Enhancing Morphological Alignment for Translating Highly Inflected Languages ¤

摘要

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