Automatic Morphological Synthesizer for Afaan Oromoo
| dc.contributor.advisor | Midekso, Dida (PhD) | |
| dc.contributor.author | Abeshu, Abebe | |
| dc.date.accessioned | 2018-06-13T06:34:00Z | |
| dc.date.accessioned | 2023-11-29T04:05:41Z | |
| dc.date.available | 2018-06-13T06:34:00Z | |
| dc.date.available | 2023-11-29T04:05:41Z | |
| dc.date.issued | 2010-06 | |
| dc.description.abstract | Computational morphology is an important component of most natural language processing tasks. Morphological generation, the process of returning one or more surface forms from a sequence of underlying (lexical) forms, can provide fine-grained parts of speech information and help resolve necessary syntactic agreements. In addition, morphological synthesis systems are used as components in many applications, including machine translation, spell-checker, speech recognition, dictionary (lexicon) compilation, POS tagging, morphological analysis, conversational systems, automatic sentence construction and many others. Generally, the thesis describes processes of automated morphological synthesis ranging from manually synthesizing words to developing a prototype and conducting an experiment. The automated generation of word forms avoids the storage of exhaustive lexicons and thereby saves memory requirement. The devepment of such systems demand an in-depth study of the morphology of the language used. Morphological synthesizers have been developed for languages like English. But there is no such a system for Afaan Oromoo, the working language of Oromia national regional sate, and one of the major languages in Ethiopia. This study is, thus, an attempt to develop automatic morphological synthesizer for Afaan Oromoo. Algorithms that take the morphological properties of Afaan Oromoo into consideration are developed from scratch and applied, as there are no previous such attempts. We employed rule based computational model to design and develop the prototype referred to as HORSIISAA. The performance of the system on average is 96.28% for verbs and 97.46% for nouns. The result obtained encourages the undertaking of further research in the area, especially with the aim of developing a full-fledged Afaan Oromoo morphological synthesizer. Keywords: Morphology, Morphological synthesis, Natural language processing, Morphological generation, Morphological processing, Afaan Oromoo, word forms | en_US |
| dc.identifier.uri | http://etd.aau.edu.et/handle/123456789/575 | |
| dc.language.iso | en | en_US |
| dc.publisher | Addis Ababa University | en_US |
| dc.subject | Morphology; Morphological Synthesis;Natural Language Processing; Morphological Generation; Morphological Processing; Afaan Oromoo; Word Forms | en_US |
| dc.title | Automatic Morphological Synthesizer for Afaan Oromoo | en_US |
| dc.type | Thesis | en_US |