Improved statistical alignment models
Franz Josef Och, Hermann Ney · Annual Meeting of the Association for Computational Linguistics (ACL) · 2000
In this paper, we present and compare various single-word based alignment models for statistical machine translation. We discuss the five IBM alignment models, the Hidden-Markov alignment model, smoothing techniques and various modifications. We present different methods to combine alignments. As evaluation criterion we use the quality of the resulting Viterbi alignment compared to a manually produced reference alignment. We show that models with a first-order dependence and a fertility model lead to significantly better results than the simple models IBM-1 or IBM-2, which are not able to go beyond zero-order dependencies.
Cited by 1,001 works. doi:10.3115/1075218.1075274 Open-access PDF
Authors
References
- An inequality and associated maximization technique in statistical estimation of probabilistic functions of a Markov process
- The mathematics of statistical machine translation: parameter estimation
- HMM-based word alignment in statistical translation
- A comparison of alignment models for statistical machine translation
- Statistical Machine Translation
- But dictionaries are data too
- Manual Annotation of Translational Equivalence: The Blinker Project
- Forming Word Classes by Statistical Clustering for Statistical Language Modelling
- Evaluation of Word Alignment Systems