Segment Choice Models: Feature-Rich Models for Global Distortion in Statistical Machine Translation

Roland Kuhn, Denis Yuen, Michel Simard, Patrick Paul, George F. Foster, Eric Joanis, Howard Johnson

Abstract: This paper presents a new approach to distortion (phrase reordering) in phrase-based machine translation (MT). Distortion is modeled as a sequence of choices during translation. The approach yields trainable, probabilistic distortion models that are global: they assign a probability to each possible phrase reordering. These "segment choice" models (SCMs) can be trained on "segment-aligned" sentence pairs; they can be applied during decoding or rescoring. The approach yields a metric called "distortion perplexity" ("disperp") for comparing SCMs offline on test data, analogous to perplexity for language models. A decision-tree-based SCM is tested on Chinese-to-English translation, and outperforms a baseline distortion penalty approach at the 99% confidence level.