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

Method and device for extracting sentence classification features based on mixed templates

A technology that mixes templates and classification features. It is applied in text database clustering/classification, character and pattern recognition, and unstructured text data retrieval. Strong matching ability and accurate classification results

Active Publication Date: 2021-07-02
BEIJING UNISOUND INFORMATION TECH
View PDF11 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a method and device for extracting sentence classification features based on mixed templates to solve the defect that the sentence classification method is not effective

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 and device for extracting sentence classification features based on mixed templates
  • Method and device for extracting sentence classification features based on mixed templates

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The preferred embodiments of the present invention will be described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described here are only used to illustrate and explain the present invention, and are not intended to limit the present invention.

[0049] A method for extracting sentence classification features based on a mixed template provided by an embodiment of the present invention, see figure 1 As shown, including steps 101-105:

[0050] Step 101: Obtain preset text, which includes positive example text and negative example text.

[0051] In the embodiment of the present invention, the positive example text and the negative example text are selected in advance, each text contains multiple lines, and one line corresponds to a sentence (ie, a preset sentence). For example, when it is necessary to select an interrogative sentence template, the positive example text may contain multiple sentences with an in...

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 present invention provides a method and device for extracting sentence classification features based on a mixed template, wherein the method includes: obtaining preset text; analyzing and processing each preset sentence in the preset text to determine the value of the preset sentence The word parameters of each word; generate the candidate template of the preset sentence according to the word parameters of all words, the candidate template includes a word parameter of all words arranged in order; and generate a positive example template set and a negative example template set; count all candidates The number of positive and negative examples of the template, and select an effective template according to the number of positive and negative examples of the candidate template; classify the sentences to be tested according to the effective template. The effective template generated by this method can be a mixed expression of word, part of speech, named entity and syntactic dependency, which can more fully describe the language rules existing in a sentence, with stronger template matching ability and better classification effect.

Description

technical field [0001] The invention relates to the technical field of sentence template mining, in particular to a method and device for extracting sentence classification features based on mixed templates. Background technique [0002] Sentence classification is mainly to judge the type of a sentence to be tested, such as judging whether a sentence is an interrogative sentence. The current sentence classification method is mainly to train a classification model based on word or part-of-speech features, and then apply this classification model to the input sentence to be tested, and use this classification model to predict the category of the sentence to be tested. [0003] Existing methods only classify sentences based on words or part-of-speech features. The classification model used in this classification method has limited expression and matching capabilities, resulting in limited classification effects. Contents of the invention [0004] The invention provides a met...

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 Patents(China)
IPC IPC(8): G06F16/35G06K9/62
CPCG06F18/24765G06F18/214
Inventor 任禾
Owner BEIJING UNISOUND INFORMATION TECH