Paper Info
Title
Improved reordering for shallow-n grammar based hierarchical phrase-based translation
Abstract
Shallow-n grammars (de Gispert et al., 2010) were introduced to reduce over-generation in the Hiero translation model (Chiang, 2005) resulting in much faster decoding and restricting reordering to a desired level for specific language pairs. However, Shallow-n grammars require parameters which cannot be directly optimized using minimum error-rate tuning by the decoder. This paper introduces some novel improvements to the translation model for Shallow-n grammars. We introduce two rules: a BITG-style reordering glue rule and a simpler monotonic concatenation rule. We use separate features for the new rules in our log-linear model allowing the decoder to directly optimize the feature weights. We show this formulation of Shallow-n hierarchical phrase-based translation is comparable in translation quality to full Hiero-style decoding (without shallow rules) while at the same time being considerably faster.
Year
Venue
Keywords
2012
HLT-NAACL
shallow rule,translation quality,shallow-n hierarchical phrase-based translation,log-linear model,shallow-n grammar,improved reordering,new rule,translation model,hiero translation model,full hiero-style decoding,bitg-style reordering glue rule
Field
DocType
Citations 
Rule-based machine translation,Monotonic function,Computer science,Phrase,Algorithm,Speech recognition,Grammar,Concatenation,Natural language processing,Artificial intelligence,Decoding methods
Conference
1
PageRank 
References 
Authors
0.35
12
2
Name
Order
Citations
PageRank
Baskaran Sankaran115513.65
Anoop Sarkar2101788.82