DIALECTBENCH: A NLP Benchmark for Dialects, Varieties, and Closely-Related Languages

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Faisal, Fahim, Ahia, Orevaoghene, Srivastava, Aarohi, Ahuja, Kabir, Chiang, David, Tsvetkov, Yulia, Anastasopoulos, Antonios
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913420181241856
author Faisal, Fahim
Ahia, Orevaoghene
Srivastava, Aarohi
Ahuja, Kabir
Chiang, David
Tsvetkov, Yulia
Anastasopoulos, Antonios
author_facet Faisal, Fahim
Ahia, Orevaoghene
Srivastava, Aarohi
Ahuja, Kabir
Chiang, David
Tsvetkov, Yulia
Anastasopoulos, Antonios
contents 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 variety datasets (10 text-level tasks covering 281 varieties). This allows for a comprehensive evaluation of NLP system performance on different language varieties. We provide substantial evidence of performance disparities between standard and non-standard language varieties, and we also identify language clusters with large performance divergence across tasks. We believe DIALECTBENCH provides a comprehensive view of the current state of NLP for language varieties and one step towards advancing it further. Code/data: https://github.com/ffaisal93/DialectBench
format Preprint
id arxiv_https___arxiv_org_abs_2403_11009
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DIALECTBENCH: A NLP Benchmark for Dialects, Varieties, and Closely-Related Languages
Faisal, Fahim
Ahia, Orevaoghene
Srivastava, Aarohi
Ahuja, Kabir
Chiang, David
Tsvetkov, Yulia
Anastasopoulos, Antonios
Computation and Language
Artificial Intelligence
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 variety datasets (10 text-level tasks covering 281 varieties). This allows for a comprehensive evaluation of NLP system performance on different language varieties. We provide substantial evidence of performance disparities between standard and non-standard language varieties, and we also identify language clusters with large performance divergence across tasks. We believe DIALECTBENCH provides a comprehensive view of the current state of NLP for language varieties and one step towards advancing it further. Code/data: https://github.com/ffaisal93/DialectBench
title DIALECTBENCH: A NLP Benchmark for Dialects, Varieties, and Closely-Related Languages
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2403.11009