2009 · 17 citations · 17 references
HumanitiesComputer ScienceTranslation StudiesComputational LinguisticsCorpus-based Translation StudiesNatural Language ProcessingLanguage ModelingMachine TranslationTranslation CorporaTranslation Quality AssessmentTranslation TechnologyWord OrderAlignment Quality EvaluationAutomated Translation EvaluationCompound ProcessingCompound Word ProcessingMachine Translation Quality EvaluationTranslation Quality MetricsTranslation Quality ScoringWord Alignment
We describe the LIU systems for English-German and German-English translation in the WMT09 shared task. We focus on two methods to improve the word alignment: (i) by applying Giza++ in a second phase to a reordered training corpus, where reordering is based on the alignments from the first phase, and (ii) by adding lexical data obtained as high-precision alignments from a different word aligner. These methods were studied in the context of a system that uses compound processing, a morphological sequence model for German, and a part-of-speech sequence model for English. Both methods gave some improvements to translation quality as measured by Bleu and Meteor scores, though not consistently. All systems used both out-of-domain and in-domain data as the mixed corpus had better scores in the baseline configuration.
17
Kishore Papineni, Salim Roukos, Todd J. Ward et al. · 2001 · 21.5K citations · Full text
Philipp Koehn, Richard Zens, Chris Dyer et al. · 2007 · 4.9K citations · Full text
SRILM - an extensible language modeling toolkit
Andreas Stolcke · 2002 · 4.4K citations
A Systematic Comparison of Various Statistical Alignment Models
Franz Josef Och, Hermann Ney · Computational Linguistics · 2003 · 3.9K citations · Full text