Analysis on bilingual machine translation systems for English and Tamil

Language in any form is the fundamental requirement to communicate and interact within the human society. In this globalization era, we interact with people from different regions and linguistic backgrounds as per our interest in social, cultural, economical, educational and professional domain. It is quite tough, rather impossible to know all the languages. Thus we need a computerized approach to convert one natural language to another as per the necessity. In this paper, we discuss statistical machine translation for the languages Tamil and English limited to travel domain. The system aims to translate from English to Tamil and vice versa. GIZA++ tool is used for training the statistical models. The performance of the system is analyzed based on various performance metrics like BLEU score and TER.

[1]  Miles Osborne,et al.  Statistical Machine Translation , 2010, Encyclopedia of Machine Learning and Data Mining.

[2]  Sneha Tripathi,et al.  Approaches to machine translation , 2010 .

[3]  Mitali Halder,et al.  English-Hindi Transliteration by Applying Finite Rules to Data before Training Using Statistical Machine Translation , 2013, 2013 International Conference on IT Convergence and Security (ICITCS).

[4]  Alon Lavie,et al.  Evaluating the Output of Machine Translation Systems , 2010, AMTA.

[5]  Rakesh Chandra Balabantaray,et al.  Odia transliteration engine using moses , 2014, 2014 2nd International Conference on Business and Information Management (ICBIM).

[6]  Kiyohiro Shikano,et al.  Response generation based on statistical machine translation for speech-oriented guidance system , 2012, Proceedings of The 2012 Asia Pacific Signal and Information Processing Association Annual Summit and Conference.

[7]  Chandranath Adak.  A bilingual machine translation system: English & Bengali , 2014, 2014 First International Conference on Automation, Control, Energy and Systems (ACES).

[8]  Fuji Ren.  Dialogue machine translation system using multiple translation processors , 2000, Proceedings 11th International Workshop on Database and Expert Systems Applications.

[9]  U. Shrawankar,et al.  Probabilistic language model for template messaging based on Bi-gram , 2012, IEEE-International Conference On Advances In Engineering, Science And Management (ICAESM -2012).

[10]  Ahmed A. Rafea,et al.  Tuning statistical machine translation parameters using perplexity , 2005, IRI -2005 IEEE International Conference on Information Reuse and Integration, Conf, 2005..