Multi-Source Domain Adaptation for Text Classification via DistanceNet-Bandits

Understand

Domain adaptation performance of a learning algorithm on a target domain is a function of its source domain error and a divergence measure between the data distribution of these two domains.

• We present a study of various distance-based measures in the context of NLP tasks, that characterize the dissimilarity between domains based on sample estimates.
• We first conduct analysis experiments to show which of these distance measures can best differentiate samples from same versus different domains, and are correlated with empirical results.
• Next, we develop a DistanceNet model which uses these distance measures, or a mixture of these distance measures, as an additional loss function to be minimized jointly with the task's loss function, so as to achieve better unsupervised domain adaptation.