{"id":15258,"date":"2022-08-04T19:35:06","date_gmt":"2022-08-04T17:35:06","guid":{"rendered":"https:\/\/grain-africa.org\/?p=15258"},"modified":"2025-10-31T18:33:01","modified_gmt":"2025-10-31T17:33:01","slug":"ai-and-local-african-languages","status":"publish","type":"post","link":"https:\/\/grain-africa.org\/en\/ai-et-langues-africaines-locales\/","title":{"rendered":"AI AND LOCAL AFRICAN LANGUAGES"},"content":{"rendered":"
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

AI AND LOCAL AFRICAN LANGUAGES <\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n

<\/div>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t
\n\nNowadays, language as a social, economic and technological barrier is increasingly being discussed. In the African context, there has been a proliferation of initiatives aimed at making people\u2019s daily lives easier. In many countries, limited proficiency in official languages is a reality that has prompted researchers (scientists, sociologists, linguists, etc.) to develop tools to bridge the gap that exists in communication and in the use of modern technology (smartphones, computers, websites\/platforms, etc.). Researchers have also put forward other justifications, notably the preservation of languages as a marker of cultural identity and a vehicle for social integration (African Language Programme, 2021).English-speaking countries appear to be leading the way in the use of Artificial Intelligence (AI) technology in linguistic practice, where several major technological innovations have emerged. In 2021, the South African telecoms company Telkom and the start-up Enlabeler launched the Izwe.ai platform, which offers transcription and translation services in several local languages and is capable of interpreting South African accents. This AI-based innovation aims to have a significant impact on the education, health and business sectors in order to reduce inequalities. In Rwanda, software development engineer Remy Muhire was part of a team that created a new open-access speech dataset for the Kinyarwanda language, involving numerous volunteers recording themselves speaking the local language: Kinyarwanda. In Nigeria, ARIKPO and DICKSON (2018) developed a machine translator from English into the local Nigerian language Efik, based on Natural Language Processing (NLP), a branch of AI. More specifically, NLP relies on the programming-based implementation of words and themes to provide high-quality translation. In Nigeria, the translator developed by ARIKPO and DICKSON was preceded by a number of similar tools, albeit based on different methods. Awofolu and Malita (2002) developed an automatic translator from English to Yoruba and vice versa, using classical syntactic and semantic analysis algorithms. Folajimi and Omonayin (2012) developed a translation mechanism based on the Statistical Machine Translation (SMT) algorithm, which translates from English into Yoruba. Odejobi et al. (2006) and Afolabi et al. (2013) carried out research into the development of a Yoruba speech synthesis system using the concatenation method. Afolabi et al. (2013) point out that the value of applying AI methods to the Yoruba language lies in its significance in Nigeria and several other African countries, such as Benin and Togo. These translation technologies must be accessible and user-friendly. According to the same source, 70% of respondents acknowledged its ease of use.\n\n \n

\nAs well as addressing the challenge of ease of use, recent platforms are seeking to enable translation into multiple languages. This is precisely what the innovative Mashakane platform (Iroro et al., 2020) has achieved, offering translation into nearly thirty local African languages. Developed by around twenty researchers (scientists and computer scientists) of African origin, this platform appears to be the most advanced in terms of translation for addressing development issues in Africa.\n\n \n

\nMore recently, two students have taken an interest in finding ways to make the most of local languages. Dossou (2022) proposes an AI model to assist with translating Fon into French. His fellow student, Emezue (2022), has worked on translating Igbo into English. Their collaboration resulted in the creation of a translation model called Fon-French Neural Machine Translation (FFR), similar to Google Translate. This innovation helps to address the shortcomings of current translation engines for local African languages.\n

\nFurthermore, the existing literature on the use of AI to support African languages highlights the potential benefits for the lives of local communities. In the field of education, UNESCO promotes AI as an effective tool that could be harnessed to address the challenges and issues facing this sector. The use of local languages in schools would contribute to improved academic performance (Ouane and Glanz, 2010).\n

\nIn agriculture, AI trials carried out in Kenya clearly demonstrate the benefits of applying AI to support African languages (Brandusescu et al., 2017 and Assefa, 2018). Rural populations, many of whom are illiterate, will be able to make agricultural management systems more efficient and resilient, gain greater access to loans through improved financial inclusion, and establish adequate and sustainable infrastructure.\n

\nIn the healthcare sector, innovative solutions exist and should be rolled out more widely to facilitate access to healthcare. Brandusescu et al. (2017) and Smith and Neupane (2018) highlight the opportunities offered by AI to address the shortage of qualified healthcare staff. Having access to practical advice from healthcare experts in local languages via platforms or mobile apps represents a significant advance in medicine, particularly in rural areas where there is a severe lack of healthcare services and infrastructure.\n

