Investigating Semi-Supervised Learning Algorithms in Text Datasets

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 ha...

Full description

Saved in:
Bibliographic Details
Main Authors: Kesgin, H. Toprak, Amasyali, M. Fatih
Format: Conference Proceeding
Language:English
Subjects:
co-training
Costs
Intelligent systems
Neural networks
self-training
semi supervised learning
Semisupervised learning
Task analysis
Technological innovation
Training
tri-training
tri-training with disagreement
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2770-7946
DOI:10.1109/ASYU56188.2022.9925410