Paper: Improving Reordering with Linguistically Informed Bilingual n-grams

ACL ID C10-2023
Title Improving Reordering with Linguistically Informed Bilingual n-grams
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2010
Authors

We present a new reordering model es- timated as a standard n-gram language model with units built from morpho- syntactic information of the source and target languages. It can be seen as a model that translates the morpho-syntactic structure of the input sentence, in contrast to standard translation models which take care of the surface word forms. We take advantage from the fact that such units are less sparse than standard translation units to increase the size of bilingual con- text that is considered during the trans- lation process, thus effectively account- ing for mid-range reorderings. Empirical results on French-English and German- English translation tasks show that our model achieves higher translation accu- racy levels than those obtained with the widely used lexicalized reord...