Paper: Semi-Supervised Training For Statistical Word Alignment

ACL ID P06-1097
Title Semi-Supervised Training For Statistical Word Alignment
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2006
Authors

We introduce a semi-supervised approach to training for statistical machine transla- tion that alternates the traditional Expecta- tion Maximization step that is applied on a large training corpus with a discriminative step aimed at increasing word-alignment quality on a small, manually word-aligned sub-corpus. We show that our algorithm leads not only to improved alignments but also to machine translation outputs of higher quality.