Enhancing morphological alignment for translating highly inflected languages

  • Authors:
  • Minh-Thang Luong;Min-Yen Kan

  • Affiliations:
  • National University of Singapore;National University of Singapore

  • Venue:
  • COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

We propose an unsupervised approach utilizing only raw corpora to enhance morphological alignment involving highly inflected 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 alignment and demonstrates improved end-to-end translations for English-Finnish and English-Hungarian.