Decoding by Dynamic Chunking for Statistical Machine Translation

In this paper we present an extension of a phrase-based decoder that dynamically chunks, reorders, and applies phrase translations in tandem. A maximum entropy classifier is trained based on the word alignments to find the best positions to chunk the source sentence. No language specific or syntactic information is used to build the chunking classifier. Words inside the chunks are moved together to enable the decoder to make longdistance re-orderings to capture the word order differences between languages with different sentence structures. To keep the search space manageable, phrases inside the chunks are monotonically translated, thus by eliminating the unnecessary local re-orderings, it is possible to perform long-distance re-orderings beyond the common fixed distortion limit. Experiments on German to English translation are reported.