Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potential for zero-shot cross-lingual transfer. However, these multilingual encoders do not precisely align words and phrases across languages. Especially, learning alignments in the multilingual embedding space usually requires sentence-level or word-level parallel corpora, which are expensive to be obtained for low-resource languages. An alternative is to make the multilingual encoders more robust; when fine-tuning the encoder using downstream task, we train the encoder to tolerate noise in the contextual embedding spaces such that even if the representations of different languages are not aligned well, the model can still achieve good performance on zero-shot cross-lingual transfer. In this work, we propose a learning strategy for training robust models by drawing connections between adversarial examples and the failure cases of zero-shot cross-lingual transfer. We adopt two widely used robust training methods, adversarial training and randomized smoothing, to train the desired robust model. The experimental results demonstrate that robust training improves zero-shot cross-lingual transfer on text classification tasks. The improvement is more significant in the generalized cross-lingual transfer setting, where the pair of input sentences belong to two different languages.
翻译:经过事先训练的多语言编码器,例如多语言的BERT和XLM-R,显示零点跨语言传输的巨大潜力。然而,这些多语言编码器并不精确地对各语文的文字和短语进行校准。特别是,多语言嵌入空间的学习调整通常需要判决一级或字级平行的组合体,对于低资源语言来说,这些组合体的费用很高。另一个办法是使多语言编码器更加强大;在使用下游任务对编码器进行微调时,我们训练编码器以容忍背景嵌入空间中的噪音,这样,即使不同语言的表达方式不协调,该模式仍然能够取得良好的成绩。在这项工作中,我们提出了一个培训强健模式的学习战略,在对抗性实例与零点跨语言传输失败案例之间建立联系。我们采用了两种广泛使用的强健的培训方法,即对抗性培训和随机化平滑动,以培训理想的稳健模式。实验结果显示,强健的培训改善了文本分类任务的零点跨语言传输。改进了两种语言的横向传输,在两种语言的版本中更为重要。