no code implementations • 22 Mar 2024 • Kyohoon Jin, Junho Lee, Juhwan Choi, Sangmin Song, Youngbin Kim
Inspired by recent studies on decision boundaries, this paper proposes a decision-boundary-aware data augmentation strategy to enhance robustness using pretrained language models.
1 code implementation • 8 Feb 2024 • Juhwan Choi, Kyohoon Jin, Junho Lee, Sangmin Song, Youngbin Kim
Rule-based text data augmentation is widely used for NLP tasks due to its simplicity.
1 code implementation • 8 Feb 2024 • Juhwan Choi, Kyohoon Jin, Junho Lee, Sangmin Song, Youngbin Kim
Text data augmentation is a complex problem due to the discrete nature of sentences.