Syntactic Preprocessing for Statistical Machine Translation

We describe an approach to automatic source-language syntactic preprocessing in the context of Arabic-English phrase-based machine translation. Source-language labeled dependencies, that are word aligned with target language words in a parallel corpus, are used to automatically extract syntactic reordering rules in the same spirit of Xia and McCord (2004) and Zhang et al. (2007). The extracted rules are used to reorder the source-language side of the training and test data. Our results show that when using monotonic decoding and translations for unigram source-language phrases only, source-language reordering gives very significant gains over no reordering (25% relative increase in BLEU score). With decoder distortion turned on and with access to all phrase translations, the differences in BLEU scores are diminished. However, an analysis of sentence-level BLEU scores shows reordering outperforms no-reordering in over 40% of the sentences. These results suggest that the approach holds big promise but much more work on Arabic parsing may be needed.