Multiple-Source Domain Adaptation via Coordinated Domain Encoders and Paired Classifiers

We present a novel multiple-source unsupervised model for text classification under domain shift. Our exploits the update rates in document representations to dynamically integrate encoders. It also employs probabilistic heuristic infer error rate target order pair source classifiers. data transformation cost and classifier accuracy feature space. have used real world scenarios of Domain Adaptation evaluate efficacy our algorithm. pretrained multi-layer transformers as encoder experiments demonstrate whether improvement achieved by adaptation models can be delivered out-of-the-box language pretraining. The testify that is top performing approach this setting.