Feature Adaptation of Pre-Trained Language Models across Languages and Domains with Robust Self-Training

29877

Knowledge Triples

Source Entity	Relationship	Target Entity
Class Aware Feature Self Distillation Method	evaluatedIn	Amazon Review Datasets Material
Pre-trained Language Models Method	usedIn	Unsupervised Domain Adaptation Method
Self Training Method	improves	Class Aware Feature Self Distillation Method
Unsupervised Domain Adaptation Method	uses	Self Training Method