This repository contains the code and datasets from Bloom, Let's Read Asia, and Department of Education (DepEd) websites used for developing the first ML-based baseline for readability assessment in the Cebuano language described in the paper A Baseline Readability Model for Cebuano.
Paper Link: https://arxiv.org/abs/2203.17225
All reading materials collected for the study are free-to-download from their original websites and licensed with CC BY 4.0 which means they are also free to distribute in any form given proper citation.
Please also add the following citation to your paper/presentation if you use the resources found in this repository:
Reyes, L. L. A., & Ibañez, M. A., & Sapinit, R., & Hussien, M., Imperial, J. M. (2022). A Baseline Readability Model for Cebuano. arXiv preprint arXiv:2203.17225.
Please send an email before submitting this repository to any data cataloging, data aggregation, and benchmarking projects/initiatives. The proponents of the paper of this dataset would like to be acknowledged appropriately or involved in co-authorship.
If you need any help reproducing the results, please don't hesitate to contact me through
Joseph Marvin Imperial
[email protected]
www.josephimperial.com