Translation Model Pruning via Usage Statistics for Statistical Machine Translation

We describe a new pruning approach to remove phrase pairs from translation models of statistical machine translation systems. The approach applies the original translation system to a large amount of text and calculates usage statistics for the phrase pairs. Using these statistics the relevance of each phrase pair can be estimated. The approach is tested against a strong baseline based on previous work and shows significant improvements.

• Type: Conference
• Year: 2007
• Where: NAACL
• Authors: Matthias Eck, Stephan Vogel, Alex Waibel
• Keywords: Computational Linguistics, NAACL 2007, Phrase Pair, Statistical Machine Translation, Translation System