Machine Translation For African Languages: Community Creation Of Datasets And Models In Uganda

Simple item page
dc.contributor.authorAkera, Benjamin
dc.contributor.authorMukiibi, Jonathan
dc.contributor.authorNaggayi, Lydia Sanyu
dc.contributor.authorNsumba, Solomon
dc.contributor.authorMwebaze, Ernest
dc.contributor.authorQuinn, John
dc.date.accessioned2025-03-07T17:35:06Z
dc.date.available2025-03-07T17:35:06Z
dc.date.issued2022-03-30
dc.description.abstractReliable machine translation systems are only available for a small proportion of the world’s languages, the key limitation being a shortage of training and evaluation data. We provide a case study in the creation of such resources by NLP teams who are local to the communities in which these languages are spoken. A parallel text corpus, SALT, was created for five Ugandan languages (Luganda, Runyankole, Acholi, Lugbara and Ateso) and various methods were explored to train and evaluate translation models. The resulting models were found to be effective for practical translation applications, even for those languages with no previous NLP data available, achieving mean BLEU score of 26.2 for translations to English, and 19.9 from English. The SALT dataset and models described are publicly available at https://github.com/SunbirdAI/salt.
dc.identifier.citationAkera, B., Mukiibi, J., Naggayi, L. S., Babirye, C., Owomugisha, I., Nsumba, S., ... & Quinn, J. (2022). Machine translation for african languages: Community creation of datasets and models in uganda. In 3rd Workshop on African Natural Language Processing.
dc.identifier.urihttps://nru.uncst.go.ug/handle/123456789/10069
dc.language.isoen
dc.publisherICLR
dc.titleMachine Translation For African Languages: Community Creation Of Datasets And Models In Uganda
dc.typeWorking Paper
Files
Collections
Humanities and the Arts