A Joint Source Channel Model for the English to Bengali Back Transliteration

  • Tirthankar Dasgupta
  • Manjira Sinha
  • Anupam Basu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8284)


In this paper we present an English-to-Bengali back transliteration system that can be used to transliterate Bengali texts written in Romanized English, back to its original script. Our proposed system uses a bilingual parallel corpus of English-Bengali transliterated word pairs and applies both the orthographic as well as phonetic information to two different computational models namely, the joint source channel model and the trigram model, to automatically identify, extract and learning of transliteration unit (TU) pairs from both the source and target language words. Finally, the system predicts the top 10 best possible outcome of the given input text. We further extend our work to make the target word prediction module more robust. This is done by the phonological analysis of the generated target sentence. Both the models have been evaluated with a set of 2000 Romanized Bengali test words. Our initial evaluation results clearly shows that the joint source channel model performs much better than the trigram model.


Bengali transliteration joint source channel model evaluation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ekbal, A., Naskar, S., Bandyopadhyay, S.: A modified joint source-channel model for transliteration. In: Proceedings of the COLING/ACL on Main Conference Poster Sessions, pp. 191–198 (2006)Google Scholar
  2. 2.
    Zhang, M., Li, H., Kumaran, A., Liu, M.: Report of NEWS 2012 machine transliteration shared task. In: Proceedings of the 4th Named Entity Workshop, pp. 10–20 (2012)Google Scholar
  3. 3.
    Schwartz, R., Chow, Y.L.: The N-best algorithm: An efficient and Exact procedure for finding the N most likely sentence hypothesi. In: Proceedings of ICASSP 1990, Albuquerque, pp. 81–84 (1990)Google Scholar
  4. 4.
    Knight, K., Graehl, J.: Machine Transliteration. Computational Linguistics 24(4), 599–612 (1998)Google Scholar
  5. 5.
    Ehara, Y., Tanaka-Ishii, K.: Multilingual text entry using automatic language detection. In: Proceedings of IJCNLP, pp. 441–448 (2008)Google Scholar
  6. 6.
    Lee, C.-J., Chang, J.S.: Acquisition of English-Chinese Transliteration Word Pairs from Parallel-Aligned Texts using a Statistical Machine (2003)Google Scholar
  7. 7.
    Translation Model. In: Proceedings of HLT-NAACL Workshop: Building and Using parallel Texts Data Driven Machine Translation and Beyond, Edmonton, pp. 96–103 (2003)Google Scholar
  8. 8.
    Li, H., Kumaran, A., Zhang, M., Pervouchine, V.: Report of NEWS 2009 Machine Transliteration Shared Task. In: Proceedings of ACL-IJCNLP 2009 Named Entities Workshop, pp. 1–18 (2009)Google Scholar
  9. 9.
    Goto, I., Kato, N., Uratani, N., Ehara, T.: Transliteration considering Context Information based on the Maximum Entropy Method. In: Proceeding of the MT-Summit IX, New Orleans, USA, pp. 125–132 (2003)Google Scholar
  10. 10.
    Li, H., Min, Z., Jian, S.: A Joint Source-Channel Model for Machine Transliteration. In: Proceedings of the 42nd Annual Meeting of the ACL (ACL 2004), Barcelona, Spain, pp. 159–166 (2004)Google Scholar
  11. 11.
    Lee, J.S., Choi, S.: English to Korean statistical transliteration for information retrieval. Computer Processing of Oriental Languages 12(1), 17–37 (1998)MathSciNetGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  • Tirthankar Dasgupta
    • 1
  • Manjira Sinha
    • 1
  • Anupam Basu
    • 1
  1. 1.Indian Institute of Technology KharagpurIndia

Personalised recommendations