paper

What makes multilingual BERT multilingual?

arXiv:2010.10938

Abstract

Recently, multilingual BERT works remarkably well on cross-lingual transfer tasks, superior to static non-contextualized word embeddings. In this work, we provide an in-depth experimental study to supplement the existing literature of cross-lingual ability. We compare the cross-lingual ability of non-contextualized and contextualized representation model with the same data. We found that datasize and context window size are crucial factors to the transferability.

arXiv admin note: substantial text overlap with arXiv:2004.09205

References in corpus (5)

Cited by in corpus (1)