A Systematic Comparison of Various Statistical Alignment Models


We present and compare various methods for computing word alignments using statistical or heuristic models. We consider the five alignment models presented in Brown, Della Pietra, Della Pietra, and Mercer (1993), the hidden Markov alignment model, smoothing techniques, and refinements. These statistical models are compared with two heuristic models based on… (More)
DOI: 10.1162/089120103321337421


22 Figures and Tables


Citations per Year

4,041 Citations

Semantic Scholar estimates that this publication has 4,041 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Och2003ASC, title={A Systematic Comparison of Various Statistical Alignment Models}, author={Franz Josef Och and Hermann Ney}, journal={Computational Linguistics}, year={2003}, volume={29}, pages={19-51} }