Linguistics & African Languages
Permanent URI for this communityhttps://repository.ui.edu.ng/handle/123456789/287
Browse
4 results
Search Results
Item Ife-itumo-loju: Wiwa Ord-iperi Fun Arun Kokoro-Apa-Soja-Ara (KASA) ati Ebola(Library Press @ UF, 2021) Odoje, C. O.Ọ̀pọ̀ ọ̀nà ni àwọn onímọ̀ ti dá lábàá fún ṣíṣe àwárí tàbí ìṣèdá ọ̀rọ̀-ìpẹ̀rí nínú èdè Yorùbá, lára wọn ni ìṣàlàyé, ìhùn-prọ́-pọ̀, ìfìṣàpẹẹrẹ, ìlọ́wẹ̀, ọ̀rọ̀-àyálọ̀, ìfẹ́-ìtumọ̀-lójú àti bẹ́ẹ̀ bẹ́ẹ̀ lọ. Ìfẹ́-ìtumọ̀-lójú ni ó jẹ́ ìwádìí yìí lógún nípa wíwá prọ́-ìpẹ̀rí fún àrùn Kókóró-Àpá-Sọjà-Àrà (KASA) àti Ebola. A ṣe àgbéyẹ̀wò 1572 ọ̀rọ̀ tí Yusuff, Adétúnjí àti Odòjé (2017) jẹ́ olóòtú fìlìmù, a sì fa àwọn tí wọ́n fẹ́ ìtumọ̀ wọn lójú yọ fún iṣẹ́ ìwádìí tí a ṣe. A ṣàwárí pé oríṣìíríṣìí mẹ́ta ọ̀tọ̀ọ̀tọ̀ ni irú àwọn ọ̀rọ̀ yìí; kò sì sí ìyọnu láti ní òye ìtumọ̀ tuntun tí a wá wọ àwọn ọ̀rọ̀ náà lórí wọn. Ó tilẹ̀ mú ìtumọ̀ gbé tán bá àwọn ọ̀rọ̀ tuntun tí a lò wọ́n fún.Item Human Evaluation of Yorùbá-English Google Translation(Creative Common Attribution-Non-Commercial 4.0 International, 2016) Odoje, C. O.The task of Machine Translation is not just about translating the text of a language to another but also its evaluation so as to monitor its improvement particularly in fluency, accuracy and efficiency. However, the only available free machine translation on Yoruba-English is “Google Translate” which has been observed to be grossly inadequate. This paper therefore examines translations done by Google Translate as against human translation in order to investigate why machine translation applications make some errors while translating human natural language. There are many matrix evaluators to do this. This paper adopts human evaluation also known as manual evaluation which is considered to be more efficient, but costly. The paper adopts Ibadan and Akungba Structured Sentence Paradigm to evaluate the translators (Google Translate and human). The translations were sent to twenty human evaluators out of which only eleven responded. The responses were subjected to statistical analysis. Findings show that human translation fares better in terms of accuracy and fluency which are informed by the quality and the quantity of training data. This paper suggests that more data, especially literary texts, should be acquired to train the translator for general efficiency and fluency.Item Exploring the Challenges of SMT Project for Resource Scarce Language in Africa: A Case Study of English-Yoruba Language Machine Translation(Research in African Languages & Linguistics, 2013) Odoje, C. O.; Akinola S. O.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.Item Towards Machine Translation for Security Surveillance(Faculty of Arts, University of Benin., 2021) Odoje, C. O.; Nweya, G. O.Global insecurity is one of the main challenges facing the world in recent times and Nigeria is among the most affected with thousands of deaths and loss of property worth billions of naira. Studies show that countries are achieving better security through the use intelligence reports where languages play significant roles than through the use of arms and ammunitions. However, previous studies on Nigerian languages have concentrated on language description and language documentation with little attention paid to language use for security surveillance and intelligence gathering This paper, therefore, evaluates Google translate, from the perspective of the Igbo and Yoruba languages. with a view to determining its level of efficiency in translating for the purpose of security surveillance or intelligence gathering, identifying its potentials for achieving better security and the challenges facing its use. The study reveals that Google translate could be used for security surveillance if properly adapted despite the shortcomings of its output. Factors such as multilingualism, inadequate funding, insufficient language resources and poor infrastructural development are some of the challenges facing the proposal. The implication is that the Nigerian government at all levels can harness the potentials of this tool towards overcoming its security challenges if it invests more in security especially at the State and Local Government levels.