The Gregorian Calendar Dates in Yoruba Language: A Machine Translation Approach

Abstract

This study discussed the development of a system for Gregorian calendar date referencing in the Yoruba language. This is with a view to solving the problem of translating Gregorian calendar date expressions into their equivalent Yoruba form with the aid of Machine Translation (MT). The study analyzed the Gregorian calendar and its various pattern of date expression, the translation into Yoruba based on context and also developed a computational-based system that translates the Gregorian calendar date phrase to the corresponding Yoruba text. The Yoruba date translation process was achieved by identifying and extracting a dated phrase in the Gregorian calendar using regular expressions, the extracted date phrase is then converted to the British pattern of date referencing which is the DD/MM/YYYY. It is this pattern of date referencing that is then translated to Yoruba form. A Context-Free Grammars (CFGs) that capture the various patterns of date referencing according to the Gregorian calendar was specified. The CFG to capture the Gregorian calendar date phrase was simulated using the Push-Down Automata (PDA) and the software for the translation of the Gregorian calendar date phrase to the corresponding Yoruba phrase was implemented with the Python programming language and the PyQt5 Graphical User Interface (GUI) module. The evaluation of the system was carried out using the Mean Opinion Score (MOS). The MOS was done using a survey method, with a sample size of 45 study area of a broadcasting station in southwest Nigeria, with linguistics students and newscasters as respondents, to elicit their knowledge of the translation of selected dates in the Gregorian calendar. The responses were compared with the output of the system. A desktop application for the translation process was deployed for the windows operating system. The result of the evaluation showed that the application was able to translate the English date phrases to Yoruba text and produce 100 percent accuracy relative to a Yoruba expert translation. The result of the respondents to the questionnaires shows that most of the respondents are not familiar with the orthography of the Yoruba language, which means that a large percentage of Yoruba native speakers cannot tone mark their responses correctly. Another observation is that most of the respondents could not translate the year numbers to Yoruba as they are not familiar with the translation of large numbers. In conclusion, this study has shown that the date referencing translation process can be computationally analyzed using the modern knowledge of computing.