CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
Unsupervised Tree Induction for Tree-based Translation
Zhai, Feifei; Zhang, Jiajun; Zhou, Yu; Zong, Chengqing
Source PublicationTransactions of the Association for Computational Linguistics
2013-05
Issue1Pages:243–254
AbstractIn current research, most tree-based translation models are built directly from parse trees. In this study, we go in another direction and build a translation model with an unsupervised tree structure derived from a novel non-parametric Bayesian model. In the model, we utilize synchronous tree substitution grammars (STSG) to capture the bilingual mapping between language pairs. To train the model efficiently, we develop a Gibbs sampler with three novel Gibbs operators. The sampler is capable of exploring the infinite space of tree structures by performing local changes on the tree nodes. Experimental results show that the string-to-tree translation system using our Bayesian tree structures significantly outperforms the strong baseline string-to-tree system using parse trees.
Other Abstract在目前的研究中,大多数基于树的翻译模型都是直接从解析树构建的。在这一研究中,我们从另一个方向出发,建立了一种基于非参数贝叶斯模型的无监督树结构的翻译模型。在模型中,我们利用同步树替换文法(STSG)捕获之间的语言对双语映射。为了有效地训练模型,我们开发了一个具有三个新的吉布斯算子的吉布斯采样器。采样器可以通过在树节点上执行局部更改来探索树结构的无限空间。实验结果表明,使用我们的贝叶斯树结构的树对树转换系统明显优于使用解析树的强基线字符串到树系统。
KeywordUnsupervised Tree Induction Syntax-based Machine Translation
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/20687
Collection模式识别国家重点实验室_自然语言处理
Recommended Citation
GB/T 7714
Zhai, Feifei,Zhang, Jiajun,Zhou, Yu,et al. Unsupervised Tree Induction for Tree-based Translation[J]. Transactions of the Association for Computational Linguistics,2013(1):243–254.
APA Zhai, Feifei,Zhang, Jiajun,Zhou, Yu,&Zong, Chengqing.(2013).Unsupervised Tree Induction for Tree-based Translation.Transactions of the Association for Computational Linguistics(1),243–254.
MLA Zhai, Feifei,et al."Unsupervised Tree Induction for Tree-based Translation".Transactions of the Association for Computational Linguistics .1(2013):243–254.
Files in This Item: Download All
File Name/Size DocType Version Access License
16-2013 TACL,ZhaiFF.(510KB)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
[Zhai, Feifei]'s Articles
[Zhang, Jiajun]'s Articles
[Zhou, Yu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhai, Feifei]'s Articles
[Zhang, Jiajun]'s Articles
[Zhou, Yu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhai, Feifei]'s Articles
[Zhang, Jiajun]'s Articles
[Zhou, Yu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 16-2013 TACL,ZhaiFF.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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