Exploring the Challenges of SMT Project for Resource Scarce Language in Africa: A Case Study of English-Yoruba Language Machine Translation

Abstract

The challenges of Machine Translation (MT) and in particular Statistical Machine Translation (SMT) have been explored and categorized. But little is known about African languages which are said to be resource scare languages. Hence, this paper explored the challenges of SMT for African languages using English-Yoriiba MT as case study. Fagunwa's books and its English translated equivalents were used as corpus and MoSes was used as the language toolkit. In the first part series of this study, we observed that the challenges of Yoriiba SMT were inexhaustible. However, the challenges of Africa SMT were categorized into two: technical and sociocultural peculiarities.