2022/10/27 by Zilin Yuan, Yinghui Li, Yuan, Zilin +9 · 1 citation
Computer Science · Mathematics · #Adversarial system #Artificial intelligence #Classifier (UML) #Computation and Language (cs.CL) #Computer science #Domain (mathematical analysis) #FOS: Computer and information sciences #Machine learning #Mathematics #Natural language processing #Ranking (information retrieval) #Sentiment Analysis and Opinion Mining #Text and Document Classification Technologies #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2210.15147
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2022/10/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06
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.