David Ifeoluwa Adelani
About
Appointed Canada CIFAR AI Chair – 2024
David Ifeoluwa Adelani is a Canada CIFAR AI Chair at Mila and an assistant professor in the School of Computer Science at McGill University.
Adelani’s area of research is natural language processing. His primary research objective is to develop machine learning models for under-resourced languages (e.g. African languages, Latin-American languages, and Indigenous languages) by leveraging text, speech, and other multi-modal resources. He hopes to improve access to information and enhance human-machine communication for these under-resourced languages.
Some of Adelani’s current projects are focused on adaptation of large language models to under-resourced languages, scaling multilingual evaluation to several languages, building machine translation evaluation metrics for under-resourced languages, and developing speech technologies (e.g. automatic speech recognition and text-to-speech) for under-resourced languages.
Awards
- Area Chair Award, IJCNLP-AACL (2023)
- Grand Challenge Best Paper Award, COLING (2022)
- Best Poster Presentation Award, The Web Conference (2019)
Relevant Publications
- Chen Y., Marchisio K., Raileanu R., Adelani D., Stenetorp P., Riedel S., & Artetxe M. (2023). Improving Language Plasticity via Pretraining with Active Forgetting. NeurIPS.
- Oladipo A., Adeyemi M., Ahia O., Owodunni A., Ogundepo O., Adelani D.I., & Lin J. (2023). Better Quality Pre-training Data and T5 Models for African Languages. EMNLP, pp. 158–168.
- Alabi J., Adelani D.I, Mosbach M., & Klakow D. (2022) “Adapting pre-trained language models to African languages via multilingual adaptive fine-tuning.” COLING, pp. 4336–4349.
- Meyer J., Adelani D.I., Casanova E., Öktem A., Whitenack D., et al. (2022). “BibleTTS: a large, high-fidelity, multilingual, and uniquely African speech corpus”. Interspeech, pp. 2383--2387.
- Adelani D.I., Abbott J., Neubig G., D’souza D., Kreutzer J., Lignos C., et al. (2021). “MasakhaNER: Named entity recognition for African languages.” Transactions of the Association for Computational Linguistics; 9, pp. 1116–1131.