Previous abstract | Contents | Next abstract

Incorporating Position Information into a Maximum Entropy/Minimum Divergence Translation Model

I describe two methods for incorporating information about the relative positions of bilingual word pairs into a Maximum Entropy/Minimum Divergence translation model. The better of the two achieves over 40\% lower test corpus perplexity than an equivalent combination of a trigram language model and the classical IBM translation model 2.


George Foster, Incorporating Position Information into a Maximum Entropy/Minimum Divergence Translation Model. In: Proceedings of CoNLL-2000 and LLL-2000, Lisbon, Portugal, 2000. [ps] [pdf] [bibtex]
Last update: June 27, 2001. erikt@uia.ua.ac.be