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

A Neural Network Mongolian-Chinese Machine Translation Method Based on Encoder-Decoder

A neural network and machine translation technology, applied in the field of machine translation, can solve problems such as insufficient model translation performance

Active Publication Date: 2020-07-17
INNER MONGOLIA UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

As a result, the translation performance of existing models is not perfect

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 Neural Network Mongolian-Chinese Machine Translation Method Based on Encoder-Decoder
  • A Neural Network Mongolian-Chinese Machine Translation Method Based on Encoder-Decoder
  • A Neural Network Mongolian-Chinese Machine Translation Method Based on Encoder-Decoder

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] The implementation of the present invention will be described in detail below in conjunction with the drawings and examples.

[0064] Such as figure 2 As shown, the present invention is also based on an encoding-decoding framework. The difference is that the modeling scheme of the Mongolian-Chinese machine translation system of the present invention includes a "review" step with an attention mechanism in the hidden layer of the encoder and modeling of a two-layer decoder model:

[0065] (1) In the hidden layer of the encoder, a "review" step with an attention mechanism is used to output some "review" vectors, which can obtain global attributes through the attention mechanism of the decoder, and all the information obtained can generate a more Abstract, global, and tight vectors effectively improve translation quality.

[0066] Through multiple "review" operations based on the attention mechanism on the encoding side, a set of "review" vectors summarizing the input in...

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

Neural Network Mongolian-Chinese Machine Translation Method Based on Encoder-Decoder is provided. The method comprises the following steps of using an encoder e and two-layer decoders d1 and d2, encoding the Mongolian source language into a vector list by the encoder E, Then, at the hidden layer of the encoder, adopting a retrospective step with attention mechanism, In the decoding process, obtaining the implied state before softmax and the draft sentence by the decoder D1, and then taking the implied state of the encoder E and the decoder D1 as the input of the decoder D2 to obtain the secondchannel sequence, i.e. The final translation. At first, that Chinese corpus is divided into words in the preprocess stage, The Mongolian-Chinese bilingual corpus is segmented into stem, affixes and cases, and the Mongolian-Chinese bilingual corpus is segmented into word segments (BPE), which can effectively refine the translation granularity and reduce the number of unknown words, and then the Mongolian-Chinese word vector is constructed by Word2vec. For unknown words, a Mongolian-Chinese dictionary of proprietary vocabulary is also constructed, which can effectively improve the quality of translation.

Description

technical field [0001] The invention belongs to the technical field of machine translation, in particular to an encoder-decoder-based neural network Mongolian-Chinese machine translation method. Background technique [0002] Since Neural Machine Translation (NMT) was first mentioned, it has made great achievements in the field of machine translation. It is comprehensively superior to Statistical Machine Translation (SMT), and has quickly become the mainstream standard of online translation systems. [0003] There are more and more neural machine translation systems on the market. Foreign Google and domestic Tencent, Alibaba, Baidu, Sogou, HKUST Xunfei, etc. have conducted a lot of research on machine translation, and have achieved remarkable research results. Scarce resources Machine translation tasks for languages ​​and minority languages ​​are also gaining more and more attention. [0004] Mongolian is an agglutinative language, and its main speakers are in Mongolia, the ...

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 Patents(China)
IPC IPC(8): G06F40/58G06F40/211G06F40/242G06F40/253
CPCG06F40/211G06F40/242G06F40/253G06F40/58
Inventor 苏依拉高芬张振王宇飞孙晓骞牛向华赵亚平赵旭
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