerned in the system that need to be disambiguated. like figure 1 As shown, the method of selecting the core concern words of the system and disambiguating is as follows:

[0056] Step 101: establish a word meaning dictionary, which contains almost all Chinese vocabulary and the meanings corresponding to these words; establish an article database;

[0057] Step 102: Select all the sentences containing a vocabulary in the article database, each sentence containing the vocabulary is called a corpus of the vocabulary, mark the meaning of the vocabulary in each corpus, and a vocabulary can have multiple The word meaning option is the meaning item, and mark the meaning of all or part of the words in the article database in this way;

[0058] When labeling, only distinguish the meanings...

no. 2 example

[0097] When the word sense disambiguation method of the present invention is applied to the technical field of retrieval, its steps are as follows:

[0098] Firstly, similar to the steps 101-103 above, an ambiguous word classification model is generated.

[0099] When retrieving, the search sentence input by the user is received, and the search keywords are extracted from the search sentence. The retrieval keywords here are the same as the system core attention words in the above word sense disambiguation method, and the method of extracting retrieval keywords is the same as the method for extracting the system core attention words in the above word sense disambiguation method.

[0100] Using existing retrieval methods, all texts containing the retrieval keywords are retrieved as preliminary retrieval results.

[0101] Determine whether the retrieval keyword is an ambiguous word, and if so, use the method of step 106 above to disambiguate the retrieval keyword (ambiguous word...

no. 3 example

[0109] This embodiment is another retrieval implementation. Firstly, an ambiguous word classification model is generated in the same way as the above steps 101-103.

[0110] When retrieving, the user adds background feature words for determining the meaning of the retrieval keyword to a retrieval keyword input, that is, the retrieval keyword is used as an ambiguous word to disambiguate the meaning of the word;

[0111] Select the background feature words of the retrieval keyword saved in the ambiguous word classification model from the input background feature words, and calculate the weight of all the selected background feature words for the meaning item for each meaning item of the retrieval keyword. And, then select a meaning item as the meaning of this retrieval keyword in the same way as in the previous embodiment;

[0112] Use the existing retrieval methods to retrieve all the texts containing the retrieval keywords as the preliminary retrieval results;

[0113] Accord...

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 discloses a word-meaning disambiguation method by using a computer, a relevant system and searching method. The invention makes use of contribution degrees of background characteristic words of an ambiguous word to each meaning item to define the meaning of the ambiguous word and the computer can automatically learn disambiguation. The disambiguation realizing method of the invention is simple and high effective and can be understood easily. The experiment demonstrates that an average accuracy of the word meaning disambiguation carried out by the system can reach more than 90 percent. Simultaneously, compared with other disambiguation methods, the method can be operated more quickly and be realized more easily by the system. And the searching method adopted by the invention just shows a user the result which is identical to the meaning of the key word inputted by the user so as to largely enhance the searching efficiency.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular, to a method for disambiguating the meaning of words and a system for disambiguating the meaning of words when processing language characters with a computer. The present invention also relates to a retrieval method. Background technique [0002] In technical fields such as computer retrieval, speech recognition, and machine translation, it is necessary for computers to process text or language, so as to achieve the purpose of simulating part or even all of human language abilities with machines. After a long period of development, human language has formed its own inherent objective language laws. However, due to the large amount of ambiguity in the vocabulary in natural language, that is, the same word may have multiple meanings. Therefore, in the process of processing the language, the computer needs to learn from many items of the vocabulary according to the examples i...

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): G06F17/27G06F17/30
Inventor 刘飞潘小双吴明辉迟松涛
Owner BEIJING XUEZHITU NETWORK TECH
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