Paper Info
Title
Improved features and grammar selection for syntax-based MT
Abstract
We present the Carnegie Mellon University Stat-XFER group submission to the WMT 2010 shared translation task. Updates to our syntax-based SMT system mainly fell in the areas of new feature formulations in the translation model and improved 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.
Year
Venue
Keywords
2010
WMT@ACL
improved grammar selection,shared translation task,group submission,new feature formulation,decoding environment,syntax-based mt,carnegie mellon university stat-xfer,translation model,scfg rule,syntax-based smt system,new feature,improved feature
Field
DocType
Citations 
Computer science,Filter (signal processing),Grammar,Speech recognition,Synchronous context-free grammar,Artificial intelligence,Natural language processing,Decoding methods,Syntax
Conference
4
PageRank 
References 
Authors
0.51
17
3
Name
Order
Citations
PageRank
Greg Hanneman1847.66
Jonathan H. Clark241116.42
alon lavie32606177.91