Open Access Open Access  Restricted Access Subscription or Fee Access

Statistical Machine Translation System

U. A. Rajitha, R. Hema

Abstract


One of the applications of Natural Language Processing is Machine Translation. Machine Translation means that by use of software to translate text or speech from one language to another language. Machine translation refers to the use of computers to automate the task of translating between human languages. Machine Translation with Statistical approach helps to do machine translation for any language pair by the use of Statistical tools. This paper describes machine translation with Statistical approach to produce better translation for English to Tamil translation system. We have collected parallel corpus from children story domain. We aligned the sentences manually. SRILM tool kit is used for language modeling. GIZA++ tool is used to build translation model. Moses decoder is used to produce better translation from English text to Tamil text.

Keywords


Statistical Machine Translation, Language Modeling

Full Text:

PDF

References


Andreas Stolcke, Speech Technology and Research Laboratory SRI International, Menlo Park, CA, U.S.A. “Srilm —An Extensible Language Modeling Toolkit” Proceedings of the IEEE, 88(8). 10. 2002.

Al-Onaizan, Y., Curin, J., Jahr, M., Knight, K., Lafferty, J., Melamed, D., Och, F.-J., Purdy, D., Smith, N. A., and Yarowsky, D.” Statistical Machine Translation, Final Report”. JHU Workshop1999. Technical Report, CLSP/JHU (1999)

Brown, P. F., Della-Pietra, S. A., Della-Pietra, V.J. and Mercer, R. L. “The mathematics of Statistical machine translation: Parameter estimation”. Computational Linguistics, 19(2) (1993) 263-311.

Franz Josef Och and Hermann Ney. “Statistical Machine Translation” EAMT Workshop, pp. 39-46, Ljubljana, Slovenia, May 2000.

Geer, D.”Statistical machine translation gains respect” Computer Publication Date: Oct. 2005 Volume: 38, Issue: 10 on pages: 18- 21

Germann, U.” Building a Statistical Machine Translation System from Scratch: How Much Bang Can We Expect for the Buck?”Proceedings of the Data-Driven MT Workshop of ACL 01. Toulouse, France (2001).

Kevin Knight. “A Statistical MT Tutorial Workbook” prepared in connection with the JHU summer workshop April 30, 1999.

“Moses – a factored phrase-based beam-search decoder for machine translation”. URL:http://www.statmt.org/moses/.13 April 2007.

Och, F.J., Tillmann, C. and Ney, H.” Improved alignment models for statistical machine translation”. In Proceedings of the 4th Conference on Empirical Methods in Natural Language Processing (EMNLP), Maryland, 1999.

Philipp Koehn, Hieu Hoang, Alexandra Birch: Chris Callison-Burch, University of Edinburgh. “Moses: Open Source Toolkit for Statistical Machine Translation” Proceedings of the ACL 2007 Demo and Poster Sessions, pages 177–180.

Ruvan Weerasinghe, Dept. of Statistics & Comp. Science, University of Colombo, Sri Lanka. ”A Statistical Machine Translation Approach to Sinhala-Tamil Language Translation”


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.