Browse DORAS
Browse Theses
Latest Additions
Creative Commons License
Except where otherwise noted, content on this site is licensed for use under a:

Multi-engine machine translation by recursive sentence decomposition

Mellebeek, Bart and Owczarzak, Karolina and van Genabith, Josef and Way, Andy (2006) Multi-engine machine translation by recursive sentence decomposition. In: AMTA 2006 - 7th Conference of the Association for Machine Translation of the Americas, 8-12 August 2006, Cambridge, Massachusetts, USA.

Full text available as:

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


In this paper, we present a novel approach to combine the outputs of multiple MT engines into a consensus translation. In contrast to previous Multi-Engine Machine Translation (MEMT) techniques, we do not rely on word alignments of output hypotheses, but prepare the input sentence for multi-engine processing. We do this by using a recursive decomposition algorithm that produces simple chunks as input to the MT engines. A consensus translation is produced by combining the best chunk translations, selected through majority voting, a trigram language model score and a confidence score assigned to each MT engine. We report statistically significant relative improvements of up to 9% BLEU score in experiments (English→Spanish) carried out on an 800-sentence test set extracted from the Penn-II Treebank.

Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Subjects:Computer Science > Machine translating
DCU Faculties and Centres:Research Initiatives and Centres > National Centre for Language Technology (NCLT)
DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Official URL:
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:Enterprise Ireland, EI SC/2003/0282
ID Code:15281
Deposited On:11 Mar 2010 11:48 by DORAS Administrator. Last Modified 28 Apr 2010 09:46

Download statistics

Archive Staff Only: edit this record