A method and device for identifying semantic relations of Chinese words based on multiple Chinese knowledge resources
A technology of relationship recognition and semantic relationship, applied in semantic analysis, natural language data processing, instruments, etc., can solve problems such as difficulty in guaranteeing accuracy and ignoring the mining and utilization of other language knowledge resources, so as to improve adaptability, improve accuracy, The effect of high recognition accuracy
Active Publication Date: 2022-04-15
南方电网互联网服务有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Existing research work only uses a certain kind of knowledge resources, but ignores the mining and utilization of other language knowledge resources; statistical learning methods are inevitably restricted by the size of the labeled corpus, and the accuracy is difficult to guarantee
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0060] In order to better understand the embodiments of the embodiments of the present invention, the following detailed description will be described in connection with the accompanying drawings and embodiments.
[0061] Semantic recognition processing is performed in words with the word "motor vehicle" and the word B "truck".
[0062] The embodiment of the present invention is based on a plurality of Chinese-speaking semantics recognition methods, such as figure 1 As shown, including the following steps:
[0063] Step 101, antisense relationship recognition.
[0064] Combined with a variety of Chinese knowledge resources to obtain antisense words, determine whether the word semantic relationship is antisense according to the antonym collection, specifically:
[0065] Step 1-1) Use the antisense relationship of the display in the HowNet, the antisense word collection ASET for the given words A and B A Extract, if b∈aset A Then there is a replied relationship between two words, ot...
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
Login to View More Abstract
The invention discloses a Chinese word semantic relationship recognition method and device based on various Chinese knowledge resources. The method includes: combining multiple Chinese knowledge resources to obtain an antonym set, and judging whether the semantic relationship between words has an antonym relationship according to the antonym set; using multiple Chinese knowledge resources to extract a partial word set, and judging whether there is a whole-part relationship between words according to the partial word set ; Use a variety of Chinese knowledge resources to extract synonym sets, and determine whether there is a synonymous relationship between words based on the synonym set; use a variety of Chinese knowledge resources to extract a hyponym set, and determine whether there is a hyponym relationship between words based on the hyponym set. By using the invention, the functions of various Chinese knowledge resources can be fully utilized, and the semantic relationship of Chinese words can be identified more accurately and effectively.
Description
Technical field [0001] The present invention relates to the field of natural language processing, and more particularly to a Chinese-speaking semantic relationship identification method and apparatus based on a variety of Chinese knowledge resources. Background technique [0002] Semantic relationship recognition refers to the semantic relationship between the given word pair automatically determines the word interval. Typical semantic relationships include: antisense relationship, overall partial relationship, synonymary relationship, upper and lower relationships, etc. Semantic relationship identifies the basic task in the field of natural language processing, which has a direct impact on words disambiguation, knowledge body construction, machine translation, information retrieval, text classification, etc. [0003] At present, most semantic relationship recognition research work primarily in English, usually based on one or more knowledge resources, using the support vector ma...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F40/30
CPCG06F40/284G06F40/30
Inventor 鹿文鹏孟凡擎杜月寒
Owner 南方电网互联网服务有限公司