Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3AR8ZJDATM" target="_blank" >RIV/00216208:11320/23:R8ZJDATM - isvavai.cz</a>
Výsledek na webu
<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85162062605&partnerID=40&md5=920079626a35aa8b4aba8d7cb2b59403" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85162062605&partnerID=40&md5=920079626a35aa8b4aba8d7cb2b59403</a>
DOI - Digital Object Identifier
—
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages
Popis výsledku v původním jazyce
"The NLP community has mainly focused on scaling Large Language Models (LLMs) vertically, i.e., making them better for about 100 languages. We instead scale LLMs horizontally: we create, through continued pretraining, Glot500-m, an LLM that covers 511 predominantly low-resource languages. An important part of this effort is to collect and clean Glot500-c, a corpus that covers these 511 languages and allows us to train Glot500-m. We evaluate Glot500-m on five diverse tasks across these languages. We observe large improvements for both high-resource and low-resource languages compared to an XLM-R baseline. Our analysis shows that no single factor explains the quality of multilingual LLM representations. Rather, a combination of factors determines quality including corpus size, script, “help” from related languages and the total capacity of the model. Our work addresses an important goal of NLP research: we should not limit NLP to a small fraction of the world's languages and instead strive to support as many languages as possible to bring the benefits of NLP technology to all languages and cultures. Code, data and models are available at https://github.com/cisnlp/Glot500. © 2023 Association for Computational Linguistics."
Název v anglickém jazyce
Glot500: Scaling Multilingual Corpora and Language Models to 500 Languages
Popis výsledku anglicky
"The NLP community has mainly focused on scaling Large Language Models (LLMs) vertically, i.e., making them better for about 100 languages. We instead scale LLMs horizontally: we create, through continued pretraining, Glot500-m, an LLM that covers 511 predominantly low-resource languages. An important part of this effort is to collect and clean Glot500-c, a corpus that covers these 511 languages and allows us to train Glot500-m. We evaluate Glot500-m on five diverse tasks across these languages. We observe large improvements for both high-resource and low-resource languages compared to an XLM-R baseline. Our analysis shows that no single factor explains the quality of multilingual LLM representations. Rather, a combination of factors determines quality including corpus size, script, “help” from related languages and the total capacity of the model. Our work addresses an important goal of NLP research: we should not limit NLP to a small fraction of the world's languages and instead strive to support as many languages as possible to bring the benefits of NLP technology to all languages and cultures. Code, data and models are available at https://github.com/cisnlp/Glot500. © 2023 Association for Computational Linguistics."
Klasifikace
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)
Návaznosti výsledku
Projekt
—
Návaznosti
—
Ostatní
Rok uplatnění
2023
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název statě ve sborníku
"Proc. Annu. Meet. Assoc. Comput Linguist."
ISBN
978-195942972-2
ISSN
0736-587X
e-ISSN
—
Počet stran výsledku
36
Strana od-do
1082-1117
Název nakladatele
Association for Computational Linguistics (ACL)
Místo vydání
—
Místo konání akce
Melaka, Malaysia
Datum konání akce
1. 1. 2023
Typ akce podle státní příslušnosti
WRD - Celosvětová akce
Kód UT WoS článku
—