NusaBERT: Teaching IndoBERT to be Multilingual and Multicultural

TL;DR

NusaBERT is a multilingual and multicultural Indonesian language model that expands vocabulary and leverages diverse regional languages, achieving state-of-the-art results in Indonesian language understanding tasks.

Contribution

It introduces NusaBERT, a novel multilingual Indonesian language model that incorporates regional languages and dialects for improved performance.

Findings

Achieves state-of-the-art performance on Indonesian language benchmarks.

Effectively handles code-switching and low-resource regional languages.

Demonstrates the importance of diverse multilingual training data.

Abstract

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.