Articles
An Open-Source Data Driven Spell Checker for Sinhala
Authors:
Ruwan Asanka Wasala ,
Was at the Language Technology Research Laboratory, University of Colombo School of Computing, 35, Reid Avenue, Colombo 07, LK
About Ruwan
He is now with the Localisation Research Centre, Department of Computer Science and Information Systems, University of Limerick, Limerick, Ireland
Ruwan Weerasinghe,
University of Colombo School of Computing, 35, Reid Avenue, Colombo 07, LK
Randil Pushpananda,
Language Technology Research Laboratory, University of Colombo School of Computing, 35, Reid Avenue, LK
Chamila Liyanage,
Language Technology Research Laboratory, University of Colombo School of Computing, 35, Reid Avenue, LK
Eranga Jayalatharachchi
University of Colombo School of Computing, 35, Reid Avenue, Colombo 07, LK
Abstract
In this paper we describe the construction of a spell checker for Sinhala, the language spoken by the majority in Sri Lanka. Due to its morphological richness, the language is difficult to enumerate completely in a lexicon. The approach described is based on n-gram statistics and is relatively inexpensive to construct without deep linguistic knowledge. This approach is particularly useful as there are very few linguistic resources available for Sinhala at present. The proposed algorithm has been shown to be able to detect and correct many of the common spelling errors of the language. Results show a promising performance achieving an average accuracy of 82%. This technique can also be applied to construct spell checkers for other phonetic languages whose linguistic resources are scarce or non-existent.
DOI: http://dx.doi.org/10.4038/icter.v3i1.2844
ICTer Vol.3 No.1 2010
How to Cite:
Wasala, R.A., Weerasinghe, R., Pushpananda, R., Liyanage, C. and Jayalatharachchi, E., 2011. An Open-Source Data Driven Spell Checker for Sinhala. International Journal on Advances in ICT for Emerging Regions (ICTer), 3(1), pp.11–24. DOI: http://doi.org/10.4038/icter.v3i1.2844
1741
Views
1582
Downloads
Published on
03 Mar 2011.
Peer Reviewed
Downloads
