CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
Deep Neural Networks in Machine Translation: An Overview
Zhang, Jiajun; Zong, Chengqing
Source PublicationIEEE INTELLIGENT SYSTEMS
2015-09-01
Volume30Issue:5Pages:16-25
SubtypeArticle
Abstract
Due to the powerful capacity of feature learning and representation, deep
neural networks (DNNs) have made big breakthroughs in speech recognition
and image processing. Following recent success in signal variable processing,
researchers want to figure out whether DNNs can achieve similar progress insymbol variable processing, such as natural language processing (NLP). As one of the
more challenging NLP tasks, machine translation (MT) has become a testing ground for
researchers who want to evaluate various kinds of DNNs. MT aims to find for the source language sentence the most probable target language sentence
that shares the most similar meaning. Essentially, MT is a sequence-to-sequence prediction task. This article gives a comprehensive overview of applications of DNNs in MT from two views: indirect application, which attempts to improve standard MT systems, and direct application, which adopts DNNs to design a purely neural MT model. We can elaborate further:
• Indirect application designs new features with DNNs in the framework of standard
MT systems, which consist of multiple submodels (such as translation selection and language models). For example, DNNs can be leveraged to represent the source language context’s semantics and better predict translation candidates.
• Direct application regards MT as a sequence- to-sequence prediction task and, without using any information from standard MT systems, designs two deep neural networks—an encoder, which learns continuous representations of source language sentences, and a decoder, which generates the target language sentence with source
sentence representation.
KeywordMachine Translation
WOS HeadingsScience & Technology ; Technology
WOS KeywordDISTRIBUTED REPRESENTATIONS
Indexed BySCI
Language英语
WOS Research AreaComputer Science ; Engineering
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS IDWOS:000361315900003
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/9012
Collection模式识别国家重点实验室_自然语言处理
Corresponding AuthorZhang, Jiajun
AffiliationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100864, Peoples R China
Recommended Citation
GB/T 7714
Zhang, Jiajun,Zong, Chengqing. Deep Neural Networks in Machine Translation: An Overview[J]. IEEE INTELLIGENT SYSTEMS,2015,30(5):16-25.
APA Zhang, Jiajun,&Zong, Chengqing.(2015).Deep Neural Networks in Machine Translation: An Overview.IEEE INTELLIGENT SYSTEMS,30(5),16-25.
MLA Zhang, Jiajun,et al."Deep Neural Networks in Machine Translation: An Overview".IEEE INTELLIGENT SYSTEMS 30.5(2015):16-25.
Files in This Item: Download All
File Name/Size DocType Version Access License
IEEE-Zhang-8-5.pdf(3692KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang, Jiajun]'s Articles
[Zong, Chengqing]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang, Jiajun]'s Articles
[Zong, Chengqing]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang, Jiajun]'s Articles
[Zong, Chengqing]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: IEEE-Zhang-8-5.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.