Depthwise separable convolution-based Chinese-Vietnamese neural machine translation method

A technology of machine translation and convolutional neural network, which is applied in the field of neural machine translation of resource-scarce languages, can solve problems such as data sparsity, achieve the effect of alleviating data sparsity and improving translation performance

Inactive Publication Date: 2020-05-12
KUNMING UNIV OF SCI & TECH
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a Chinese-Vietnamese neural machine translation method based on depthwise separable convolution to solve the problem of data sparseness in resource-scarce language neural machine translation, and the method significantly improves the performance of Chinese-Vietnamese neural machine translation

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
  • Depthwise separable convolution-based Chinese-Vietnamese neural machine translation method
  • Depthwise separable convolution-based Chinese-Vietnamese neural machine translation method
  • Depthwise separable convolution-based Chinese-Vietnamese neural machine translation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] Embodiment 1: as Figure 1-3 As shown, the Chinese-Vietnamese neural machine translation method based on depth separable convolution, the specific steps of the method are as follows:

[0028] Step1. According to the language characteristics of Vietnamese, Vietnamese is divided into four different translation granularity sequences. The four divided granularities are word granularity, syllable granularity, character granularity, and subword granularity; the specific segmentation methods are as follows : The word granularity is segmented by existing word segmentation software, the subword granularity is processed by the subword segmentation algorithm, and the character granularity is segmented by the self-written algorithm; in addition to the above common granularity segmentation, Vietnamese also has A special syllable granularity. Each syllable is often a meaningful unit that can be used independently. These units can also be used as the basis for forming polysyllabic wor...

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 depthwise separable convolution-based Chinese-Vietnamese neural machine translation method, and belongs to the technical field of resource scarcity type language neural machine translation. According to language characteristics of Vietnamese, Vietnamese is segmented into four different translation granularity sequences of words, syllables, characters and sub-words; secondly, a neural machine translation model is improved by utilizing depthwise separable convolution; a depthwise separable convolutional neural network is added; convolution operation is carried out on different granularity sequences input by the model and more feature data are extracted. By adding the depthwise separable convolutional neural network prior to an encoder embedding layer of the neuralmachine translation model, The depthwise separable convolution-based Chinese-Vietnamese neural machine translation method is constructed in the field of resource scarcity type language machine translation, so that the problem of sparse data of the resource scarcity type language neural machine translation is effectively relieved, and the translation performance is improved.

Description

technical field [0001] The invention relates to a Chinese-Vietnamese neural machine translation method based on depthwise separable convolution, and belongs to the technical field of resource-scarce language neural machine translation. Background technique [0002] In recent years, Neural Machine Translation (NMT) has become an important direction of machine translation research. With the increasingly frequent development of Sino-Vietnamese relations, Chinese-Vietnamese neural machine translation is of great significance and value to Sino-Vietnamese exchanges. Vietnamese is a resource-scarce language. It is characterized by the lack of bilingual alignment corpus and difficulty in corpus collection, which makes the problem of data sparseness very serious, which greatly affects the translation effect of the model. [0003] In neural machine translation, in order to alleviate the problem of data sparseness, smaller input / output granularity is generally used to solve the proble...

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): G06F40/58G06F40/289G06N3/04
CPCG06N3/045
Inventor 余正涛徐毓赖华高盛祥文永华于志强朱俊国
Owner KUNMING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap