Lexicalized Reordering for Left-to-Right Hierarchical Phrase-based Translation
Maryam Siahbani, Anoop Sarkar · 2017
Phrase-based and hierarchical phrasebased (Hiero) translation models differ radically in the way reordering is modeled.Lexicalized reordering models play an important role in phrase-based MT and such models have been added to CKY-based decoders for Hiero.Watanabe et al. (2006) propose a promising decoding algorithm for Hiero (LR-Hiero) that visits input spans in arbitrary order and produces the translation in left to right (LR) order which leads to far fewer language model calls and leads to a considerable speedup in decoding.We introduce a novel shift-reduce algorithm to LR-Hiero to decode with our lexicalized reordering model (LRM) and show that it improves translation quality for Czech-English, Chinese-English and German-English.