A Curriculum Learning Approach for Multi-domain Text Classification Using Keyword weight Ranking
This addresses the need for efficient cross-domain text classification with limited annotated data, representing an incremental improvement over existing adversarial learning methods.
The paper tackles the problem of domain dependence and data scarcity in text classification by proposing a curriculum learning strategy based on keyword weight ranking to improve multi-domain models, achieving state-of-the-art performance on Amazon review and FDU-MTL datasets.
Text classification is a very classic NLP task, but it has two prominent shortcomings: On the one hand, text classification is deeply domain-dependent. That is, a classifier trained on the corpus of one domain may not perform so well in another domain. On the other hand, text classification models require a lot of annotated data for training. However, for some domains, there may not exist enough annotated data. Therefore, it is valuable to investigate how to efficiently utilize text data from different domains to improve the performance of models in various domains. Some multi-domain text classification models are trained by adversarial training to extract shared features among all domains and the specific features of each domain. We noted that the distinctness of the domain-specific features is different, so in this paper, we propose to use a curriculum learning strategy based on keyword weight ranking to improve the performance of multi-domain text classification models. The experimental results on the Amazon review and FDU-MTL datasets show that our curriculum learning strategy effectively improves the performance of multi-domain text classification models based on adversarial learning and outperforms state-of-the-art methods.