NusaBERT: Teaching IndoBERT to be Multilingual and Multicultural
This addresses natural language understanding for Indonesia's under-represented languages, though it appears incremental as it builds directly on IndoBERT.
The paper tackles the challenge of Indonesia's diverse linguistic landscape by developing NusaBERT, which builds on IndoBERT with vocabulary expansion and a multilingual corpus, achieving state-of-the-art performance on benchmarks for multiple Indonesian languages.
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.