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

Extraction method of sensitive characteristics of Chinese language multi-word expression comprising loose structure

A sensitive feature and loose technology, applied in the computer field, can solve problems such as reduced computing efficiency and increased complexity, and achieve the effect of reducing complexity and improving computing efficiency

Active Publication Date: 2013-10-23
SUZHOU VOCATIONAL UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] There is a problem with the above algorithm, that is, even if a certain attribute has no effect in extracting a multi-word expression (the weight is 0), the value of the feature must be calculated, which will inevitably lead to a decrease in computational efficiency and an increase in complexity

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
  • Extraction method of sensitive characteristics of Chinese language multi-word expression comprising loose structure
  • Extraction method of sensitive characteristics of Chinese language multi-word expression comprising loose structure
  • Extraction method of sensitive characteristics of Chinese language multi-word expression comprising loose structure

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] The preferred embodiments of the present invention are described in detail below, so that the advantages and features of the present invention can be more easily understood by those skilled in the art, so as to define the protection scope of the present invention more clearly.

[0022] Embodiments of the invention include:

[0023] A method for extracting sensitive features of Chinese multi-word expressions containing loose structures, the steps are as follows:

[0024] (1) Sensitive feature set of multi-word expression with compact structure

[0025] The researchers have done a lot of research on the compact structure. This project combines the compact structure features used in previous studies to determine the sensitive feature set of the compact structure, and then selects the features that are sensitive to the compact structure extraction from this feature set. . Feature set with Φ(g i )express. The current part of speech has been defaulted to be a multi-word e...

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 an extraction method of sensitive characteristics of Chinese language multi-word expression comprising a loose structure. The extraction method comprises the following steps that 1), in a sensitive characteristic set of multi-word expression in a compact structure, some characteristic which can improve an extraction result of the multi-word expression is regarded as the characteristic set of the multi-word expression, and the characteristic set is shown as phi(gi); 2), in a sensitive characteristic set of the multi-word expression in the loose structure, various characteristics combining word lists, rules, templates and semantic characteristics by statistical information and a manpower summary serve as a characteristic set of the loose structure, and the characteristic set is shown as phis(gi); and 3), the sensitive characteristic selects an algorithm, and sensitive characteristic selection means that a characteristic subset which is the most efficient and has a greatest influence on a classification effect is selected from all the characteristics. With the adoption of the mode, a various-characteristic combined strategy combining various characteristics such as the word lists, the rules, the templates and the semantic characteristics by the statistical information and the manpower summary can be adopted, so that the sensitive characteristic sets suitable for different structures can be further obtained, the computation efficiency can be improved, and the complexity can be reduced.

Description

technical field [0001] The invention relates to the field of computers, in particular to a method for extracting sensitive features of Chinese multi-word expressions containing loose structures. Background technique [0002] The features used in the extraction process of multi-word expressions have a significant impact on the extraction results. There are many types of multi-word expressions in Chinese, and the sensitive features of different types of multi-word expressions are also different. [0003] Due to the complexity of Chinese language phenomena and the variety of phrase structures in Chinese multi-word expressions (as shown in Table 1), this project studies the most important and typical types of multi-word expressions. [0004] Table 1: Types of multi-word expressions with compact structure and loose structure to be extracted in this project [0005] [0006] The so-called "sensitive features" refer to the features that play a decisive role in chunk recognitio...

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 梁颖红
Owner SUZHOU VOCATIONAL UNIV