• Getnet Assefa

This study is conducted to develop an effective spelling checker system for the Amharic language. Currently there are few natural language processing works that have been done for this language. However, there is no effective spell checker system developed for this language yet. In this study, an effective spell checker mode is developed and then implemented using visual basic programming language. For the prototype development, two basic algorithms were applied in different phases of the study. The Metaphone algorithm is applied for spelling error detection and edit distance algorithm is applied for selecting the most possible correct word for the miss spelled word. For a better usability the developed system is embedded in the Microsoft Office word 2010 word processing system as an add-in. Finally, the developed prototype is tested using test data of 500 words and from these words, 100 of them are miss-spelled deliberately and a dictionary of 125,000 words is used. In the testing phase, the system shows excellent result in its error detection and also in its suggestions.

Amharic, Dictionary, Natural Language Processing, Spellchecker

"Automatic Amharic spelling error detection and correction using hybrid approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 6, page no.605-611, June-2018, Available :http://www.jetir.org/papers/JETIR1806682.pdf

"Automatic Amharic spelling error detection and correction using hybrid approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 6, page no. pp605-611, June-2018, Available at : http://www.jetir.org/papers/JETIR1806682.pdf