A Word Sense Disambiguation Model for Amharic Words using Semi-Supervised Learning Paradigm

Abstract

The main objective of this research was to design a WSD (word sense disambiguation) prototype model for Amharic words using semi-supervised learning method to extract training sets which minimizes the amount of the required human intervention and it can produce considerable improvement in learning accuracy. Due to the unavailability of Amharic word net, only five words were selected. These words were atena (አጠና), derese (ደረሰ), tenesa (ተነሳ), bela (በላ) and ale (አለ). A separate data sets using five ambiguous words were prepared for the development of this Amharic WSD prototype. The final classification task was done on fully labelled training set using Adaboost, bagging, and AD tree classification algorithms on WEKA package.

Keywords: Ambiguity Bootstrapping Word Sense disambiguation