Paper: Enhancing Morphological Alignment for Translating Highly Inflected Languages

ACL ID C10-1084
Title Enhancing Morphological Alignment for Translating Highly Inflected Languages
Venue International Conference on Computational Linguistics
Session Main Conference
Year 2010
Authors

We propose an unsupervised approach uti- lizing only raw corpora to enhance mor- phological alignment involving highly in- flected languages. Our method focuses on closed-class morphemes, modeling their influence on nearby words. Our language- independent model recovers important links missing in the IBM Model 4 align- ment and demonstrates improved end-to- end translations for English-Finnish and English-Hungarian.