The "massively-multilingual" training of multilingual models is known to limit their utility in any one language, and they perform particularly poorly on low-resource languages. However, there is evidence that low-resource languages can benefit from targeted multilinguality, where the model is trained on closely related languages. To test this approach more rigorously, we systematically study best practices for adapting a pre-trained model to a language family. Focusing on the Uralic family as a test case, we adapt XLM-R under various configurations to model 15 languages; we then evaluate the performance of each experimental setting on two downstream tasks and 11 evaluation languages. Our adapted models significantly outperform mono- and multilingual baselines. Furthermore, a regression analysis of hyperparameter effects reveals that adapted vocabulary size is relatively unimportant for low-resource languages, and that low-resource languages can be aggressively up-sampled during training at little detriment to performance in high-resource languages. These results introduce new best practices for performing language adaptation in a targeted setting.

对于低资源语言，通过针对性的多语言训练，依照乌拉尔语系为案例进行调整，通过实验证明适应性的词汇大小对于低资源语言的影响相对较小，低资源语言在训练阶段能够进行积极采样而对高资源语言的性能影响微乎其微，从而为特定语境中的语言适应性提供了新的最佳实践。

针对低资源语言家族的定向多语言适应