Open type problem automatic generation method based on a generative adversarial network

An automatic generation and open technology, applied in biological neural network models, natural language data processing, instruments, etc., can solve problems such as difficulty in generating readability, difficulty in fitting data, and divergence of answers.

Active Publication Date: 2019-04-12
PEKING UNIV +1
View PDF2 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the deficiencies in the prior art, the object of the present invention is to provide an open question automatic generation model method based on a generative confrontation network, which is used to solve the pr

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
  • Open type problem automatic generation method based on a generative adversarial network
  • Open type problem automatic generation method based on a generative adversarial network
  • Open type problem automatic generation method based on a generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] Below in conjunction with accompanying drawing, further describe the present invention through embodiment, but do not limit the scope of the present invention in any way.

[0063] The present invention provides a method for automatically generating a problem model based on a generative confrontation network, and improves the effect of automatic problem generation by adopting a generative confrontation network architecture.

[0064] figure 1 Shown is the process of the method proposed by the present invention, including: constructing an open-ended question automatic generation data set; constructing an automatic question generation model including a generator and a discriminator; and training the question automatic generation model by using an adversarial training method of enhanced learning. Specifically include:

[0065] 1) Construct open-ended questions to automatically generate data sets;

[0066] Since the field of automatic generation of open-ended que...

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 an open type problem automatic generation method based on a generative adversarial network, an established problem automatic generation model comprises a generator and a discriminator, a data set is automatically generated by constructing an open type problem, and automatic problem generation is realized by adopting a model adversarial training method of reinforcement learning. According to the method, the problems that answers are divergent and large in difference in open question generation, and efficient fitting is difficult to use with the maximum likelihood methodcan be solved, and the automatic question generation effect is improved.

Description

technical field [0001] The invention relates to the technical field of natural language computer processing, in particular to a model method for automatically generating open questions based on a generative confrontation network. Background technique [0002] Natural language generation technology is one of the important branches in the field of natural language processing technology, which aims to make computers have human-like language creation ability. Automatic question generation refers to: input a specific background corpus (such as a piece of news, a piece of opinion, etc.), the computer refines, summarizes the main information, and further outputs one or more related to the input, good readability, and practical significance. question. [0003] According to the directivity of the generated questions, automatic question generation can be divided into two categories: "closed" and "open". The automatic generation of closed questions is designed to generate fixed-point...

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): G06F16/332G06F17/27G06N3/04
CPCG06F40/289G06N3/048G06N3/044G06N3/045
Inventor 柴梓万小军谢勤也黄波李大任
Owner PEKING UNIV
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