Unsupervised English short text sentence running analysis method

An analysis method and unsupervised technology, applied in the creation of semantic tools, text database query, unstructured text data retrieval, etc., can solve problems such as inability to accurately analyze off-topic sentences, ignoring semantic relevance, and poor accuracy of off-topic scoring.

Active Publication Date: 2019-09-27
GUILIN UNIV OF ELECTRONIC TECH
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the traditional unsupervised English essay sentence off-topic analysis method ignores the semantic correlation between words, which leads to the inability to accurately analyze the off-topic sentence and the poor accuracy of the off-topic degree score when performing English essay sentence off-topic analysis.

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
  • Unsupervised English short text sentence running analysis method
  • Unsupervised English short text sentence running analysis method
  • Unsupervised English short text sentence running analysis method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0168] refer to Figure 1-5 , a kind of concrete implementation steps of English essay sentence off-topic analysis method are as follows;

[0169] Step 1: Execute the "English Essay Preprocessing Module"

[0170] The input English essays are taken from the English essays of Chinese students in the International Corpus of Asian English Learners. The title and content of the English essays are as follows:

[0171] The titles of English passages to be analyzed are as follows:

[0172] whether smoking should be completely banned at all the restaurants in the country

[0173] The content of the English essay to be analyzed is as follows:

[0174]Smoking is a popular activity among human beings, especially men. Butas we all know, cigarettes contain some poison, many countries have banned smoking at public places. It's not enough, stopping smoking should not only at public places but also in the restaurants. have improved that cigarette has nicotine.It's a kind of poison.People w...

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 unsupervised English short text sentence running analysis method. An analysis system is composed of an English short text preprocessing module, a multivariate semantic representation model construction module, an English short text representation model construction module and an English short text sentence running analysis module which are sequentially connected. After an English short text is processed by the analysis system, a sentence of a question running in the English short text, and a question running degree score and a comment of the sentence of the English short text can be finally obtained. According to the method, the problems that a traditional unsupervised English short text sentence running analysis method neglects semantic correlation between words, so that the running sentences cannot be accurately analyzed during English short text sentence running analysis, and the running degree score is poor are solved.

Description

technical field [0001] The invention relates to natural language processing technology, and is an unsupervised analysis method for judging whether a sentence in an English essay is off-topic. The analysis method of the invention is only suitable for analyzing English essays, but not for analyzing Chinese essays. Background technique [0002] The traditional sentence off-topic analysis methods of English essays are mainly divided into two categories, one is supervised methods and the other is unsupervised methods. The supervised method requires a large number of English texts with the same title as the English essay to be analyzed to train and build the analysis model, so as to analyze whether the sentences in the English essay are off topic; the unsupervised method only needs the title of the English essay to analyze the sentences in the English essay Is it beside the point. In the actual sentence analysis of English essays, it is difficult to collect a large number of trai...

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): G06F16/33G06F16/36G06F17/27
CPCG06F16/3344G06F16/3335G06F16/3334G06F16/36G06F40/205G06F40/253G06F40/247G06F40/289G06F40/30
Inventor 黄桂敏刘剑周娅
Owner GUILIN UNIV OF ELECTRONIC TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products