Evolution of Representations in Cross-Lingual Fine-tuning

Abstract

Cross-lingual fine-tuning has been widely used to bridge the gap between high-resource & low-resource languages. In this paper, we study the evolution of the learned representations during cross-lingual fine-tuning. We fine-tune a pre-trained multi-lingual BERT on a small Dutch corpus. A BERT model, pre-trained on Dutch exclusively, is used as a comparative baseline. We show that our transferred multi-lingual BERT learns a different representation subspace than the native model. Additionally, we explore the loss in multi-lingual capacity during fine-tuning.

Type
Publication
Evolution of Representations in Cross-Lingual Fine-tuning