Model With Minimal Translation Units, But Decode With Phrases

Nadir Durrani, Alexander Fraser, Helmut Schmid

N-gram-based models co-exist with their phrase-based counterparts as
an alternative SMT framework. Both techniques have pros and
cons. While the N-gram-based framework provides a better model that
captures both source and target contexts and avoids spurious phrasal
segmentation, the ability to memorize and produce larger translation
units gives an edge to the phrase-based systems during decoding, in
terms of better search performance and superior selection of
translation units. In this paper we combine N-gram-based modeling with
phrase-based decoding, and obtain the benefits of both approaches. Our
experiments show that using this combination not only improves the
search accuracy of the N-gram model but that it also improves the BLEU
scores. Our system outperforms state-of-the-art phrase-based systems
(Moses and Phrasal) and N-gram-based systems by a significant margin
on German, French and Spanish to English translation tasks.