Learning by imitation dialogue generation method based on generative adversarial networks

A network and generator technology, which is applied in neural learning methods, biological neural network models, special data processing applications, etc., can solve the problems of high proportion of sentences and high frequency of generating general sentences, so as to improve the frequency and increase the diversity , avoid time-consuming and labor-intensive effects

Active Publication Date: 2018-11-02
TONGJI UNIV
View PDF4 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing dialogue generation models based on generation methods often have problems such as a high proportion o

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
  • Learning by imitation dialogue generation method based on generative adversarial networks
  • Learning by imitation dialogue generation method based on generative adversarial networks
  • Learning by imitation dialogue generation method based on generative adversarial networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0039] The present invention relates to a kind of imitation learning dialogue generation method based on confrontation generation network, comprising the following steps:

[0040] 1) Establish a corresponding type of expert corpus.

[0041] 2) Establish an adversarial generation network (GAN) including a generator and a discriminator. The generator (Generator) in GAN is composed of a pair of encoder (Encoder) and decoder (Decoder). The discriminator in GAN is composed of A classifier composed of a feed-forward neural network.

[0042] The form of the optimal solution of the classifier is as follows:

[0043]

[0044] Among them, p data (x) is the real sample distribution from the expert corpus, its label can be set to 1; p gis the sample distribution from the fake corpus, and its label can be set to 0; G represents the generator in GAN, and D represents the discriminator in GAN.

[0045] The purpose of the generator is: the encoder uses the cyclic neural network (RNN) o...

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 relates to a learning by imitation dialogue generation method based on generative adversarial networks. The method comprises the following steps: 1) building a dialogue statement expertcorpus; 2) building the generative adversarial network, wherein a generator in the generative adversarial network comprises a pair of encoder and decoder; 3) building a false corpus; 4) performing first classification training for a discriminator; 5) inputting an input statement into the generator, and training the encoder and the decoder in the generator through a reinforcement learning architecture; 6) adding an output statement generated in the step 5) into the false corpus, and continuing training the discriminator; 7) alternatively performing training of the generator and training of thediscriminator through a training mode of the generative adversarial network, until that the generator and the discriminator both are converged. Compared with the prior art, the method provided by theinvention can generate the statements more similar as that of human and avoid emergence of too much general answers, and can promote training effects of a dialogue generation model and solve a problemof extremely high frequency of the general answers.

Description

technical field [0001] The invention relates to dialogue generation research technology in the field of artificial intelligence and cognitive computing, in particular to a dialogue generation method for imitation learning based on an adversarial generation network. Background technique [0002] The Internet has become a very important information dissemination tool in the world, and there is great value in its massive text data. Dialogue systems, also known as interactive conversational agents, virtual agents, or chatbots, have a wide range of applications, such as technical support services, language learning tools, personal assistants, and more. As an important interactive interface to realize natural language understanding and embody machine intelligence, dialogue system has received extensive attention. At present, how to enable machines to have continuous, meaningful, and personalized dialogues with humans is one of the important issues to be solved in the field of dia...

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): G06N3/04G06N3/08G06F17/30
CPCG06N3/08G06N3/044G06N3/045
Inventor 向阳赵宇晴张默涵
Owner TONGJI 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