@inproceedings{faisal-etal-2024-dialectbench,
title = "{DIALECTBENCH}: An {NLP} Benchmark for Dialects, Varieties, and Closely-Related Languages",
author = "Faisal, Fahim and
Ahia, Orevaoghene and
Srivastava, Aarohi and
Ahuja, Kabir and
Chiang, David and
Tsvetkov, Yulia and
Anastasopoulos, Antonios",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.luhme-long.777/",
doi = "10.18653/v1/2024.acl-long.777",
pages = "14412--14454",
abstract = "Language technologies should be judged on their usefulness in real-world use cases. An often overlooked aspect in natural language processing (NLP) research and evaluation is language variation in the form of non-standard dialects or language varieties (hereafter, varieties). Most NLP benchmarks are limited to standard language varieties. To fill this gap, we propose DIALECTBENCH, the first-ever large-scale benchmark for NLP on varieties, which aggregates an extensive set of task-varied varieties datasets (10 text-level tasks covering 281 varieties). This allows for a comprehensive evaluation of NLP system performance on different varieties. We provide substantial proof of performance disparities between standard and non-standard language varieties, and we also identify language clusters with larger performance divergence across tasks.We believe DIALECTBENCH provides a comprehensive view of the current state of NLP for varieties and one step towards advancing it further."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="faisal-etal-2024-dialectbench">
<titleInfo>
<title>DIALECTBENCH: An NLP Benchmark for Dialects, Varieties, and Closely-Related Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fahim</namePart>
<namePart type="family">Faisal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orevaoghene</namePart>
<namePart type="family">Ahia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aarohi</namePart>
<namePart type="family">Srivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kabir</namePart>
<namePart type="family">Ahuja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulia</namePart>
<namePart type="family">Tsvetkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Language technologies should be judged on their usefulness in real-world use cases. An often overlooked aspect in natural language processing (NLP) research and evaluation is language variation in the form of non-standard dialects or language varieties (hereafter, varieties). Most NLP benchmarks are limited to standard language varieties. To fill this gap, we propose DIALECTBENCH, the first-ever large-scale benchmark for NLP on varieties, which aggregates an extensive set of task-varied varieties datasets (10 text-level tasks covering 281 varieties). This allows for a comprehensive evaluation of NLP system performance on different varieties. We provide substantial proof of performance disparities between standard and non-standard language varieties, and we also identify language clusters with larger performance divergence across tasks.We believe DIALECTBENCH provides a comprehensive view of the current state of NLP for varieties and one step towards advancing it further.</abstract>
<identifier type="citekey">faisal-etal-2024-dialectbench</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.777</identifier>
<location>
<url>https://aclanthology.org/2024.luhme-long.777/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>14412</start>
<end>14454</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DIALECTBENCH: An NLP Benchmark for Dialects, Varieties, and Closely-Related Languages
%A Faisal, Fahim
%A Ahia, Orevaoghene
%A Srivastava, Aarohi
%A Ahuja, Kabir
%A Chiang, David
%A Tsvetkov, Yulia
%A Anastasopoulos, Antonios
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F faisal-etal-2024-dialectbench
%X Language technologies should be judged on their usefulness in real-world use cases. An often overlooked aspect in natural language processing (NLP) research and evaluation is language variation in the form of non-standard dialects or language varieties (hereafter, varieties). Most NLP benchmarks are limited to standard language varieties. To fill this gap, we propose DIALECTBENCH, the first-ever large-scale benchmark for NLP on varieties, which aggregates an extensive set of task-varied varieties datasets (10 text-level tasks covering 281 varieties). This allows for a comprehensive evaluation of NLP system performance on different varieties. We provide substantial proof of performance disparities between standard and non-standard language varieties, and we also identify language clusters with larger performance divergence across tasks.We believe DIALECTBENCH provides a comprehensive view of the current state of NLP for varieties and one step towards advancing it further.
%R 10.18653/v1/2024.acl-long.777
%U https://aclanthology.org/2024.luhme-long.777/
%U https://doi.org/10.18653/v1/2024.acl-long.777
%P 14412-14454
Markdown (Informal)
[DIALECTBENCH: An NLP Benchmark for Dialects, Varieties, and Closely-Related Languages](https://aclanthology.org/2024.luhme-long.777/) (Faisal et al., ACL 2024)
ACL
- Fahim Faisal, Orevaoghene Ahia, Aarohi Srivastava, Kabir Ahuja, David Chiang, Yulia Tsvetkov, and Antonios Anastasopoulos. 2024. DIALECTBENCH: An NLP Benchmark for Dialects, Varieties, and Closely-Related Languages. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 14412–14454, Bangkok, Thailand. Association for Computational Linguistics.