Adding Amharic to a Unification-Based Machine Translation System: An Experiment (Sabest)

This book presents a morphosyntactic description of the Amharic language. Amharic belongs to the Semitic language family and is one of the most widely spoken languages in Ethiopia. The aims of this book are to describe Amharic morphosyntax using the concepts of contemporary grammar formalisms, such as Dependency Grammar, Head-Driven Phrase Structure Grammar and Lexical Functional Grammar. Further it presents the results of the application and evaluation of different natural language processing tools and techniques, such as finite state morphological analysis, unification-based formalisms, transfer-based machine translation systems, and machine learning techniques, to the Amharic language. This publication is of interest to students and researchers in computational linguistics. Specifically, it benefits those with a special interest in the morphosyntactic description and/or computational treatment of Semitic languages, in general, and Amharic, in particular.