Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A dialogue response generation method and system based on enhanced dual-channel sequence learning

A dual-channel, sequence technology, applied in the field of dialogue reply generation based on enhanced dual-channel sequence learning, can solve problems such as inability to use words

Active Publication Date: 2020-07-24
ZHEJIANG UNIV
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Each new word only uses the previously generated vocabulary, but cannot use the words that have not yet been generated

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 dialogue response generation method and system based on enhanced dual-channel sequence learning
  • A dialogue response generation method and system based on enhanced dual-channel sequence learning
  • A dialogue response generation method and system based on enhanced dual-channel sequence learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0067] The present invention will be further elaborated and illustrated below in conjunction with the accompanying drawings and specific embodiments.

[0068] Such as figure 1 As shown, the framework of the present invention is mainly divided into two parts: (a) Retouching neural network, adapted from the traditional encoder-decoder framework, adding a retouching module. (b) The new reinforcement learning module optimizes the gradient of the self-learning strategy by calculating the difference in reward values ​​obtained from training and testing. The specific steps are described as follows:

[0069] (a) Retouch the neural network, first generate a draft, and then further retouch based on the draft to obtain the final output. The basic steps are as follows:

[0070] 1. Model the context and get the context representation vector C u . where C u The acquisition of is by considering all the sentences in the context as a whole, and using the attention mechanism and deep recu...

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 reinforcement dual-channel sequence learning-based dialog reply generation method and system. The method comprises the following steps of: (1) modeling a context to obtain acontext semantic vector; (2) carrying out combined learning on a current dialog and the context semantic vector by utilizing an encoder so as to current a current dialog vector and an encoder vector;(3) inputting the context semantic vector and the current dialog vector into a decoder so as to obtain a first channel dialog reply draft and a decoder vector; (4) inputting the encoder vector, the decoder vector and the first cannel dialog reply draft into an embellishing device to carry out embellishing, so as to generate an embellished dialog reply of a second channel; (5) optimizing a target function by utilizing a reinforcement learning algorithm; and (6) ending model training and generating and outputting a dialog reply. By utilizing the method and system, dialog generation models can grasp global information more deeply, and replies more according with dialog scenes and having substantial contents can be generated.

Description

technical field [0001] The invention relates to the field of natural language processing dialogue systems, in particular to a dialogue reply generation method and system based on enhanced dual-channel sequence learning. Background technique [0002] In recent years, we have witnessed the flourishing development of human-computer interaction systems. With a large number of publicly available online dialogue corpora, dialogue systems have received extensive attention from researchers in both industry and academia. The emergence of assistants such as Apple's Siri, Microsoft's Cortana and Xiaoice chatbots have brought computer-computer interaction systems into thousands of households. The main research field of the present invention is the most core technology in the dialogue system—dialogue reply generation. Given the dialogue context, the model is required to automatically generate dialogue responses that conform to normal chat logic based on the current dialogue content. A...

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): G06F16/332G06F40/30
CPCG06F40/30
Inventor 陈哲乾蔡登赵洲何晓飞
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap 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