\nIn the aforementioned areas, the application of AI is proving to be essential for overcoming the barriers arising from the use of official languages. These barriers can rightly be regarded as inequalities, as a sub-population is often excluded. This exclusion often affects women, who are increasingly being taken into account in future planning. The development of AI technologies incorporates this gender dimension, which could promote and accelerate women\u2019s entrepreneurship and leadership. Over the last five years, the results regarding the promotion of women in Sub-Saharan Africa have been encouraging: in 2017, 27% of entrepreneurs were women, representing the highest proportion of any region in the world (the Mastercard Index of Women Entrepreneurs, MIWE). By breaking down language barriers, AI therefore presents a real opportunity to be seized in the business world.\n

\nThe development of AI tools to support African languages faces numerous constraints. Several factors are worth highlighting, the most commonly discussed being the need to improve the legal and regulatory framework and the lack of initiatives to secure funding commensurate with the opportunities that AI can offer.\n

\nAt the continental level, Africa has few regional initiatives in the areas of development policy and AI regulation that reflect the enormous progress that needs to be made collectively (Gwagwa et al., 2020). The flagship initiative is the Convention on Cybersecurity and the Protection of Personal Data (African Union, 2014). At national level, only 17 of the 55 member states of the African Union (AU) have adopted comprehensive legislation on \u201cdata protection and privacy\u201d, according to the survey on African AI policies conducted by Global Information Society Watch in 2019. These regulatory frameworks need to be reviewed and updated to take account of developments in the field of AI (Gwagwa et al., 2020).\n

\nAccording to The Web Foundation\u2019s 2017 report, the lack of a comprehensive regulatory framework is holding back the sector\u2019s development to some extent. Businesses lack benchmarks and strategic guidance, and public policy is far from fulfilling its role as a catalyst. There is a clear need for coordinated action involving all stakeholders. Furthermore, the lack of evidence in the field of AI makes it difficult, if not virtually impossible, to draw conclusions based on data usage (Web Foundation, 2017).\n

\nApart from the fact that the legal framework is still in its infancy, the limited use of local African languages in a global economy dominated by foreign languages (English, French, Chinese, etc.) dampens interest in these languages. AI giants, driven by economic profitability, will not invest unless there are real prospects for return. This makes it even more difficult to apply AI to local African languages, which therefore remain dependent on local initiatives set up by the private or public sector \u2013 initiatives that are already financially constrained by socio-demographic challenges (poverty, unemployment, health, etc.). Thus, in Africa, shortcomings in funding and investment to establish STEM (science, technology, engineering and mathematics) and to put in place high-quality infrastructure drastically hinder the prospects for a strong and inclusive AI industry.\n\n

