A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters
This work addresses the lack of standardization in few-shot crosslingual transfer experiments, which is a problem for researchers and practitioners evaluating and applying these methods.
This paper investigates few-shot crosslingual transfer, revealing that model performance is highly sensitive to the specific selection of few-shot examples. Through experiments on 40 sampled sets across six NLP tasks and up to 40 languages, the authors demonstrate that a simple full model finetuning approach can outperform several state-of-the-art few-shot methods.
Few-shot crosslingual transfer has been shown to outperform its zero-shot counterpart with pretrained encoders like multilingual BERT. Despite its growing popularity, little to no attention has been paid to standardizing and analyzing the design of few-shot experiments. In this work, we highlight a fundamental risk posed by this shortcoming, illustrating that the model exhibits a high degree of sensitivity to the selection of few shots. We conduct a large-scale experimental study on 40 sets of sampled few shots for six diverse NLP tasks across up to 40 languages. We provide an analysis of success and failure cases of few-shot transfer, which highlights the role of lexical features. Additionally, we show that a straightforward full model finetuning approach is quite effective for few-shot transfer, outperforming several state-of-the-art few-shot approaches. As a step towards standardizing few-shot crosslingual experimental designs, we make our sampled few shots publicly available.