Dual Adversarial Co-Learning for Multi-Domain Text Classification
This work addresses the problem of improving generalization in multi-domain text classification for applications like sentiment analysis, though it appears incremental as it builds on existing adversarial and co-learning methods.
The paper tackles multi-domain text classification by proposing a dual adversarial co-learning approach that learns shared-private networks and uses dual adversarial regularizations to align features across domains and between labeled and unlabeled data, achieving state-of-the-art performance on sentiment classification datasets.
In this paper we propose a novel dual adversarial co-learning approach for multi-domain text classification (MDTC). The approach learns shared-private networks for feature extraction and deploys dual adversarial regularizations to align features across different domains and between labeled and unlabeled data simultaneously under a discrepancy based co-learning framework, aiming to improve the classifiers' generalization capacity with the learned features. We conduct experiments on multi-domain sentiment classification datasets. The results show the proposed approach achieves the state-of-the-art MDTC performance.