SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3A5HPDDYT4" target="_blank" >RIV/00216208:11320/25:5HPDDYT4 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85189938251&partnerID=40&md5=db61cf1c40ab16c24c8d22ceaaaf9e1e" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85189938251&partnerID=40&md5=db61cf1c40ab16c24c8d22ceaaaf9e1e</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects

Popis výsledku v původním jazyce

Despite the progress in building multilingual language models, evaluation is often limited to a few languages with available datasets which excludes a large number of low-resource languages. In this paper, we create SIB-200-a large-scale open-sourced benchmark dataset for topic classification in 205 languages and dialects to address the lack of evaluation dataset for Natural Language Understanding (NLU). For many of the languages covered in SIB-200, this is the first publicly available evaluation dataset for NLU. The dataset is based on Flores-200 machine translation corpus. We annotated the English portion of the dataset and extended the sentence-level annotation to the remaining 204 languages covered in the corpus. Despite the simplicity of this task, our evaluation in full-supervised setting, cross-lingual transfer setting and prompting of large language model setting show that there is still a large gap between the performance of high-resource and low-resource languages when multilingual evaluation is scaled to numerous world languages. We found that languages unseen during the pretraining of multilingual language models, languages from under-represented families (like Nilotic and Altantic-Congo), and languages from the regions of Africa, Americas, Oceania and South East Asia, often have the lowest performance on our topic classification dataset. We hope our dataset encourage a more inclusive evaluation of multilingual language models on a more diverse set of languages. © 2024 Association for Computational Linguistics.

Název v anglickém jazyce

SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects

Popis výsledku anglicky

Despite the progress in building multilingual language models, evaluation is often limited to a few languages with available datasets which excludes a large number of low-resource languages. In this paper, we create SIB-200-a large-scale open-sourced benchmark dataset for topic classification in 205 languages and dialects to address the lack of evaluation dataset for Natural Language Understanding (NLU). For many of the languages covered in SIB-200, this is the first publicly available evaluation dataset for NLU. The dataset is based on Flores-200 machine translation corpus. We annotated the English portion of the dataset and extended the sentence-level annotation to the remaining 204 languages covered in the corpus. Despite the simplicity of this task, our evaluation in full-supervised setting, cross-lingual transfer setting and prompting of large language model setting show that there is still a large gap between the performance of high-resource and low-resource languages when multilingual evaluation is scaled to numerous world languages. We found that languages unseen during the pretraining of multilingual language models, languages from under-represented families (like Nilotic and Altantic-Congo), and languages from the regions of Africa, Americas, Oceania and South East Asia, often have the lowest performance on our topic classification dataset. We hope our dataset encourage a more inclusive evaluation of multilingual language models on a more diverse set of languages. © 2024 Association for Computational Linguistics.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

EACL - Conf. European Chapter Assoc. Comput. Linguist., Proc. Conf.

ISBN

979-889176088-2

ISSN

—

e-ISSN

—

Počet stran výsledku

20

Strana od-do

226-245

Název nakladatele

Association for Computational Linguistics (ACL)

Místo vydání

—

Místo konání akce

St. Julian's

Datum konání akce

1. 1. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—