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
2015-09-01
发表期刊IEEE INTELLIGENT SYSTEMS
卷号30期号:5页码:16-25
文章类型Article
摘要
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.
关键词Machine Translation
WOS标题词Science & Technology ; Technology
关键词[WOS]DISTRIBUTED REPRESENTATIONS
收录类别SCI
语种英语
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号WOS:000361315900003
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/9012
专题模式识别国家重点实验室_自然语言处理
通讯作者Zhang, Jiajun
作者单位Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100864, Peoples R China
推荐引用方式
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.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
IEEE-Zhang-8-5.pdf(3692KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhang, Jiajun]的文章
[Zong, Chengqing]的文章
百度学术
百度学术中相似的文章
[Zhang, Jiajun]的文章
[Zong, Chengqing]的文章
必应学术
必应学术中相似的文章
[Zhang, Jiajun]的文章
[Zong, Chengqing]的文章
相关权益政策
暂无数据
收藏/分享
文件名: IEEE-Zhang-8-5.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。