\n<\/div>\n
    \n \t\n\n \t
  1. Aanu Adeoye, CNN, \u00abGoogle has opened its first artificial intelligence lab in Africa, in Ghana\u00bb, 16 January 2019. Available at: <\/span>https:\/\/edition.cnn.com\/2019\/04\/14\/africa\/google-ai-center-accra-intl\/index.html<\/span><\/a><\/li>\n\n\n\n \n\n \t\n\n \t
  2. Afolabi Akinlolu Olarinde<\/span><\/a>, <\/span>\u00c9lie Omidiora<\/span><\/a> and <\/span>Oladiran Tayo Arulogun<\/span><\/a>, \u00abDevelopment of a Text-to-Speech System for the Yoruba Language\u00bb, 2013. Available at: <\/span>https:\/\/www.researchgate.net\/publication\/download<\/span><\/a><\/li>\n\n<\/li>\n\n \n\n \t\n\n \t
  3. Africanews, \u00abArtificial intelligence in the service of African languages\u00bb, 23 December 2021. Available at: <\/span>https:\/\/fr.africanews.com\/2021\/12\/23\/pour-une-intelligence-artificielle-au-service-des-langues-africaines\/\/<\/span><\/a><\/li>\n\n<\/li>\n\n \n\n \t\n\n \t
  4. AFRICAN NLP, \u00abMASAKHANE \u2013 MACHINE TRANSLATION FOR AFRICA\u00bb, 2020. Available at: <\/span>https:\/\/arxiv.org\/pdf\/2003.11529.pdf<\/span><\/a><\/li>\n\n<\/li>\n\n \n\n \t\n\n \t
  5. AfricaNLP workshop, \u00abMACHINE TRANSLATION FOR AFRICAN LANGUAGES: COMMUNITY CREATION OF DATASETS AND MODELS IN UGANDA\u00bb, 2022. Available at: <\/span>https:\/\/openreview.net\/pdf?id=BK-z5qzEU-9<\/span><\/a><\/li>\n\n<\/li>\n\n \n\n \t\n\n \t
  6. Association for Computational Linguistics, \u00abParticipatory Research for Low-resourced Machine Translation: A Case Study in African Languages\u00bb, 20 November 2020. Available at: <\/span>https:\/\/www.researchgate.net\/publication\/347235065_Participatory_Research_for_Low-<\/span><\/a><\/li>\n\n<\/li>\n\n \n\n \t\n\n \t
  7. Arthur Gwagwa, Erika Kraemer-Mbula1, Nagla Rizk, Isaac Rutenberg, J\u00e9r\u00e9my De Beer, \u00abArtificial Intelligence (AI) Deployments in Africa: Benefits, Challenges and Policy Dimensions\u00bb, 1 December 2020. Available at: <\/span>https:\/\/journals.co.za\/doi\/abs\/10.23962\/10539\/30361<\/span><\/a><\/li>\n\n<\/li>\n\n \n\n \t
  8. BBC News, \u00abArtificial intelligence in Africa: \u2018I taught a bot to read my mum\u2019s text messages\u201d\u00bb, (online), 6 May 2020. Available at: <\/span>https:\/\/www.bbc.com\/afrique\/region-52552206<\/span><\/a><\/li>\n\n<\/li>\n\n \n
  9. Conference: EACL 2009 Workshop on Language Technologies for African Languages, \u00abThe SAWA Corpus: a Parallel Corpus of English and Swahili\u00bb, 2009. Available at: <\/span>https:\/\/www.researchgate.net\/publication\/234819266_The_SAWA_corpus_a_parallel_corpus_English_-_Swahili<\/span><\/a><\/li>\n\n<\/li>\n\n \n\n \t\n\n \t
  10. Gilles-Maurice de Schryver, \u00abIntroduction to the special issue on African Language Technology\u00bb, September 2011. Available at: <\/span>https:\/\/www.researchgate.net\/link\/5a2d6dfe0f7e9b63e53d2bb6\/download<\/span><\/a><\/li>\n\n\n \n\n\n\n \t
  11. Guy De Pauw, Gilles-Maurice de Schryver, Laurette Pretorius and Lori Levin, \u00abIntroduction to the special issue on African Language Technology\u00bb, 2011. Available at: <\/span>https:\/\/www.researchgate.net\/the_special_issue_on_African_Language_Technology\/download<\/span><\/a><\/li>\n\n<\/li>\n\n \n\n \t\n\n \t
  12. Global Information Society Watch, \u00abArtificial Intelligence\u00bb, 2019. Available at: <\/span>https:\/\/www.researchgate.net\/_Artificial_intelligence<\/span><\/a><\/li>\n\n<\/li>\n\n \n\n \t
  13. \n\n \t
  14. Iwara I. Arikpo<\/span><\/a>, University of Calabar, \u00abDevelopment of an automated English-to-local-language translator using Natural Language Processing\u00bb, July 2028. Available at:<\/span>https:\/\/www.researchgate.net\/publication\/326722662_Development_of_an_automated_English-to-local language_translator_using_Natural_Language_Processing\/link\/5b609c96a6fdccf0b204ae0c\/download<\/span><\/a><\/li>\n\n<\/li>\n\n \n\n \t\n\n \t
  15. Jade Z. Abbott and Laura Martinus, \u00abBenchmarking Neural Machine Translation for Southern African Languages\u00bb. Available at: <\/span>http:\/\/www.winlp.org\/wp-content\/uploads\/2019\/final_papers\/174_Paper.pdf<\/span><\/a><\/li>\n\n<\/li>\n\n \n\n \t\n\n \t
