{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/yad-leveraging-t5-for-improved-automatic","title":"YAD: Leveraging T5 for Improved Automatic Diacritization of Yorùbá Text","arxiv_id":"2412.20218","date":"2024-12-28","proceeding":null,"authors":["Akindele Michael Olawole","Jesujoba O. Alabi","Aderonke Busayo Sakpere","David I. Adelani"],"abstract":"In this work, we present Yor\\`ub\\'a automatic diacritization (YAD) benchmark dataset for evaluating Yor\\`ub\\'a diacritization systems. In addition, we pre-train text-to-text transformer, T5 model for Yor\\`ub\\'a and showed that this model outperform several multilingually trained T5 models. Lastly, we showed that more data and larger models are better at diacritization for Yor\\`ub\\'a","url_abs":"https://arxiv.org/abs/2412.20218v1","url_pdf":"https://arxiv.org/pdf/2412.20218v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"yad-leveraging-t5-for-improved-automatic","repo_url":"https://github.com/ajesujoba/YAD","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"adafactor","method_name":"Adafactor"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"glu","method_name":"Gated Linear Unit"},{"method_slug":"inverse-square-root-schedule","method_name":"Inverse Square Root Schedule"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sentencepiece","method_name":"SentencePiece"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"t5","method_name":"T5"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.20218","atlas_url":"https://app.syntology.ai/?focus=2412.20218","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}