Deep learning problem classification method and system combining multi-level attention mechanism

A deep learning and problem classification technology, applied in the field of information processing, can solve the problem that the classification method cannot integrate the feature extraction capabilities of the two models well

Active Publication Date: 2018-11-13
HEFEI UNIV OF TECH
View PDF5 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Second: The existing problem classification methods cannot well integrate the feature extraction capabilities of the two models

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
  • Deep learning problem classification method and system combining multi-level attention mechanism
  • Deep learning problem classification method and system combining multi-level attention mechanism
  • Deep learning problem classification method and system combining multi-level attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] Specific embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described here are only used to illustrate and explain the present invention, and are not intended to limit the present invention.

[0054] Question classification is a basic part of question answering system research, and its accuracy directly affects the system's ability to understand natural language. On the one hand, question classification can provide semantic restrictions and constraints for subsequent information retrieval and answer extraction by determining the target answer type of the question, narrowing the search range of candidate answers, and improving the accuracy of the question answering system. For example, "Where is the most famous Anhui cuisine restaurant?" is a question about the location. When the subsequent answer is extracted, it only needs to match the location type ...

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 deep learning problem classification method combining a multi-level attention mechanism, and relates to the field of information processing technology. The deep learning problem classification method comprises the following steps: constructing an interrogative word vector set, wherein the interrogative word vector set includes interrogative word vectors and common word vectors including interrogative word information; extracting window mapping of interrogative sentences by convolution operation according to the interrogative word vector set; extracting sequential characteristics of the interrogative sentences according to the window mapping; and classifying the interrogative sentences according to the sequential characteristics. Through adoption of the method, semantic information of interrogative words in the interrogative sentences is enhanced. Moreover, a convolutional neural network and a long-term and short-term memory model are fused through the attention mechanism in deep learning, thereby effectively increasing the accuracy of problem classification.

Description

technical field [0001] The present invention relates to the technical field of information processing, in particular to a deep learning problem classification method and system combined with a multi-level attention mechanism. Background technique [0002] There are two main types of traditional problem classification methods, one is rule-based methods, and the other is machine learning-based methods. The rule-based method mainly builds a large number of rule bases manually, and adopts the method of rule matching to realize problem classification. The method based on machine learning regards question classification as a supervised learning task, expands the question text by manually formulating features and introducing external corpus, and uses classic support vector machines, naive Bayesian and other machine learning algorithms to classify . [0003] In recent years, due to the maturity of deep learning technology, the problem classification method based on machine learnin...

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): G06F17/30G06F17/27
CPCG06F40/289
Inventor 余本功许庆堂陈杨楠陈能英
Owner HEFEI UNIV OF 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap