Abstract
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.
Cite
CITATION STYLE
Foster, G. (2000). Incorporating position information into a maximum entropy/minimum divergence translation model. In Proceedings of the 4th Conference on Computational Natural Language Learning, CoNLL 2000 and of the 2nd Learning Language in Logic Workshop, LLL 2000 - Held in cooperation with ICGI 2000 (pp. 37–42). Association for Computational Linguistics (ACL). https://doi.org/10.3115/1117601.1117610
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
