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

Method for recognizing domain-specific terms on basis of contextual information

A technology of contextual information and identification methods, applied in the field of ontology learning, can solve the problem of low efficiency of term extraction

Inactive Publication Date: 2017-05-31
BEIJING UNIV OF TECH
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problem of low extraction efficiency of specific domain terms in ontology learning, this invention proposes a domain term recognition method that integrates contextual information, integrates statistical and linguistic methods, and draws on traditional domain correlation and domain consistency ideas , combined with the log-likelihood ratio, describe the distribution of candidate terms in different fields from the perspective of the recurrence times of candidate term context information, then calculate the domain attribute values ​​of candidate terms, and finally extract domain terms

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 for recognizing domain-specific terms on basis of contextual information
  • Method for recognizing domain-specific terms on basis of contextual information
  • Method for recognizing domain-specific terms on basis of contextual information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0017] (1) The calculation formula adopted in the present invention is introduced

[0018] Assuming contextual information X and Y, then, the formula for calculating word form similarity between X and Y is as follows:

[0019]

[0020] Among them, CommonWord(X, Y) represents the number of identical words in X and Y, and WordNum(X) and WordNum(Y) represent the number of words contained in X and Y respectively.

[0021] Then, the word order similarity calculation formula of X and Y is as follows:

[0022] WordOrderSim(X, Y) = 1-Rev(X, Y) / MaxRev(X, Y) (2)

[0023] Among them, Rev(X, Y) and MaxRev(X, Y) respectively represent the reverse sequence number and the maximum reverse sequence number of the natural number sequence with the same number of words in X and Y.

[0024] Therefore, the calculation formula of contextual similarity ...

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 for recognizing domain-specific terms on the basis of contextual information, and aims to solve the problem that term extraction efficiency is low in the specific field in ontology learning. The method comprises the following steps: describing distribution conditions of candidate terms in different fields in the aspect of repetition times of the contextual information of the candidate terms by integrating statistics and linguistics methods on the basis of dependency of the traditional fields and field consistency thinking through log-likelihood ratio; then calculating field attribute values of the candidate terms; and finally, extracting a field term according to the field attribute value of each candidate term. By the method for recognizing domain-specific terms on the basis of the contextual information, quite good term extraction accuracy can be obtained. The method not only can be used in term extraction in the fields such as anti-depression drugs, but also can be used as a candidate concept generation tool in a concept extracting method.

Description

technical field [0001] The invention relates to term extraction in the field of ontology learning, in particular to term extraction in the field of depression medicine. [0002] technical background [0003] Ontology has shown excellent performance in solving problems such as knowledge representation, knowledge organization and knowledge sharing. Therefore, it is widely used in information technology, artificial intelligence, knowledge engineering, knowledge management, information retrieval and other fields, especially the emergence of Semantic Web. , which makes Ontology propose a new solution for Web information sharing and brings broad prospects for its development. Ontology, as a clear specification of conceptual model, is a relational model between concepts. As a description of concepts, terms can be used to represent instances of concepts, so ontology term extraction becomes the primary task of ontology construction, which is of great significance to ontology learning...

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
IPC IPC(8): G06F17/27G06K9/62
CPCG06F40/289G06F40/247G06F18/22
Inventor 董广场陈建辉钟宁
Owner BEIJING UNIV OF TECH