@inproceedings{ma-etal-2025-taxi1500,
title = "Taxi1500: A Dataset for Multilingual Text Classification in 1500 Languages",
author = "Ma, Chunlan and
Imani, Ayyoob and
Ye, Haotian and
Pei, Renhao and
Asgari, Ehsaneddin and
Schuetze, Hinrich",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-short.36/",
doi = "10.18653/v1/2025.naacl-short.36",
pages = "414--439",
ISBN = "979-8-89176-190-2",
abstract = "While broad-coverage multilingual natural language processing tools have been developed, a significant portion of the world{'}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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-etal-2025-taxi1500">
<titleInfo>
<title>Taxi1500: A Dataset for Multilingual Text Classification in 1500 Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chunlan</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayyoob</namePart>
<namePart type="family">Imani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haotian</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Renhao</namePart>
<namePart type="family">Pei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehsaneddin</namePart>
<namePart type="family">Asgari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hinrich</namePart>
<namePart type="family">Schuetze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-190-2</identifier>
</relatedItem>
<abstract>While broad-coverage multilingual natural language processing tools have been developed, a significant portion of the world’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.</abstract>
<identifier type="citekey">ma-etal-2025-taxi1500</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-short.36</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-short.36/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>414</start>
<end>439</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Taxi1500: A Dataset for Multilingual Text Classification in 1500 Languages
%A Ma, Chunlan
%A Imani, Ayyoob
%A Ye, Haotian
%A Pei, Renhao
%A Asgari, Ehsaneddin
%A Schuetze, Hinrich
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-190-2
%F ma-etal-2025-taxi1500
%X While broad-coverage multilingual natural language processing tools have been developed, a significant portion of the world’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.
%R 10.18653/v1/2025.naacl-short.36
%U https://aclanthology.org/2025.naacl-short.36/
%U https://doi.org/10.18653/v1/2025.naacl-short.36
%P 414-439
Markdown (Informal)
[Taxi1500: A Dataset for Multilingual Text Classification in 1500 Languages](https://aclanthology.org/2025.naacl-short.36/) (Ma et al., NAACL 2025)
ACL
- Chunlan Ma, Ayyoob Imani, Haotian Ye, Renhao Pei, Ehsaneddin Asgari, and Hinrich Schuetze. 2025. Taxi1500: A Dataset for Multilingual Text Classification in 1500 Languages. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers), pages 414–439, Albuquerque, New Mexico. Association for Computational Linguistics.