Words can have more than one distinct meaning and many words can be interpreted in multiple waysrndepending on the context in which they occur. The process of automatically identifying the meaning ofrna polysemous word in a sentence is a fundamental task in Natural Language Processing (NLP). Thisrnphenomenon poses challenges to Natural Language Processing systems. There have been many effortsrnon word sense disambiguation for English; however, the amount of efforts for Amharic is very little.rnMany natural language processing applications, such as Machine Translation, Information Retrieval,rnQuestion Answering, and Information Extraction, require this task, which occurs at the semantic level.rnIn this thesis, a knowledge-based word sense disambiguation method that employs Amharic WordNetrnis developed. Knowledge-based Amharic WSD extracts knowledge from word definitions and relationsrnamong words and senses. The proposed system consists of preprocessing, morphological analysis andrndisambiguation components besides Amharic WordNet database. Preprocessing is used to prepare therninput sentence for morphological analysis and morphological analysis is used to reduce various formsrnof a word to a single root or stem word. Amharic WordNet contains words along with its differentrnmeanings, synsets and semantic relations with in concepts. Finally, the disambiguation component isrnused to identify the ambiguous words and assign the appropriate sense of ambiguous words in arnsentence using Amharic WordNet by using sense overlap and related words.rnWe have evaluated the knowledge-based Amharic word sense disambiguation using AmharicrnWordNet system by conducting two experiments. The first one is evaluating the effect of AmharicrnWordNet with and without morphological analyzer and the second one is determining an optimalrnwindows size for Amharic WSD. For Amharic WordNet with morphological analyzer and AmharicrnWordNet without morphological analyzer we have achieved an accuracy of 57.5% and 80%,rnrespectively. In the second experiment, we have found that two-word window on each side of thernambiguous word is enough for Amharic WSD. The test results have shown that the proposed WSDrnmethods have performed better than previous Amharic WSD methods.rnKeywords: Natural Language Processing, Amharic WordNet, Word Sense Disambiguation,rnKnowledge Based Approach, Lesk Algorithm