Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Context-aware dual-attention natural language inference method

A natural language and context-aware technology, applied in the field of deep learning and natural language understanding, can solve the problems of not using sentence context information, lack of accurate understanding of sentence semantics, etc.

Active Publication Date: 2020-08-25
UNIV OF SCI & TECH OF CHINA
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The above-mentioned natural language reasoning methods all focus on mining the information of the sentence itself. Under actual conditions, the same sentence can express different meanings according to different situations. These methods do not use the context information of the sentence, so they lack the ability to understand the sentence Accurate understanding of semantics

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
  • Context-aware dual-attention natural language inference method
  • Context-aware dual-attention natural language inference method
  • Context-aware dual-attention natural language inference method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The following describes the technical solutions in the embodiments of the present invention clearly and completely with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

[0020] The embodiment of the present invention provides a dual-attention natural language reasoning method for situational awareness, such as figure 1 As shown, it mainly includes:

[0021] Step 11. Obtain images with heterogeneous data and corresponding natural language sentence pairs containing contextual information.

[0022] In the embodiment of the present invention, the heterogeneous data of each sample includes: natural language premise sen...

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 context-aware double-attention natural language reasoning method. For natural language sentence pairs with context information, a multi-modal learning method and an attention mechanism are used to make full use of text and image information, thereby improving Accurately understand the semantics expressed by the sentence and the interaction between the two sentences under such semantics, and then accurately judge whether there is a reasoning relationship between the two sentences. There are disadvantages of methods that do not take into account the context in which sentences are placed.

Description

Technical field [0001] The present invention relates to the technical field of deep learning and natural language understanding, in particular to a dual attention natural language reasoning method for situational awareness. Background technique [0002] Natural Language Inference (NLI) is an important part of the field of natural language understanding. The main problem to be solved is to determine whether the Hypothesis Sentence can be inferred from the Premise Sentence. Therefore, one of the primary problems to be solved by natural language reasoning is the understanding of sentence semantics, which helps machines understand the multiple ways of expressing the same meaning by humans; secondly, compared to other problems in the field of natural language understanding, such as dialogue systems, question and answer The system not only needs to understand semantics, but also needs to take into account the reliability and stability of the generation process. Natural language underst...

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): G06F40/30G06N5/04G06N3/04G06N3/08
CPCG06N5/04G06N3/08G06F40/30G06N3/044G06N3/045
Inventor 陈恩红刘淇张琨吕广奕吴乐
Owner UNIV OF SCI & TECH OF CHINA
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
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