Synonym Extraction for Afaan Oromoo Words

Abstract

The aim of this study is to analyze and determine appropriate contexts of using Afaan Oromoo words and phrases in writing and readings. Even though many users can easily read and write Afaan Oromoo words and phrases, they feel uncomfortable with understanding them and formulating queries for the language. This is either because of their limited vocabulary in Afaan Oromoo, or because of the possible misusages of Afaan Oromoo words. Although Afaan Oromoo is spoken by large number of people (more than 34% of the total population of the country), and rich in words, many advances still have been lacking in a computational linguistics and natural language processing area. Since the numbers of word forms that can be generated from a single stem are so many, Afaan Oromoo language is morphologically very rich and complex when compared to other Latin-based languages. In addition to this, a single Afaan Oromoo word may have different Synonyms (a word or phrase which has the same or nearly the same meaning as another word or phrase in the same language). These and similar evidences made it not only morphologically, but also structurally complex than other languages. Hence, in this study, different analysis of Synonym extraction for Afaan Oromoo words and phrases are studied. Up to our knowledge, no study done before in the area of synonym extraction, and this work is the first of its kind to investigate synonym extraction for Afaan Oromoo language. The proposed system was evaluated using the dataset consisting of 123 words collected from different sources, through considerering all appropriates dialects of Afaan Oromoo. The result from our experiment shows that the lexicon size and rules in the knowledge base play a vital role to recognize the valid synonyms for valid input words. Algorithms and techniques used in this study obtained good performance when compared to the other resource-rich languages like English. The result obtained encourages the undertaking of further research in the area, especially with the aim of developing a full-fledged Afaan Oromoo synonym extraction.