We propose a practical scheme to train a single multilingual sequence
labeling model that yields state of the art results and is small and fast
enough to run on a single CPU. Starting from a public multilingual BERT
checkpoint, our final model is 6x smaller and 27x faster, and has higher
accuracy than a state-of-the-art multilingual baseline. We show that our model
especially outperforms on low-resource languages, and works on codemixed input
text without being explicitly trained on codemixed examples. We showcase the
effectiveness of our method by reporting on part-of-speech tagging and
morphological prediction on 70 treebanks and 48 languages.

我们提出了一种实用的方案来训练一个单一的多语言序列标注模型，这个模型在单个 CPU 上运行，能够给出最先进的结果，足够小和快速。从一个公共的多语言 BERT 检查点开始，我们的最终模型比最先进的多语言基线模型更加准确，并且速度更快，6 倍更小。我们证明了我们的模型特别是在低资源语言上表现出色，并且可以在混合输入文本上工作，而不需要对混合示例进行明确的训练。我们通过 70 棵树库和 48 种语言的词汇标注和形态预测来展示我们方法的有效性。