A method and system for dialogue reply generation based on self-comment sequence learning

A technology of sequence and computer system, applied in the field of dialogue reply generation based on self-comment sequence learning, can solve the problems of difficult initialization strategy, mismatch of objective functions, huge word space, etc., to improve the efficiency of text generation and reduce the word search space. Effect

Active Publication Date: 2021-11-19
ZHEJIANG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this technology still has some inherent defects: one is the generation distribution deviation, that is, the dialogue generation distribution on the training set and the test set is likely to be different
Second, the objective function does not match, and it is impossible to directly optimize the evaluation index during the training process.
However, there are still thorny problems in the dialogue reply generation algorithm based on reinforcement learning: one is based on the minimum batch gradient descent method, there are a lot of changes, if it is not well regularized, it is easy to become unstable; Under the characteristics of learning, the word space of text generation becomes extremely large, and it is difficult to get a good initialization strategy

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
  • A method and system for dialogue reply generation based on self-comment sequence learning
  • A method and system for dialogue reply generation based on self-comment sequence learning
  • A method and system for dialogue reply generation based on self-comment sequence learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] The present invention will be further elaborated and illustrated below in conjunction with the accompanying drawings and specific embodiments.

[0063] Such as figure 1 As shown, the present invention divides the encoder-decoder framework into a training module and a testing module, and puts these two modules into the optimization process of the whole model synchronously. Among them, (a) module is a training module, (b) module is a testing module, and the specific steps are as follows:

[0064] (a) Use cross entropy to learn the generation probability between each word in the text generation training process, the basic steps are as follows:

[0065] 1. Initialize the model parameters. For each sentence input, there is a start character , and initialize the hidden state h 0 and unit c 0 as input.

[0066] 2. For each unit, enter the hidden state h of the previous unit i and c i , and the newly entered word w i , after the learning of the recurrent neural ...

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 dialogue reply generation method and system based on self-comment sequence learning, wherein the dialogue reply generation method includes the following steps: (1) modeling the context of the current dialogue to obtain a contextual semantic vector; (2) ) According to the context semantic vector, establish a dialogue model based on self-review sequence learning; (3) train and test the dialogue model, and obtain the training reward value and test reward value respectively; (4) calculate the difference between the two reward values, Optimize the dialog model by calculating the policy gradient; (5) After the dialog model is trained, output the dialog reply. Utilizing the present invention, the dialog generation model can generate more substantive replies toward the direction of optimizing the evaluation index during the training process, and greatly reduce the instability of generated dialogs.

Description

technical field [0001] The invention relates to the field of natural language processing dialog systems, in particular to a method and system for generating dialog replies based on self-comment sequence learning. Background technique [0002] In recent years, dialogue systems, as an important technical support for human-computer interaction, have attracted the attention of researchers from industry and academia. Dialogue reply generation has always been one of the most popular and difficult tasks in dialogue systems. Dialogue reply generation technology, that is, given the specific context and the current chat dialogue given by the other party, the machine can generate a reply that conforms to the context and has substantive reply content through semantic understanding and semantic generation technology. This technology has been widely used in many human-computer interaction systems, such as intelligent customer service systems, chat robots, personal intelligent assistants,...

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): G06F16/332
Inventor 陈哲乾蔡登杨荣钦潘博远赵洲何晓飞
Owner ZHEJIANG 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