UniBridge: A Unified Approach to Cross-Lingual Transfer Learning for Low-Resource Languages

TL;DR

UniBridge introduces a unified method for cross-lingual transfer learning that optimizes embeddings and vocabulary size, significantly enhancing performance in low-resource languages.

Contribution

It presents novel techniques for embedding initialization and vocabulary optimization, improving cross-lingual transfer effectiveness in low-resource settings.

Findings

Improved F1-Score across multiple languages

Effective embedding initialization leveraging lexical and semantic alignment

Systematic search for optimal vocabulary size

Abstract

In this paper, we introduce UniBridge (Cross-Lingual Transfer Learning with Optimized Embeddings and Vocabulary), a comprehensive approach developed to improve the effectiveness of Cross-Lingual Transfer Learning, particularly in languages with limited resources. Our approach tackles two essential elements of a language model: the initialization of embeddings and the optimal vocabulary size. Specifically, we propose a novel embedding initialization method that leverages both lexical and semantic alignment for a language. In addition, we present a method for systematically searching for the optimal vocabulary size, ensuring a balance between model complexity and linguistic coverage. Our experiments across multilingual datasets show that our approach greatly improves the F1-Score in several languages. UniBridge is a robust and adaptable solution for cross-lingual systems in various languages, highlighting the significance of initializing embeddings and choosing the right vocabulary size in cross-lingual environments.