Back close

Sequence labeling approach for English to Tamil Transliteration using Memory based Learning

Publication Type : Conference Paper

Publisher : ICON - 2008 6th International Conference on Natural Language Processing

Source : ICON - 2008 6th International Conference on Natural Language Processing (2008)

Url : http://mt-archive.info/ICON-2008-Vijaya.pdf

Campus : Coimbatore

School : School of Engineering

Center : Computational Engineering and Networking

Department : Electronics and Communication

Year : 2008

Abstract : Machine transliteration is an automatic method that converts words/characters in one alphabetical system to corresponding phonetically equivalent words/characters in another alphabetical system. Machine Transliteration has been used extensively to assist machine translation, data mining, cross language information retrieval and more recently in popular web portals, SMS and chat systems. In this paper, we propose a method where transliteration problem is modeled as a sequence labeling problem and proceed to solve this using Memory-based learning. We have applied this technique for transliterating English to Tamil and achieved exact Tamil transliterations for 84.16% of English names. We get an accuracy of 93.33% when we choose from the first five ranked transliterations.

Cite this Research Publication : V. MS, Vishwa, S. G. Amrita, V, D., VP, A., and Dr. Soman K. P., “Sequence labeling approach for English to Tamil Transliteration using Memory based Learning”, in ICON - 2008 6th International Conference on Natural Language Processing, 2008.

Admissions Apply Now