SpellCheF: Spelling Checker and Corrector for Filipino
Charibeth K. Cheng | Cedric Paul Alberto | Ian Anthony Chan | Vazir Joshue Querol
Discipline: Languages
Abstract:
SpellCheF is a spell checker for Filipino that uses a hybrid approach in detecting and correcting misspelled words in a document. Its approach is composed of dictionary-lookup, n-gram analysis, Soundex and character distance measurements. It is a plug-in to OpenOffice Writer. Two spelling rules and guidelines, namely, the Komisyon sa Wikang Filipino 2001 Revision of the Alphabet and Guidelines in Spelling the Filipino Language (or KWF), and the Gabay sa Editing sa Wikang Filipino (or GABAY) rulebooks, were incorporated into the system. SpellCheF is composed of three modules, namely the lexicon builder, the detector and the corrector. These three modules used both manual-formulated and learned rules to carry out their tasks. Test results showed that the lexicon builder was able to correctly categorize words based on the spelling rules used. It also generated three databases, namely, (1) the KWF-compliant words database, (2) the Gabay-compliant words database, and (3) the database of words common to both KWF and GABAY. The detector module had an overall error rate of 7% in identifying misspellings. Furthermore, it was observed that n-gram analysis performed better than the simple dictionary look-up. The corrector module had a 94% accuracy rate in generating word suggestions. Results also showed that using the soundex code, more suggestions were generated compared to the use of n-gram analysis. However, the first character of the soundex-based suggestions was always the same as the first character of the misspelled word.
Full Text:
Note: Kindly Login or Register to gain access to this article.