The University of Edinburgh System Description for IWSLT 2007
| Citations: | 1 - 0 self |
BibTeX
@MISC{Schroeder_theuniversity,
author = {Josh Schroeder},
title = {The University of Edinburgh System Description for IWSLT 2007},
year = {}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
We present the University of Edinburgh’s submission for the IWSLT 2007 shared task. Our efforts focused on adapting our statistical machine translation system to the open data conditions for the Italian-English task of the evaluation campaign. We examine the challenges of building a system with a limited set of in-domain development data (SITAL), a small training corpus in a related but distinct domain (BTEC), and a large out of domain corpus (Europarl). We concentrated on the corrected text track, and present additional results of our experiments using the open-source Moses MT system with speech input. 1.
Citations
| 434 | Moses: Open source toolkit for statistical machine translation - Koehn, Hoang, et al. - 2007 |
| 282 | Lattice-based minimum error rate training for statistical machine translation - Macherey, Och, et al. - 2008 |
| 77 | Europarl: A multilingual corpus for evaluation of machine translation - Koehn - 2002 |
| 43 | Experiments in Domain Adaptation for Statistical Machine Translation - Koehn, Schroeder - 2007 |
| 34 | Edinburgh system description for the 2005 IWSLT speech translation evaluation - Koehn, Axelrod, et al. - 2005 |
| 30 | Statistical Phrase based Translation - Koehn, Och, et al. - 2003 |
| 22 | Mixture-model adaptation for SMT - Foster, Kuhn - 2007 |
| 10 | CCG supertags in factored statistical machine translation - Birch, Osborne, et al. - 2007 |
| 3 | SRILM - an extensible language modeling toolkit - Stolke - 2002 |
| 3 | IBM Arabic-to-English Translation for IWSLT 2006 - Lee - 2006 |
| 1 | Edinburgh system description for the 2006 TC-STAR spoken language translation evaluation - Arun, Axelrod, et al. - 2006 |
