Phrasetable Smoothing for Statistical Machine Translation

We discuss different strategies for smoothing the phrasetable in Statistical MT, and give results over a range of translation settings. We show that any type of smoothing is a better idea than the relativefrequency estimates that are often used. The best smoothing techniques yield consistent gains of approximately 1% (absolute) according to the BLEU metric.

• Type: Conference
• Year: 2006
• Where: EMNLP
• Authors: George F. Foster, Roland Kuhn, Howard Johnson
• Keywords: Better Idea, EMNLP 2006, EMNLP 2007, Smoothing, Statistical MT