Better Alignments = Better Translations?
Kuzman Ganchev, Joäo Graça, Ben Taskar · Scholarly Commons (University of Pennsylvania) · 2008
Automatic word alignment is a key step in training statistical machine translation sys-tems. Despite much recent work on word alignment methods, alignment accuracy in-creases often produce little or no improve-ments in machine translation quality. In this work we analyze a recently proposed agreement-constrained EM algorithm for un-supervised alignment models. We attempt to tease apart the effects that this simple but ef-fective modification has on alignment preci-sion and recall trade-offs, and how rare and common words are affected across several lan-guage pairs. We propose and extensively eval-uate a simple method for using alignment models to produce alignments better-suited for phrase-based MT systems, and show sig-nificant gains (as measured by BLEU score) in end-to-end translation systems for six lan-guages pairs used in recent MT competitions. 1