Many text classification tasks are domain-dependent, and various domain adaptation approaches have been proposed to predict unlabeled data in a new domain. Domain-adversarial neural networks(DANN) and their variants have been actively used recently and have achieved state-of-the-art results for this problem. However, most of these approaches assume that the label proportions of the source and target domains are similar, which rarely holds in real-world scenarios. Sometimes the label shift is very large and the DANN fails to learn domain-invariant features. In this study, we focus on unsupervised domain adaptation of text classification with label shift and introduce a domain adversarial network with label proportions estimation (DAN-LPE) framework. The DAN-LPEsimultaneously trains a domain adversarial net and processes label proportions estimation by the distributions of the predictions. Experiments show the DAN-LPE achieves a good estimate of the target label distributions and reduces the label shift to improve the classification performance.
View on arXiv