  16. Journal of Literature, Languages and Linguistics, \u00abA Simple Data-Driven Yoruba Language Dictionary\u00bb, 2015. Available at: <\/span>https:\/\/core.ac.uk\/download\/pdf\/234693015.pdf<\/span><\/a><\/li>\n\n<\/li>\n\n \n\n \t\n\n \t
  17. Laura Martinus, Jason Webster, Joanne Moonsamy, Moses Shaba Jnr, Ridha Moosa, & Robert Fairon, \u00abNEURAL MACHINE TRANSLATION FOR SOUTH AFRICA\u2019S OFFICIAL LANGUAGES\u00bb, 2020. Available at: <\/span>https:\/\/arxiv.org\/pdf\/2005.06609.pdf<\/span><\/a><\/li>\n\n<\/li>\n\n \n\n \t\n\n \t
  18. Liu Kanglang and Muhammad Afzaal, \u00abArtificial Intelligence (AI) and Translation Teaching: A Critical Perspective on the Transformation of Education\u00bb, 2021. Available at: <\/span>http:\/\/krepublishers.com\/02-Journals\/IJES\/IJES-33-0-000-21-Web\/IJES-33-1-3-000-21-Abst-PDF\/IJES-33-1-3-064-21-1159-Kanglang-<\/span><\/a><\/li>\n\n<\/li>\n\n \n\n \t\n\n \t
  19. Louis-Nino Kansoun, Osiris, \u00abIzwe.ai, the AI platform launched by Telkom to overcome language barriers in South Africa\u00bb, (online), September 2022. Available at <\/span>http:\/\/www.osiris.sn\/Izwe-ai-la-plateforme-d-IA-lancee.html<\/span><\/a><\/li>\n\n<\/li>\n\n \n\n \t\n\n \t
  20. Ouane A. and Glanz C., \u00abWhy and how Africa should invest in African languages and multilingual education\u00bb, 2010. Available at: <\/span>https:\/\/files.eric.ed.gov\/fulltext\/ED540509.pdf<\/span><\/a><\/li>\n\n<\/li>\n\n \n\n \t\n\n \t
  21. Olufemi D. Ninan and Odetunji A. O.d\u00e9.jo.b\u00ed, \u00abTheoretical Issues in the Computational Modelling of Yor\u00f9b\u00e1 Narratives\u00bb. Available at: <\/span>https:\/\/drops.dagstuhl.de\/opus\/volltexte\/2013\/4142\/pdf\/p153-ninan.pdf<\/span><\/a><\/li>\n\n<\/li>\n\n \n\n \t\n\n \t
  22. Solomon Assefa, \u00abHello Tractor: a pilot digital wallet for agriculture based on AI and blockchain\u00bb, 11 December 2018. Available at: <\/span>https:\/\/www.ibm.com\/blogs\/research\/2018\/12\/hello-tractor\/<\/span><\/a><\/li>\n\n<\/li>\n\n \n\n \t\n\n \t
  23. Thot Cursus, \u00abTranslation into African languages: a promising field for the global language industry\u00bb, 1 December 2019. Available at: <\/span>https:\/\/cursus.edu\/fr\/21148\/la-traduction-en-langues-africaines-terrain-davenir-pour-lindustrie-linguistique-mondiale<\/span><\/a><\/li>\n\n<\/li>\n\n \n\n \t\n\n \t
  24. UNESCO\u2019s International Conference on Language Technologies for All (LT4All), \u00abAI4D \u2013 African Language Programme\u00bb, December 2019. Available at: <\/span>https:\/\/arxiv.org\/pdf\/2104.02516.pdf<\/span><\/a><\/li>\n\n<\/li>\n\n \n\n \t\n\n \t
  25. The Web Foundation, \u00abArtificial intelligence: Starting the policy dialogue in Africa\u00bb, 2017. Available at: <\/span>https:\/\/webfoundation.org\/docs\/2017\/12\/Artificial-Intelligence-starting-the-policy-dialogue-in-Africa.pdf<\/span><\/a><\/li>\n\n<\/li>\n\n \n\n \t
  26. Yetunde Folajimi and Omonayin, University of Ibadan, \u00abUsing Statistical Machine Translation (SMT) as a Language Translation Tool for Understanding the Yoruba Language\u00bb, February 2012. Available at: <\/span>https:\/\/www.researchgate.net\/for_Understanding_Yoruba_Language\/download<\/span><\/a><\/li>\n
    \n\u00a0Authors: Cheikh FAYE, Isac MINGOU and Ndierebi BA<\/i><\/span>\n\n \t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>\n\t\t
    \r\n
    Similar articles<\/div>\r\n
    \r\n\r\n
    \r\n
    \r\n \r\n\r\n \"STEM\r\n\r\n \r\n\r\n <\/a>\r\n <\/div>\r\n\r\n \r\n STEM AND EDUCATION: RESEARCH INTO GENDER-RELATED GAPS <\/a>\r\n\r\n

    \r\n Not so long ago, people lived and went about their daily lives in close-knit communities. Every shopkeeper knew their customers personally and could... <\/p>\r\n <\/div>\r\n

    \r\n
    \r\n \r\n\r\n \"\"\r\n\r\n <\/a>\r\n <\/div>\r\n\r\n \r\n AI and women\u2019s economic empowerment in agriculture <\/a>\r\n\r\n

    \r\n This Machine Learning Glossary aims to provide a brief introduction to the most important machine learning terms \u2013 both for commercial and... <\/p>\r\n <\/div>\r\n \r\n <\/div>\r\n\r\n