Improved Features and Grammar Selection for Syntax-Based MT
Greg Hanneman, Jonathan H. Clark, Alon Lavie · 2010
We present the Carnegie Mellon Univer-sity Stat-XFER group submission to the WMT 2010 shared translation task. Up-dates to our syntax-based SMT system mainly fell in the areas of new feature for-mulations in the translation model and im-proved filtering of SCFG rules. Compared to our WMT 2009 submission, we report a gain of 1.73 BLEU by using the new features and decoding environment, and a gain of up to 0.52 BLEU from improved grammar selection. 1