A Syntax-based Statistical Translation Model

We present a syntax-based statistical translation model. Our model transforms a source-language parse tree into a target-language string by applying stochastic operations at each node. These operations capture linguistic differences such as word order and case marking. Model parameters are estimated in polynomial time using an EM algorithm. The model produces word alignments that are better than those produced by IBM Model 5.

• Type: Conference
• Year: 2001
• Where: ACL
• Authors: Kenji Yamada, Kevin Knight
• Keywords: ACL 2001, ACL 2007, Model, Model Produces Word, Statistical Translation Model