A Tagging-style Reordering Model for Phrase-based SMT

摘要

For current statistical machine translation system, reordering is still a major problem for language pairs like Chinese-English, where the source and target language have significant word order differences. In this paper we propose a novel tagging-style reordering model. Our model converts the reordering problem into a sequence labeling problem, i.e. a tagging task. For the given source sentence, we assign each source token a label which contains the reordering information for that token. We also design an unaligned word tag so that the unaligned word phenomenon is automatically covered in the proposed model. Our reordering model is conditioned on the whole source sentence. Hence it is able to catch long dependencies in the source sentence. The decoder makes use of the tagging information as soft constraints so that in the test phase (during translation) our model is very efficient. The model training on large scale tasks requests notably amounts of computational resources. We carried out experiments on five Chinese-English NIST tasks trained with BOLT data. Results show that our model improves the baseline system by 0.98 Bleu 1.21 Ter on average.