GREAT: open source software for statistical machine translation
| 详细信息 | 推荐本文 | |
- 作者：Jorge Gonz谩lez (1) jgonzalez@dsic.upv.es
Francisco Casacuberta (1) - 关键词：Statistical machine translation – ; Monotonic bilingual segmentation – ; Grammatical inference – ; Language modelling – ; Stochastic finite ; state transducers
- 刊名：Machine Translation
- 出版时间：June 2011
- 出版年：2011
- 期刊代码：36_09226567
- 类别：cp
- 卷：25
- 期：2
- 页码：145-160
- 数据来源：sp
摘要
In this article, the first public release of GREAT as an open-source, statistical machine translation (SMT) software toolkit is described. GREAT is based on a bilingual language modelling approach for SMT, which is so far implemented for n-gram models based on the framework of stochastic finite-state transducers. The use of finite-state models is motivated by their simplicity, their versatility, and the fact that they present a lower computational cost, if compared with other more expressive models. Moreover, if translation is assumed to be a subsequential process, finite-state models are enough for modelling the existing relations between a source and a target language. GREAT includes some characteristics usually present in state-of-the-art SMT, such as phrase-based translation models or a log-linear framework for local features. Experimental results on a well-known corpus such as Europarl are reported in order to validate this software. A competitive translation quality is achieved, yet using both a lower number of model parameters and a lower response time than the widely-used, state-of-the-art SMT system Moses.