A Label Proportions Estimation Technique for Adversarial Domain Adaptation in Text Classification

TL;DR

This paper introduces DAN-LPE, a novel framework for unsupervised text classification domain adaptation that estimates label proportions to handle label shift, improving classification accuracy across different domains.

Contribution

The paper proposes a new domain adversarial network with label proportions estimation (DAN-LPE) to address label shift in unsupervised domain adaptation for text classification.

Findings

DAN-LPE accurately estimates target label distributions.

DAN-LPE reduces label shift and improves classification performance.

Experimental results outperform existing domain adaptation methods.

Abstract

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 used widely recently and have achieved promising 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 most real-world scenarios. Sometimes the label shift can be 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-LPE simultaneously trains a domain adversarial net and processes label proportions estimation by the confusion of the source domain and the predictions of the target domain. Experiments show the DAN-LPE achieves a good estimate of the target label distributions and reduces the label shift to improve the classification performance.