Forced Derivations for Hierarchical Machine Translation
Stephan Peitz, Arne Mauser, Joern Wuebker, Hermann Ney · RWTH Publications (RWTH Aachen) · 2012
We present an efficient framework to estimate the rule probabilities for a hierarchical phrasebased statistical machine translation system from parallel data.In previous work, this was done with bilingual parsing.We use a more efficient approach splitting the bilingual parsing into two stages, which allows us to train a hierarchical translation model on larger tasks.Furthermore, we apply leave-one-out to counteract over-fitting and use the expected count from the inside-outside algorithm to prune the rule set.On the WMT12 Europarl German→English and French→English tasks, we improve translation quality by up to 1.0 BLEU and 0.9 TER while simultaneously reducing the rule set to 5% of the original size.