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

Text generation method based on generative adversarial network

A network and text technology, applied in the field of text generation based on generative confrontation network, can solve the problems of limiting the potential of natural language processing and difficult training of GAN, and achieve the effect of enriching semantic and context information, increasing convergence speed, and improving structure

Inactive Publication Date: 2021-03-26
TONGJI UNIV
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The proposal of SeqGAN makes the combination of reinforcement learning and GAN applied to text generation become the focus, but due to the problem of difficult training of GAN itself, its potential in the field of natural language processing is limited.

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
  • Text generation method based on generative adversarial network
  • Text generation method based on generative adversarial network
  • Text generation method based on generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In order to make the objectives, technical solutions and advantages of the present invention clearer, the text generation method according to the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present invention, not to limit the present invention, that is, the protection scope of the present invention is not limited to the following embodiments. Appropriate changes can be made by a skilled person, and these changes may fall within the scope of the invention as defined in the claims.

[0041] like figure 1 As shown in the block diagram of the structure, according to a specific embodiment of the present invention, the following steps are included:

[0042] 1) Preprocess the short text dataset and represent it as short text vector data mainly based on word embeddings. The MS COCO short text datas...

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 text generation method based on a generative adversarial network, and relates to the field of text generation, in particular to a text generation method based on the generative adversarial network. According to the technical scheme, the truth value capable of guiding the network is obtained by utilizing the text data in the real data set, so that the purpose of increasingthe convergence rate of the generated network is achieved. According to the method, the distance between a generated text and a real text is measured by cosine distance and the like, and the distanceis added to a target function of a generated network, so that the target function is gradually optimized in the training process. Besides, a self-attention mechanism is added to the input layer to improve the structure of the discrimination network, so that the network can obtain richer semantic and contextual information, and the performance of the discrimination network is optimized. Accordingto the invention, the text data conforming to logic can be generated more stably.

Description

technical field [0001] The invention relates to the field of text generation, in particular to a text generation method based on a generative confrontation network. Background technique [0002] As an important research direction in the field of natural language processing, text generation technology has great application prospects. For example, it can be applied to intelligent question answering and dialogue, machine translation and other systems to achieve more intelligent and natural human-computer interaction; it can also replace editors with text generation systems to achieve automatic news writing and publishing. [0003] Text generation refers to the use of "machine learning + natural language processing" technology to enable computers to have human-level language expression capabilities, including machine translation, sentence generation, dialogue generation, etc. Usually, the strategy of text generation is with the help of language model, which is a probability-bas...

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): G06F40/211G06F40/30G06K9/62G06N3/04G06N3/08
CPCG06F40/211G06F40/30G06N3/049G06N3/08G06N3/045G06F18/24
Inventor 王俊丽吴雨茜韩冲张超波
Owner TONGJI 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