Maneno Yetu: Dynamic Corpus Construction and Pretraining for Swahili NLP.

@inproceedings{zawuya-2025-maneno, author = {Chaddy Anthony Zawuya and Alfred Malengo Kondoro and Diana Rwegasira and Juma H. Lungo}, editor = {Meeyoung Cha and Carl Yang and Senjuti Basu Roy and Chanyoung Park and Zhenhui Jessie Li and Noseong Park and Carl Yang and Senjuti Basu Roy and Zhenhui Jessie Li and Jaap Kamps and Kijung Shin and Bryan Hooi and Lifang He}, title = {{Maneno Yetu: Dynamic Corpus Construction and Pretraining for Swahili NLP}}, booktitle = {{Proceedings of the 34th ACM International Conference on Information and Knowledge Management, CIKM 2025, Seoul, Republic of Korea, November 10-14, 2025}}, pages = {6564--6569}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3746252.3761628}, doi = {https://doi.org/10.1145/3746252.3761628} }