Happy New Year 2015. We have a great news for you.
KONKANVERTER 2.1 is now ready for your service. Please feel free to try it out and give us the feedback.
KONKANVERTER 2.1 is A Finite State Transducer based Statistical Machine Transliteration Engine for Konkani Language. For more detail about this please watch out this space. We will post the Technical Paper written by Our Techie Vinodh Rajan for your reference soon. (Ok its here: http://www.aclweb.org/anthology/W/W14/W14-5502.pdf)
(We have developed a finite state transducer based transliteration engine called Konkanverter that performs statistical machine transliteration between three different scripts used to write the Konkani language. The statistical machine transliteration system consists of cascading finite state transducers combining both rule-based and statistical approaches. Based on the limited availability of parallel corpora, this cascading approach is found to perform better than a pure rule-based approach or pure statistical approach. – Vinodh Rajan) Thank you Vinodh for this great work.
I thank Poet Melwyn Rodrigues for using Konkanverter regularly to transliterate from Kannada script to Devanagari Script for publishing in Kavitaa.com. Without his support and help Konkanverter could not have reached this stage.
KONKANVERTER 2.1 is enabled with Correction Submission tool. With this now you can submit the correction of incorrect words for evaluation. Feel free to Transliterate. If you feel certain word is not correct, please click on the word and edit the word using Unicode Font. Corrections suggested by you will be submitted for evaluation and acceptance. Thank you so much for your interest in Konakni and KONKANVERTER.
Please let me know your feedback.
Thank you very much,
World Institute of Konkani Language,
World Konkani Centre,
Just to inform you about the new developments at KONKANVERTER Project.
1. I would like to put on record our sincere gratitude to Asmitay Prathistan, Goa for loaning us the Devanagari Konkani Text Corpus they had developed. This corpus contains about 3 million words.
2. Two more persons joined our team, I welcome Mr. Isidore Dantas and Ms. Jascinta Pinto who are working on ROMI and Kannada script Text corpora.
3. Happy to let you know that we have already cracked some of the serious issues like “O” in romi through Corpus Linguistic methods introduced by Vinodh Rajan. It will be visible in the next version though.
4. Thanks for waiting, KONKANVERTER Ver. 2 is expected soon. Please bear with us.
Thanks & Regards,