Summary of Enhancing Effectiveness and Robustness in a Low-resource Regime Via Decision-boundary-aware Data Augmentation, by Kyohoon Jin et al.
Enhancing Effectiveness and Robustness in a Low-Resource Regime via Decision-Boundary-aware Data Augmentation
by Kyohoon Jin, Junho Lee, Juhwan Choi, Sangmin Song, Youngbin Kim
First submitted to arxiv on: 22 Mar 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed decision-boundary-aware data augmentation strategy leverages pretrained language models to enhance robustness in low-resource regimes. By shifting latent features closer to the decision boundary, followed by reconstruction, ambiguous versions are generated with soft labels. Additionally, mid-K sampling is employed to increase sentence diversity. The approach outperforms other methods through extensive experiments and is extensible with curriculum data augmentation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper proposes a new way to make AI models more robust when they don’t have much training data. They use a special technique called “decision-boundary-aware” that helps the model make better decisions by shifting its focus to the boundary between correct and incorrect answers. The approach also generates ambiguous sentences with soft labels, making it harder for the model to misclassify text. This method can be used in low-resource settings where there’s limited data available. |
Keywords
* Artificial intelligence * Data augmentation
