XJIPC OpenIR  > 多语种信息技术研究室
Filtering Reordering Table Using a Novel Recursive Autoencoder Model for Statistical Machine Translation
Kong, JY (Kong, Jinying); Yang, YT (Yang, Yating); Wang, L (Wang, Lei); Zhou, X (Zhou, Xi); Jiang, TH (Jiang, Tonghai); Li, X (Li, Xiao)
2017
Source PublicationMATHEMATICAL PROBLEMS IN ENGINEERING
ISSN1024-123X
Issue6Pages:1-9
Abstract

In phrase-based machine translation (PBMT) systems, the reordering table and phrase table are very large and redundant. Unlike most previous works which aim to filter phrase table, this paper proposes a novel deep neural network model to prune reordering table. We cast the task as a deep learning problem where we jointly train two models: a generative model to implement rule embedding and a discriminative model to classify rules. The main contribution of this paper is that we optimize the reordering model in PBMT by filtering reordering table using a recursive autoencoder model. To evaluate the performance of the proposed model, we performed it on public corpus tomeasure its reordering ability. The experimental results show that our approach obtains high improvement in BLEU score with less scale of reordering table on two language pairs: English-Chinese (+0.28) and Uyghur-Chinese (+ 0.33) MT.

DOI10.1155/2017/3492587
Indexed BySCI
WOS IDWOS:000403167100001
Citation statistics
Document Type期刊论文
Identifierhttp://ir.xjipc.cas.cn/handle/365002/5088
Collection多语种信息技术研究室
Corresponding AuthorYang, YT (Yang, Yating)
Affiliation1.Chinese Acad Sci, Xinjiang Tech Inst Phys & Chem, Urumqi 830011, Peoples R China
2.Xinjiang Lab Minor Speech & Language Informat Pro, Urumqi 830011, Peoples R China
3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
Recommended Citation
GB/T 7714
Kong, JY ,Yang, YT ,Wang, L ,et al. Filtering Reordering Table Using a Novel Recursive Autoencoder Model for Statistical Machine Translation[J]. MATHEMATICAL PROBLEMS IN ENGINEERING,2017(6):1-9.
APA Kong, JY ,Yang, YT ,Wang, L ,Zhou, X ,Jiang, TH ,&Li, X .(2017).Filtering Reordering Table Using a Novel Recursive Autoencoder Model for Statistical Machine Translation.MATHEMATICAL PROBLEMS IN ENGINEERING(6),1-9.
MLA Kong, JY ,et al."Filtering Reordering Table Using a Novel Recursive Autoencoder Model for Statistical Machine Translation".MATHEMATICAL PROBLEMS IN ENGINEERING .6(2017):1-9.
Files in This Item:
File Name/Size DocType Version Access License
Filtering Reordering(2490KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Kong, JY (Kong, Jinying)]'s Articles
[Yang, YT (Yang, Yating)]'s Articles
[Wang, L (Wang, Lei)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Kong, JY (Kong, Jinying)]'s Articles
[Yang, YT (Yang, Yating)]'s Articles
[Wang, L (Wang, Lei)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Kong, JY (Kong, Jinying)]'s Articles
[Yang, YT (Yang, Yating)]'s Articles
[Wang, L (Wang, Lei)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Filtering Reordering Table Using a Novel Recursive Autoencoder Model for Statistical Machine Translation.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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