Wprowadzenie do metod statystycznych w tłumaczeniu automatycznym

• Authors: Marcin Junczys-Dowmunt

Title variants

EN

An introduction to statistical methods in machine translation

• Languages of publication: PL

Abstracts

PL

The intention of this article is to provide a concise introduction to the basic mathematical concepts of statistical translation models as they were introduced by Brown et al. (1993) in their groundbreaking work The Mathematics of Statistical Machine Translation: Parameter Estimation. We concentrate on a simplified description of the first two translation models known as IBM Model 1 and 2. It is one major aim of this work to serve as tutoring material for students of computational linguistics, mathematics or computer science and therefore a lot of comments, additional examples and step-by-step explanations are given, augmenting the original formula by Brown et al. (1993). For both discussed models the calculations for a small parallel corpus are described in detail. 

EN

The intention of this article is to provide a concise introduction to the basic mathematical concepts of statistical translation models as they were introduced by Brown et al. (1993) in their groundbreaking work The Mathematics of Statistical Machine Translation: Parameter Estimation. We concentrate on a simplified description of the first two translation models known as IBM Model 1 and 2. It is one major aim of this work to serve as tutoring material for students of computational linguistics, mathematics or computer science and therefore a lot of comments, additional examples and step-by-step explanations are given, augmenting the original formula by Brown et al. (1993). For both discussed models the calculations for a small parallel corpus are described in detail.

• Publisher: Uniwersytet im. Adama Mickiewicza w Poznaniu
• Journal: Investigationes Linguisticae
• Year: 2008
• Volume: 16
• Pages: 44-66

Dates

published

2008-12-15

Contributors

author

Marcin Junczys-Dowmunt

• Instytut Językoznawstwa, Uniwersytet im. Adama Mickiewicza al. Niepodległości 4, 61-874 Poznań

References

• Al-Onaizan, Y., J. Curin, M. Jahr, K. Knight, J. Lafferty, I. Melamed, F. Och, D. Purdy, N. Smith i D. Yarowsky (1999). Statistical machine translation. Rap. tech., JHU workshop.
• Brown, P. F., V. J. Della Pietra, S. A. Della Pietra i R. L. Mercer (1993). The mathematics of statistical machine translation: parameter estimation. Comput. Linguist., 19(2):263-311.
• Dempster, A. P.,N. M. Laird i D. B. Rubin (1977). Maximum Likelihood from Incomplete Data via the EM Algorithm.
• Journal of the Royal Statistical Society. Series B (Methodological), 39(1): 1-38.
• Jurafsky, D. i J. H. Martin (2000). Speech andLanguage Processing: An Introduction to Natural Language Processing, Computational Linguistics and Speech Recognition (International Edition). Prentice Hall.
• Kay, M. i M. Roscheisen (1993). Text-trańslatioń aligńmeńt. Comput. Linguist., 19(1): 121-142.
• Knight, K. (1999). A Statistical MT Tutorial Workbook. Niepublikowane.
• Manning, C. D. i H. Schutze (1999). Foundations o f Statistical Natural Language Processing. The MIT Press.
• Melamed, I. D. (2000). Models of translational eąuwalence among words. Comput. Linguist., 26(2):221-249.
• Och, F. J. i H. Ney (2003). A systematic comparison of various statistical aligńmeńt models. Comput. Linguist., 29(1): 19-51.
• Somers, H. (2001). Bilingual parallel corpora and Language Engineering.

Identifiers

DOI

10.14746/il.2008.16.5