You are here
Advances in Word Reordering Modeling for Phrase-Based Statistical Machine Translation
We discuss the word reordering issue in phrase-based SMT and present some approaches to enhance the standard word reordering constraints used by popular tools like Moses. The presented methods redefine the permutation space for each input sentence, so that long reordering is allowed only between selected words or chunks. We show that our best approaches result in more accurate translations at no extra computational cost. Performance improvements are measured with two competitive SMT systems translating from Arabic to English and from German to English.