Authors : Adebimpe Esan, Bolaji Omodunbi, Olatayo Olaniyan, Precious Odiase and Timileyin Olaleye
Abstract: An Adjectival Phrase-based (ADJP) system was developed in this article for English to Yorùbá machine translation. The data for the developed system was extracted from locally spoken words and stored in a database. JFLAP was used to test the re-write rules and grammar using parse trees and Python programming language is the core programming language used in developing the system. The developed translator was evaluated by comparing expert’s translated phrases to that of the developed translator and the experimental subject respondents using the Mean Opinion Score (MOS) technique based on word orthography. Results show that the expert’s average accuracy was 100% while the respondent’s was 76.3% and the developed machine translator’s accuracy was 95.5%. In conclusion, the developed system’s accuracy is close to the expert’s and higher than that of the experimental subject respondent’s.
Adebimpe Esan, Bolaji Omodunbi, Olatayo Olaniyan, Precious Odiase and Timileyin Olaleye, 2020. Development of an Adjectival Phrase-Based English to Yorùbá Machine Translator. International Journal of Soft Computing, 15: 97-102.