The Trade-offs of Domain Adaptation for Neural Language Models

被引:0
|
作者
Grangier, David [1 ]
Iter, Dan [1 ,2 ]
机构
[1] Google, Mountain View, CA 94043 USA
[2] Stanford, Palo Alto, CA USA
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This work connects language model adaptation with concepts of machine learning theory. We consider a training setup with a large out-of-domain set and a small in-domain set. We derive how the benefit of training a model on either set depends on the size of the sets and the distance between their underlying distributions. We analyze how out-of-domain pre-training before in-domain fine-tuning achieves better generalization than either solution independently. Finally, we present how adaptation techniques based on data selection, such as importance sampling, intelligent data selection and influence functions, can be presented in a common framework which highlights their similarity and also their subtle differences.
引用
收藏
页码:3802 / 3813
页数:12
相关论文
共 50 条