LiBERTa: Advancing Ukrainian Language Modeling through Pre-training from Scratch

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AHX9D2IK8" target="_blank" >RIV/00216208:11320/25:HX9D2IK8 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85195202322&partnerID=40&md5=865f154a2dba93fd65ec5a9b55e88114" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85195202322&partnerID=40&md5=865f154a2dba93fd65ec5a9b55e88114</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

LiBERTa: Advancing Ukrainian Language Modeling through Pre-training from Scratch

Popis výsledku v původním jazyce

Recent advancements in Natural Language Processing (NLP) have spurred remarkable progress in language modeling, predominantly benefiting English. While Ukrainian NLP has long grappled with significant challenges due to limited data and computational resources, recent years have seen a shift with the emergence of new corpora, marking a pivotal moment in addressing these obstacles. This paper introduces LiBERTa Large, the inaugural BERT Large model pre-trained entirely from scratch only on Ukrainian texts. Leveraging extensive multilingual text corpora, including a substantial Ukrainian subset, LiBERTa Large establishes a foundational resource for Ukrainian NLU tasks. Our model outperforms existing multilingual and monolingual models pre-trained from scratch for Ukrainian, demonstrating competitive performance against those relying on cross-lingual transfer from English. This achievement underscores our ability to achieve superior performance through pre-training from scratch with additional enhancements, obviating the need to rely on decisions made for English models to efficiently transfer weights. We establish LiBERTa Large as a robust baseline, paving the way for future advancements in Ukrainian language modeling. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

Název v anglickém jazyce

LiBERTa: Advancing Ukrainian Language Modeling through Pre-training from Scratch

Popis výsledku anglicky

Recent advancements in Natural Language Processing (NLP) have spurred remarkable progress in language modeling, predominantly benefiting English. While Ukrainian NLP has long grappled with significant challenges due to limited data and computational resources, recent years have seen a shift with the emergence of new corpora, marking a pivotal moment in addressing these obstacles. This paper introduces LiBERTa Large, the inaugural BERT Large model pre-trained entirely from scratch only on Ukrainian texts. Leveraging extensive multilingual text corpora, including a substantial Ukrainian subset, LiBERTa Large establishes a foundational resource for Ukrainian NLU tasks. Our model outperforms existing multilingual and monolingual models pre-trained from scratch for Ukrainian, demonstrating competitive performance against those relying on cross-lingual transfer from English. This achievement underscores our ability to achieve superior performance through pre-training from scratch with additional enhancements, obviating the need to rely on decisions made for English models to efficiently transfer weights. We establish LiBERTa Large as a robust baseline, paving the way for future advancements in Ukrainian language modeling. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

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

Ukrainian Nat. Lang. Process. Workshop, UNLP LREC-COLING - Workshop Proc.

ISBN

978-249381443-2

ISSN

—

e-ISSN

—

Počet stran výsledku

9

Strana od-do

120-128

Název nakladatele

European Language Resources Association (ELRA)

Místo vydání

—

Místo konání akce

Torino, Italia

Datum konání akce

1. 1. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—