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

A Mongolian-Chinese machine translation method based on anti-neural network

A machine translation and neural network technology, applied in the computer field, can solve the problems of low parallel corpus data of neural network model, difficult machine translation system, etc.

Inactive Publication Date: 2018-11-27
INNER MONGOLIA UNIV OF TECH
View PDF2 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Especially for some small languages ​​(such as Mongolian), these problems are more prominent, and the parallel corpus data that can be used to train the neural network model is less, so it is difficult to train and build a high-quality, high-performance machine translation system

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 Mongolian-Chinese machine translation method based on anti-neural network
  • A Mongolian-Chinese machine translation method based on anti-neural network
  • A Mongolian-Chinese machine translation method based on anti-neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The implementation of the present invention will be described in detail below in conjunction with the drawings and examples.

[0035] Such as figure 1 As shown, the present invention is a Mongolian-Chinese machine translation method based on an adversarial neural network. On the basis of the generation network G of the original machine translation, a discriminant network D confronting the generation network G is introduced; by realizing the method of binary classification, Judging the translation of the target language, if it comes from the training parallel corpus, the return value is 1, and if it comes from the result of generating network G machine translation, the return value is 0.

[0036] The discriminant network D adopts a multi-layer perceptron feed-forward neural network model, and the binary classification method is:

[0037] Take the form of a rectified linear unit (RELU):

[0038]

[0039] Choose RELU, which has faster convergence speed than tanh in gr...

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 Mongolian-Chinese translation method based on an anti-neural network includes: introducing a discriminating network D that competes with a generation network G on the basis of the original machine translation generation network G, wherein the discriminating network D mainly implements binary classification of the output of the generation network G; determining a translation of a target language,and returning a value 1 if the translation is from a trained parallel corpus; and returning a value 0 if the translation is from a machine translation result of the generated network G. When the probability distribution of real data is not (hard to) calculate (such as the source language parallel corpus data is less), the training mechanism that the generator and the discriminator compete with each other can enable the generator to approximate the probability distribution that is difficult to calculate.

Description

technical field [0001] The invention belongs to the technical field of computers, and in particular relates to a Mongolian-Chinese machine translation method based on an adversarial neural network. Background technique [0002] Machine Translation (MT for short) is one of the earliest research branches in the field of natural language processing. It is the process of using a computer (machine) to convert a natural language into another natural language with exactly the same meaning. Machine translation is a research direction of artificial intelligence, which has very important scientific research value and practical value. With the continuous deepening of the globalization process and the rapid development of the Internet, machine translation technology is playing an increasingly important role in domestic and foreign political, economic, social, and cultural exchanges. [0003] At present, the machine translation method based on neural network is the best method in the fi...

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): G06F17/28G06N3/08
CPCG06F40/58G06N3/08
Inventor 苏依拉王宇飞孙晓骞高芬张振牛向华赵亚平
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