CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
Towards Machine Translation in Semantic Vector Space
Jiajun Zhang; Shujie Liu; Mu Li; Ming Zhou; Chengqing Zong
Source PublicationACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP)
2015-03
Volume14Issue:2Pages:26
Abstract
Measuring the quality of the translation rules and their composition is an essential issue in the conventional statistical machine translation (SMT) framework. To express the translation quality, the previous lexical and phrasal probabilities are calculated only according to the co-occurrence statistics in the bilingual corpus and may be not reliable due to the data sparseness problem. To address this issue, we propose measuring the quality of the translation rules and their composition in the semantic vector embedding space (VES). We present a recursive neural network (RNN)-based translation framework, which includes two
submodels. One is the bilingually-constrained recursive auto-encoder, which is proposed to convert the lexical translation rules into compact real-valued vectors in the semantic VES. The other is a type-dependent recursive neural network, which is proposed to perform the decoding process by minimizing the semantic gap (meaning distance) between the source language string and its translation candidates at each state in a bottom-up structure. The RNN-based translation model is trained using a max-margin objective function that maximizes the margin between the reference translation and the n-best translations in forced decoding. In the experiments, we first show that the proposed vector representations for the translation rules are very reliable for application in translation modeling. We further show that the proposed type-dependent, RNN-based model can significantly improve the translation quality in the large-scale, end-to-end Chineseto-English translation evaluation.
KeywordStatistical Machine Translation Recursive Neural Network Semantic Meaning Distance Vector Embedding Space Max-margin Training
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/19930
Collection模式识别国家重点实验室_自然语言处理
Recommended Citation
GB/T 7714
Jiajun Zhang,Shujie Liu,Mu Li,et al. Towards Machine Translation in Semantic Vector Space[J]. ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP),2015,14(2):26.
APA Jiajun Zhang,Shujie Liu,Mu Li,Ming Zhou,&Chengqing Zong.(2015).Towards Machine Translation in Semantic Vector Space.ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP),14(2),26.
MLA Jiajun Zhang,et al."Towards Machine Translation in Semantic Vector Space".ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP) 14.2(2015):26.
Files in This Item: Download All
File Name/Size DocType Version Access License
ACM TALLIP,No.2, Vol(1375KB)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
[Jiajun Zhang]'s Articles
[Shujie Liu]'s Articles
[Mu Li]'s Articles
Baidu academic
Similar articles in Baidu academic
[Jiajun Zhang]'s Articles
[Shujie Liu]'s Articles
[Mu Li]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Jiajun Zhang]'s Articles
[Shujie Liu]'s Articles
[Mu Li]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: ACM TALLIP,No.2, Vol.14(March 2015), 26 pages- J. Zhang.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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