Please use this identifier to cite or link to this item: https://dl.ucsc.cmb.ac.lk/jspui/handle/123456789/545
Title: Subasa - Sinhala Spellchecker Version 2.0
Authors: Jayalatharachchi, D.E.
Issue Date: 24-Oct-2013
Abstract: Sinhala, the majority language of Sri Lanka, is still in its infancy with respect to natural language processing research and applications, of which, spell checking is an important area. One of the major issues with implementing a Sinhala spell checker is the deficiency of resources like morphological analyzers, tagged corpora and comprehensive lexica. Due to rich morphological features, using an entirely rule based approach or integration with an existing spellchecker program is difficult as well. A viable alternative is to use a data-driven approach as shown with the spell checking system named “Subasa”. This project attempts to improve the quality of the data driven spell checker “Subasa”, using minimum edit distance techniques and make the system available online to public for free. In addition, this project compares publicly available spell checkers including this one to evaluate their performance.
URI: http://hdl.handle.net/123456789/545
Appears in Collections:Master of Information Technology - 2011

Files in This Item:
File Description SizeFormat 
Final_Report.pdf
  Restricted Access
970.93 kBAdobe PDFView/Open Request a copy


Items in UCSC Digital Library are protected by copyright, with all rights reserved, unless otherwise indicated.