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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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