Transferring BERT Capabilities from High-Resource to Low-Resource Languages Using Vocabulary Matching

TL;DR

This paper introduces a vocabulary matching method to transfer BERT capabilities from high-resource to low-resource languages, improving language understanding with minimal data, demonstrated on Silesian and Kashubian.

Contribution

The paper proposes a novel vocabulary matching technique to adapt BERT for low-resource languages, enabling effective transfer from high-resource models.

Findings

Improved BERT performance on low-resource languages

Effective transfer with minimal training data

Potential to democratize language understanding models

Abstract

Pre-trained language models have revolutionized the natural language understanding landscape, most notably BERT (Bidirectional Encoder Representations from Transformers). However, a significant challenge remains for low-resource languages, where limited data hinders the effective training of such models. This work presents a novel approach to bridge this gap by transferring BERT capabilities from high-resource to low-resource languages using vocabulary matching. We conduct experiments on the Silesian and Kashubian languages and demonstrate the effectiveness of our approach to improve the performance of BERT models even when the target language has minimal training data. Our results highlight the potential of the proposed technique to effectively train BERT models for low-resource languages, thus democratizing access to advanced language understanding models.