@inproceedings{0239f19ff46646e69e4aee75e77310aa,
title = "Taxi1500: A Dataset for Multilingual Text Classification in 1500 Languages",
abstract = "While broad-coverage multilingual natural language processing tools have been developed, a significant portion of the world{\textquoteright}s over 7000 languages are still neglected. One reason is the lack of evaluation datasets that cover a diverse range of languages, particularly those that are low-resource or endangered. To address this gap, we present a large-scale text classification dataset encompassing 1504 languages many of which have otherwise limited or no annotated data. This dataset is constructed using parallel translations of the Bible. We develop relevant topics, annotate the English data through crowdsourcing and project these annotations onto other languages via aligned verses. We benchmark a range of existing multilingual models on this dataset. We make our dataset and code available to the public.1",
author = "Chunlan Ma and Ayyoob Imani and Haotian Ye and Renhao Pei and Ehsaneddin Asgari and Hinrich Sch{\"u}tze",
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",
doi = "10.18653/v1/2025.naacl-short.36",
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 = "414--439",
editor = "Luis Chiruzzo and Alan Ritter and Lu Wang",
booktitle = "Short Papers",
address = "United States",
}