Investigating Semi-Supervised Learning Algorithms in Text Datasets


2022 Innovations in Intelligent Systems and Applications Conference, ASYU 2022, Antalya, Turkey, 7 - 09 September 2022 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/asyu56188.2022.9925410
  • City: Antalya
  • Country: Turkey
  • Keywords: co-training, self-training, semi supervised learning, tri-training, tri-training with disagreement
  • Yıldız Technical University Affiliated: Yes


Using large training datasets enhances the generalization capabilities of neural networks. Semi-supervised learning (SSL) is useful when there are few labeled data and a lot of unlabeled data. SSL methods that use data augmentation are most successful for image datasets. In contrast, texts do not have consistent augmentation methods as images. Consequently, methods that use augmentation are not as effective in text data as they are in image data. In this study, we compared SSL algorithms that do not require augmentation; these are self-training, co-training, tri-training, and tri-training with disagreement. In the experiments, we used 4 different text datasets for different tasks. We examined the algorithms from a variety of perspectives by asking experiment questions and suggested several improvements. Among the algorithms, tri-training with disagreement showed the closest performance to the Oracle; however, performance gap shows that new semi-supervised algorithms or improvements in existing methods are needed.