Paper: Incorporating Position Information Into A Maximum Entropy/Minimum Divergence Translation Model

ACL ID W00-0707
Title Incorporating Position Information Into A Maximum Entropy/Minimum Divergence Translation Model
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2000
Authors

I describe two methods for incorporating infor- mation 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 perplex- ity than an equivalent combination of a trigram language model and the classical IBM transla- tion model 2.