Computational modelling of Yorùbá numerals in a number-to-text conversion system

Abstract

In this paper, we examine the processes underlying the Yorùbá numeral system and describe a computational system that is capable of converting cardinal numbers to their equivalent Standard Yorùbá number names. First, we studied the mathematical and linguistic basis of the Yorùbá numeral system so as to formalise its arithmetic and syntactic procedures. Next, the process involved in formulating a ContextFree Grammar (CFG) to capture the structure of the Yorùbá numeral system was highlighted. Thereafter, the model was reduced into a set of computer programs to implement the numerical to lexical conversion process. System evaluation was done by ranking the output from the software and comparing the output with the representations given by a group of Yorùbá native speakers. The result showed that the system gave correct representation for numbers and produced a recall of 100% with respect to the collected corpus. Our future study is focused on developing a text normalisation system that will produce number names for other numerical expressions such as ordinal numbers, date, time, money, ratio, etc. in Yorùbá text.

Web-Based Yorùbá Numeral Translation System

“…The study by [16], shows that Yorùbá numeral maintains a VCV (disyllabic) open syllabic structure while English numeral has a monosyllabic closed syllabic structure CVC for numeral 1, 5, 9 and 10, CVCC for 6, and VC for 8. The study also agreed with [14] and [12] that, numerals 200, 300 and 400 are basic in Yorùbá numeral system while numerals 500, 700 and 900 are derived through a combination of subtraction and multiplication whereas 600, 800 and 1000 are derived by multiplying 200 by 3, 4, and 5 respectively. The work further explain that, in Yorùbá 'l' and 'n' are allophones, therefore, while 'n' goes with nasalised vowel, 'l' goes with oral vowels.…”

“…In the production rule, NP, represent noun phrase or simply number phrase, MP represents multiplicative base, and NUM is the generated number. As reported in [14], Yorùbá numeral system is very methodical, therefore, an efficient computational system is necessary to accurately derived it numeral representation. It is as seen as a near difficult form of numeral system.…”

“…But in [13], it was argued that where the European decimal system is based upon units of ten and the functions of additions and multiplication as it is used in English numeral, Yorùbá numeral system is based upon units of both ten and twenty and the function of addition, multiplication and subtraction. [14] Further argued that, Yorùbá numeral system is not fully vigesimal, and that elements of decimal and quinary (base 5) are also used in its numeral representation.…”

“…In the study conducted by [14], it was explain that, apart from Yorùbá, other African languages with vigesimal numeral system are; Madingo, Mundo, Logone, Nupe, Nembe, Bingo, Efik, Vie, Igbo and Afadeh. It was emphasize that Yorùbá counting system has lexemes for basic numbers from one (1) to ten (10) and six higher numerals (twenty (20), thirty (30), two hundred (200), three hundred (300), four hundred (400), and twenty thousand (20000).…”

A Hindu-Arabic to Hausa Number Transcription System

“…A numeral system consists of a set of symbols used for recording numbers and number names (Hess, 1970). Today, numbers are seen as tools that are absolutely necessary for our day-to-day activities (Agbeyangi et al, 2016), as they are used in trade, cosmology, mathematics, divination, music and medicine (Akinade & Odejobi, 2014). The invention of a numeration system is regarded as one of the great accomplishments of man, and the Hindu-Arabic, simply Arabic (0,1,2,3,4,5,6,7,8,9) is one of the most widely used numerals (Hess, 1970).…”