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

Synonymous sentence conversion method based on deep text matching

A conversion method and technology of synonymous sentences, applied in the field of deep learning, can solve the problems of high labor and material cost, weak model generalization ability, manual definition, etc., achieving less labor and material resources, saving labor and material resources, and short feature selection process. Effect

Inactive Publication Date: 2019-11-15
INSPUR ARTIFICIAL INTELLIGENCE RES INST CO LTD SHANDONG CHINA
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Since the traditional method needs to manually define and extract features, it takes a lot of manpower and material resources to extract a small number of effective features.
It is difficult for traditional models to discover features with unclear meanings, and the generalization ability of the model is not strong

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
  • Synonymous sentence conversion method based on deep text matching
  • Synonymous sentence conversion method based on deep text matching
  • Synonymous sentence conversion method based on deep text matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In order to enable those skilled in the art to better understand the solution of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. Apparently, the described embodiments are only some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0031] Synonym conversion is a hot field in natural language processing. When it is necessary to cite documents, it is very important to master the skill of converting synonymous sentences. Accurately and completely paraphrasing the required cited documents is often the key to writing various papers. However, it is very difficult to master the skill of converting synonymous sentences, especially when citing f...

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 synonymous sentence conversion method based on deep text matching. The implementation process of the method comprises the following steps: firstly, acquiring any two texts, analyzing words of the two texts, matching short sentences structurally through the words, then applying the short sentences to sentence patterns longer than the short sentences, concluding matching information, generating a matching degree, and finally outputting the two texts with the highest matching degree as synonymous sentences. Compared with the prior art, the synonymous sentence conversionmethod based on deep text matching has the advantages that semantic interaction is performed on input sentence patterns on the basis of a text matching model based on deep learning, and then the optimal synonymous sentence patterns are output according to the matching degree; compared with an existing synonymous sentence conversion method, the synonymous sentence conversion method has the advantages that more manpower and material resources are saved, the cost for manually extracting the features is low, and the features with unobvious meanings implied in a large amount of data are easier to discover.

Description

technical field [0001] The invention relates to the technical field of deep learning, in particular to a synonym conversion method based on deep text matching with strong practicability. Background technique [0002] Synonymous sentences (synonymous sentences) are also called "synonymous sentences". A group of sentences with different syntactic structures but the same propositional meaning. For example, "Old Zhang criticized Xiao Wang", "Old Zhang criticized Xiao Wang", "Xiao Wang was criticized by Lao Zhang", these three sentences are synonymous sentences. Synonymous sentences can be converted to each other without changing the meaning of the proposition; if the meaning of the proposition is different before and after the conversion, it is not a synonymous sentence. Synonymous sentences are also called paraphrased sentences in semantics, and the conversion relationship between certain types of formal structures can be established by means of syntactic paraphrase. [0003...

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): G06F16/33G06F17/27G06K9/62
CPCG06F16/3344G06F18/214
Inventor 汝佩哲李锐于治楼
Owner INSPUR ARTIFICIAL INTELLIGENCE RES INST CO LTD SHANDONG CHINA
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