Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

NusaBERT: Teaching IndoBERT to be Multilingual and Multicultural

Domaine:

natural language processing

Type de record:

papermodel
Créateur:
WonSetLimJoy
Hôte:avatar
Indonesia's linguistic landscape is remarkably diverse, encompassing over 700 languages and dialects, making it one of the world's most linguistically rich nations. This diversity, coupled with the widespread practice of code-switching and the presence of low-resource regional languages, presents unique challenges for modern pre-trained language models. In response to these challenges, we developed NusaBERT, building upon IndoBERT by incorporating vocabulary expansion and leveraging a diverse multilingual corpus that includes regional languages and dialects. Through rigorous evaluation across a range of benchmarks, NusaBERT demonstrates state-of-the-art performance in tasks involving multiple languages of Indonesia, paving the way for future natural language understanding research for under-represented languages.

Visit

arxiv.org

Tasks

language modeling

Tags

Computation and Language

Similaires

Individualisation in the Multicultural Teaching-Learning SituationPOLAR: A Benchmark for Multilingual, Multicultural, and Multi-Event Online PolarizationMacaron: Controlled, Human-Written Benchmark for Multilingual and Multicultural Reasoning via Template-FillingTeaching Social Studies from multicultural perspective: a practical approach to re-fashion African Studies for transformationTeaching LLMs to Abstain across Languages via Multilingual FeedbackMacaron: A Controlled, Human-Written Benchmark for Multilingual and Multicultural Reasoning via Template-Filling

Individualisation in the Multicultural Teaching-Learning Situation

This article aims to indicate that an individualised approach is imperative for the successful teach

POLAR: A Benchmark for Multilingual, Multicultural, and Multi-Event Online Polarization

Online polarization poses a growing challenge for democratic discourse, yet most computational socia

Macaron: Controlled, Human-Written Benchmark for Multilingual and Multicultural Reasoning via Template-Filling

Multilingual benchmarks rarely test reasoning over culturally grounded premises: translated datasets

Teaching Social Studies from multicultural perspective: a practical approach to re-fashion African Studies for transformation

Currently, global education and global citizenship for social transformation addresses the issues of

Teaching LLMs to Abstain across Languages via Multilingual Feedback

Multilingual LLMs often have knowledge disparities across languages, with larger gaps in under-resou

Macaron: A Controlled, Human-Written Benchmark for Multilingual and Multicultural Reasoning via Template-Filling

Evaluating whether large language models (LLMs) genuinely understand the world from a non-English pe