ComputingComputer ScienceNatural Language ProcessingTranslation TheoryTranslator TrainingMachine TranslationMultilingual Natural Language ProcessingSemi-supervised LearningTranslation Quality AssessmentBilingual Text CorporaBilingual Text TranslationCross-lingual TransferMonolingual CorporaStatistical Machine TranslationTransductive LearningTransductive Transfer LearningTranslation Quality Metrics
Statistical machine translation systems are typically trained on large bilingual corpora and target‑language monolingual data. This study investigates transductive semi‑supervised methods to leverage source‑language monolingual data for better translation quality. The authors propose several transductive algorithms and evaluate them on French‑English EuroParl and NIST Chinese‑English large‑data tracks. The experiments demonstrate significant translation quality gains on both tasks.
Statistical machine translation systems are usually trained on large amounts of bilingual text and monolingual text in the target language. In this paper we explore the use of transductive semi-supervised methods for the effective use of monolingual data from the source language in order to improve translation quality. We propose several algorithms with this aim, and present the strengths and weaknesses of each one. We present detailed experimental evaluations on the French‐English EuroParl data set and on data from the NIST Chinese‐English largedata track. We show a significant improvement in translation quality on both tasks.
16
Kishore Papineni, Salim Roukos, Todd J. Ward et al. · 2001 · 21.5K citations · Full text
Combining labeled and unlabeled data with co-training
Avrim Blum, Tom M. Mitchell · 1998 · 5.6K citations · Full text
SRILM - an extensible language modeling toolkit
Andreas Stolcke · 2002 · 4.4K citations