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

A Chinese abstract generation method and device based on a generative adversarial network

A technology of abstract and Chinese, applied in the field of Chinese abstract generation based on generative adversarial network, can solve the problem of inconsistency of actual evaluation indicators of optimization methods, and achieve the effect of reducing the appearance of unregistered words, high performance, and reducing dictionary

Active Publication Date: 2019-05-17
INST OF INFORMATION ENG CAS
View PDF5 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problem of inconsistency between the optimization method and the actual evaluation index, the present invention proposes a method and device for generating a Chinese abstract based on a generative confrontation network

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 Chinese abstract generation method and device based on a generative adversarial network
  • A Chinese abstract generation method and device based on a generative adversarial network
  • A Chinese abstract generation method and device based on a generative adversarial network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] In order to make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below through specific embodiments and accompanying drawings.

[0044] In the method for generating a Chinese abstract based on a generative confrontation network in this embodiment, the abstract generation process is as follows figure 1 shown, including the following steps:

[0045] Step 1. Perform data preprocessing operations such as word segmentation, stop words removal, and special word marking on the given Chinese data set, and divide the data into training set, verification set and test set after shuffling.

[0046] Step 2, build a Chinese abstract generation model based on GAN, and use the training set in step 1 to train the Chinese abstract generation model.

[0047] Step 3: After the training of the Chinese summary generation model is completed, use the test set to test the performance of the model...

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 Chinese abstract generation method and device based on a generative adversarial network. The method comprises the following steps of 1) carrying out preprocessing operationon a given Chinese data set to form a training set; 2) constructing a Chinese abstract generation model based on the generative adversarial network, and training the Chinese abstract generation modelby using the training set; and 3) inputting the Chinese text to be subjected to abstract generation into the trained Chinese abstract generation model to obtain a corresponding abstract. According tothe method, a discriminator is used for minimizing errors to replace a framework with the maximum abstract generation probability; particularly, a discriminator composed of three LSTMs is designed, features can be better captured, and the classification effect is assisted; and the efficiency of the text abstract can be effectively improved by using characters as units and combining contexts. According to the method, the abstract of the large-scale Chinese text can be automatically generated, and the generated abstract is more natural and coherent and has readability.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence and deep learning, and in particular relates to a method and device for generating a Chinese abstract based on a generative confrontation network. Background technique [0002] With the advent of the era of big data, Internet information is growing exponentially, especially text information. How to quickly obtain key information from redundant texts is very important. However, constructing summaries manually is expensive and impractical. Therefore, it is of practical value to construct an automatic summarization system with low cost, large scale and high efficiency. [0003] The current Chinese summarization methods can be divided into "extractive summarization" and "generative summarization". Extractive summary methods include classification-based Bayesian, maximum entropy, and SVM, and graph-based TextRank and LexRank methods. Since generative summarization is generated based...

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): G06F16/34G06F16/35
Inventor 曹亚男徐灏尚燕敏刘燕兵谭建龙郭莉
Owner INST OF INFORMATION ENG CAS
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