Deep open-source machine translation

详细信息

下载全文

推荐本文 |

• 作者：Francis Bond (1) bond@ieee.org
  Stephan Oepen (2) oe@ifi.uio.no
  Eric Nichols (3) eric@ecei.tohoku.ac.jp
  Dan Flickinger (4) danf@stanford.edu
  Erik Velldal (2) erikve@ifi.uio.no
  Petter Haugereid (1) petterha@ntu.edu.sg
• 关键词：Machine translation &#8211 ; Open source &#8211 ; Semantic transfer &#8211 ; HPSG &#8211 ; MRS
• 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：87-105
• 数据来源：sp

摘要

This paper summarizes ongoing efforts to provide software infrastructure (and methodology) for open-source machine translation that combines a deep semantic transfer approach with advanced stochastic models. The resulting infrastructure combines precise grammars for parsing and generation, a semantic-transfer based translation engine and stochastic controllers. We provide both a qualitative and quantitative experience report from instantiating our general architecture for Japanese–English MT using only open-source components, including HPSG-based grammars of English and Japanese.