Improved Reordering for Shallow-n Grammar based Hierarchical Phrase-based Translation

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 loglinear model allowing the decoder to directly optimize the feature weights. We show this formulation of Shallow-n hierarchical phrasebased translation is comparable in translation quality to full Hiero-style decoding (without shallow rules) while at the same time being considerably faster.