Edinburgh’s Submission to all Tracks of the WMT2009 Shared Task with Reordering and Speed Improvements to Moses

Edinburgh’s Submission to all Tracks of the WMT2009 Shared Task with Reordering and Speed Improvements to Moses

Cached

Download Links

by Barry Haddow

Citations:

BibTeX

@MISC{Haddow_edinburgh’ssubmission,
    author = {Barry Haddow},
    title = {Edinburgh’s Submission to all Tracks of the WMT2009 Shared Task with Reordering and Speed Improvements to Moses},
    year = {}
}

Bookmark

OpenURL

Abstract

Edinburgh University participated in the WMT 2009 shared task using the Moses phrase-based statistical machine translation decoder, building systems for all language pairs. The system configuration was identical for all language pairs (with a few additional components for the German-English language pairs). This paper describes the configuration of the systems, plus novel contributions to Moses including truecasing, more efficient decoding methods, and a framework to specify reordering constraints. 1

Citations

434	Moses: Open source toolkit for statistical machine translation - Koehn, Hoang, et al. - 2007
274	A Maximum Entropy Part-Of-Speech Tagger - Ratnaparkhi - 1996
166	Three generative, lexicalized models for statistical parsing - Collins - 1997
66	Factored translation models - Koehn, Hoang - 2007
65	Clause restructuring for statistical machine translation - Collins, Koehn, et al. - 2005
45	Empirical methods for compound splitting - Koehn, Knight - 2003
30	Forest Rescoring: Faster Decoding with Integrated Language Models - Huang, Chiang - 2007
10	Faster beam-search decoding for phrasal statistical machine translation - Moore, Quirk - 2007
2	Feature-rich translation of noun phrases - Koehn, Knight - 2003