Except where otherwise noted, content on this site is licensed for use under a:

Exploiting parallel treebanks to improve phrase-based statistical machine translation

Tinsley, John and Hearne, Mary and Way, Andy (2007) Exploiting parallel treebanks to improve phrase-based statistical machine translation. In: TLT 2007 - The 6th International Workshop on Treebanks and Linguistic Theories, 7-8 December, 2007, Bergen, Norway.

Full text available as:

Preview

PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
121Kb

Abstract

We use existing tools to automatically build two parallel treebanks from existing parallel corpora. We then show that combining the data extracted from both the treebanks and the corpora into a single translation model can improve the translation quality in a baseline phrase-based statistical machine translation system.

Item Type:	Conference or Workshop Item (Paper)
Event Type:	Workshop
Refereed:	Yes
Uncontrolled Keywords:	parallel treebanks; statistical machine translation;
Subjects:	Computer Science > Machine translating
DCU Faculties and Centres:	Research Initiatives and Centres > National Centre for Language Technology (NCLT)
Official URL:	http://tlt07.uib.no/index.php?page=main
Use License:	This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:	Science Foundation Ireland, SFI 05/RF/CMS064
ID Code:	15266
Deposited On:	09 Mar 2010 16:48 by DORAS Administrator. Last Modified 27 Apr 2010 15:11

Download statistics

Archive Staff Only: edit this record