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

Emotion controllable reply generation method using fine tuning and reordering strategies

A reordering and emotion technology, applied in the field of artificial intelligence, can solve the problems of inconsistency between the emotion of the generated reply and the specified emotion, low-quality safe reply, and small amount of information, so as to achieve strong language modeling ability, increase probability, and increase probability. Effect

Active Publication Date: 2021-07-20
INNER MONGOLIA UNIV OF TECH
View PDF10 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the shortcomings of the above-mentioned prior art, the object of the present invention is to provide a method for generating emotionally controllable responses using fine-tuning and reordering strategies. Reply, the lack of emotion control method in the dialogue generation model leads to the problem that the emotion of the generated reply is inconsistent with the specified emotion, and the "pre-training + fine-tuning" strategy is applied to the generation of emotion controllable reply

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
  • Emotion controllable reply generation method using fine tuning and reordering strategies
  • Emotion controllable reply generation method using fine tuning and reordering strategies
  • Emotion controllable reply generation method using fine tuning and reordering strategies

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The implementation of the present invention will be described in detail below in conjunction with the drawings and examples.

[0039]The present invention is an emotion controllable reply generation method, mainly designing a fine-tuning algorithm to fine-tune the pre-training model to increase the probability of the model outputting the same type of emotion, alleviating the problem of low quality reply content and safe reply, and designing an emotion sorting algorithm to model Output statement builds. The present invention specifically adopts the method of "pre-training + fine-tuning" based on a large-scale pre-trained language model, improves the "fine-tuning" strategy in the "pre-training + fine-tuning" method, and adds a new "reordering" strategy. The improved "fine-tuning" strategy adjusts the pre-training model to make the language model learn the semantics and emotional dependencies; The reply sentence with the closest category is used as the final generated rep...

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

A sentiment controllable reply generation method utilizing a fine tuning and reordering strategy comprises the following steps: training a large-scale open domain language pre-training model GPT-2 by utilizing a fine tuning algorithm, namely training the GPT-2 by using open domain multi-round dialogue corpora with sentiment category labels; enabling a language model to learn a dependency relationship between semantics and emotions in a mode of carrying out mixed training on dialogue statements and corresponding emotion category labels; an EmoGPT model is obtained, and the EmoGPT model is utilized; and according to a specified emotion category label, performing emotion reordering on the generated K replies to obtain a final generated reply. According to the method, the problem that the emotion of the generated reply is inconsistent with the specified emotion due to the lack of an emotion control method in the dialogue generation model under the condition of multiple rounds of dialogues is solved, the emotion controllable reply generation of the multiple rounds of dialogues is realized, and the emotion consistency of the reply generated by the dialogues is improved.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence and relates to the generation of emotional dialogues, in particular to an emotion controllable reply generation method using fine-tuning and reordering strategies. Background technique [0002] Dialogue generation refers to the generation of reply sentences word by word or word by word according to the given dialogue context. The most basic requirement for the generated reply statement is that the grammar is correct and the language expression is natural and fluent. Emotional dialogue generation puts higher requirements on the reply sentences generated by the model. In addition to meeting the basic grammar and language expression requirements, it also needs to be full of emotion. The emotional controllability of generated responses is an important research direction in emotional dialogue generation. [0003] Previous research work was mainly based on the Seq2Seq model, which impr...

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): G06F16/332G06F16/33G06F16/338G06N3/04G06N3/08
CPCG06F16/3329G06F16/3344G06F16/338G06N3/084G06N3/045
Inventor 杜宝祥马志强王春喻贾文超
Owner INNER MONGOLIA UNIV OF TECH
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