Development of an Amharic spelling corrector for tolerant-retrieval

  • Authors:

  • Andargachew Mekonnen

  • Affiliations:

  • Hawassa University, Hawassa, Ethiopia

  • Venue:
  • Proceedings of the International Conference on Management of Emergent Digital EcoSystems
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper describes the development of a spelling corrector for Amharic, the official language of Ethiopia. The algorithm is designed to be integrated into tolerant-retrieval search systems. The spelling corrector uses Amharic Metaphone and edit distance algorithms to offer acceptable suggestions for misspelled words. To this end, a standard dictionary for the spelling corrector to use was compiled. Application of the spelling corrector to a test data corpus indicates that the algorithm makes 81.7% valid suggestions.