Large multilingual models, such as mBERT, have shown promise in crosslingual transfer. In this work, we employ pruning to quantify the robustness and interpret layer-wise importance of mBERT. On four GLUE tasks, the relative drops in accuracy due to pruning have almost identical results on mBERT and BERT suggesting that the reduced attention capacity of the multilingual models does not affect robustness to pruning. For the crosslingual task XNLI, we report higher drops in accuracy with pruning indicating lower robustness in crosslingual transfer. Also, the importance of the encoder layers sensitively depends on the language family and the pre-training corpus size. The top layers, which are relatively more influenced by fine-tuning, encode important information for languages similar to English (SVO) while the bottom layers, which are relatively less influenced by fine-tuning, are particularly important for agglutinative and low-resource languages.

通过对mBERT进行修剪，我们 quantifying 它的鲁棒性和逐层理解其重要性，结果表明缩减其注意力容量不会影响其鲁棒性。而在跨语言任务XNLI中，修剪会导致准确性下降，这表明跨语言转移的鲁棒性较低。此外，编码器层的重要性受语言族和预训练语料大小的影响。

多语言BERT中注意力头的可剪枝性