Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for improving sentence similarity accuracy judgment

A sentence similarity and accuracy technology, applied in the direction of instruments, semantic analysis, text database query, etc., can solve the problems that it is difficult to meet the requirements of users, the similarity cannot be calculated correctly, and the recognition of sentence similarity is low. Improve the similarity comparison, improve the accuracy of similarity judgment, and improve the overall processing effect

Pending Publication Date: 2020-10-09
QINGDAO UNIV OF SCI & TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The method based on linguistic features can provide strong support for co-occurrence words and similarity calculation at the semantic level with the help of semantic dictionaries, but this method relies too much on semantic dictionaries, and the quality of dictionaries is uneven. The similarity of words in the dictionary is determined. For words that have not been registered in the dictionary, the similarity cannot be calculated correctly
The similarity algorithm based on word vectors takes into account the vector representation of each word at the semantic level. This algorithm not only retains the semantic characteristics of the word itself, but also breaks through the limitations of the dictionary. It is still very low, and it is difficult to meet the requirements of users in the real use environment

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 improving sentence similarity accuracy judgment
  • Method for improving sentence similarity accuracy judgment
  • Method for improving sentence similarity accuracy judgment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0039] As shown in the figure, a method for improving the judgment of sentence similarity accuracy, the specific processing steps are as follows:

[0040] 101) Preprocessing step: each word in the English sentence is separated by a space, at this time, the sentence S and the sentence T are expressed as: S(s 1 ,s 2 …s n ) and T(t 1 ,t 2 ...t r ).

[0041] 102) Extraction step: the preprocessed text sentence is obtained by using the trained word model to obtain the word vector of each word in the sentence S and the sentence T, and obtain the position code of each word in the sentence S and the sentence T, and obtain Position encoding vector.

[0042] Such as figure 1As shown, the word model includes an input layer, a hidden layer and an output layer to realize contextual word prediction target words, specifically by defining a set of voca...

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 a method for improving sentence similarity accuracy. The method comprises the following specific processing steps: 101) a preprocessing step, 102) an extraction step, 103) a normalization step, 104) a position correlation step, 105) a JS divergence processing step, 106) a word similarity processing step and 107) a final similarity acquisition step. The method for improvingthe sentence similarity accuracy is reasonable in overall processing process, high in accuracy and simple in modeling.

Description

technical field [0001] The invention relates to the field of text sentence meaning analysis, more specifically, it relates to a method for improving the judgment accuracy of sentence similarity. Background technique [0002] In the field of information retrieval, sentence similarity is an important basis to reflect whether the information requested by the user matches the information in the document, and it is widely used in text classification, automatic summarization, machine translation, intelligent question answering and other fields. Therefore, how to effectively measure the similarity between sentences has become an important research topic for scholars in related fields. [0003] At present, the research on sentence similarity can be roughly divided into the following categories: (1) methods based on co-occurrence words, which calculate the similarity by judging the number of identical words or synonyms in two sentences. (2) A method based on probability distribution...

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): G06F16/33G06F40/211G06F40/289G06F40/30G06K9/62
CPCG06F16/3344G06F40/211G06F40/289G06F40/30G06F18/22
Inventor 周艳平李金鹏朱小虎袁绍正
Owner QINGDAO UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com