@inproceedings{0c572f752661491dbc10145bca8e7246,
title = "D{\o}{\~n}{\textquoteright}t T{\`o}ů{\v c}ḥ M{\'y} D{\"i}{\c a}{\c c}ŗıtīcs",
abstract = "The common practice of preprocessing text before feeding it into NLP models introduces many decision points which have unintended consequences on model performance. In this opinion piece, we focus on the handling of diacritics in texts originating in many languages and scripts. We demonstrate, through several case studies, the adverse effects of inconsistent encoding of diacritized characters and of removing diacritics altogether. We call on the community to adopt simple but necessary steps across all models and toolkits in order to improve handling of diacritized text and, by extension, increase equity in multilingual NLP.",
author = "Kyle Gorman and Yuval Pinter",
note = "Publisher Copyright: {\textcopyright} 2025 Association for Computational Linguistics; 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2025 ; Conference date: 29-04-2025 Through 04-05-2025",
year = "2025",
month = jan,
day = "1",
doi = "10.18653/v1/2025.naacl-short.25",
language = "English",
series = "Proceedings of the 2025 Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies: Long Papers, NAACL-HLT 2025",
publisher = "Association for Computational Linguistics (ACL)",
pages = "285--291",
editor = "Luis Chiruzzo and Alan Ritter and Lu Wang",
booktitle = "Short Papers",
address = "United States",
}