A Robust Contrastive Alignment Method For Multi-Domain Text Classification
This addresses inefficiency in multi-domain text classification for scenarios with constantly emerging domains, though it appears incremental as it builds on existing private-shared paradigms.
The paper tackles the challenge of multi-domain text classification by proposing a robust contrastive alignment method that uses supervised contrastive learning to align features across domains, requiring only two universal feature extractors instead of complex multi-classifier frameworks. Experimental results show it performs on par with or sometimes better than state-of-the-art methods.
Multi-domain text classification can automatically classify texts in various scenarios. Due to the diversity of human languages, texts with the same label in different domains may differ greatly, which brings challenges to the multi-domain text classification. Current advanced methods use the private-shared paradigm, capturing domain-shared features by a shared encoder, and training a private encoder for each domain to extract domain-specific features. However, in realistic scenarios, these methods suffer from inefficiency as new domains are constantly emerging. In this paper, we propose a robust contrastive alignment method to align text classification features of various domains in the same feature space by supervised contrastive learning. By this means, we only need two universal feature extractors to achieve multi-domain text classification. Extensive experimental results show that our method performs on par with or sometimes better than the state-of-the-art method, which uses the complex multi-classifier in a private-shared framework.