DMix: Distance Constrained Interpolative Mixup
Ramit Sawhney, Megh Thakkar, Shrey Pandit, Debdoot Mukherjee, Lucie Flek
This paper has been retracted. Paper was already published elsewhere and the authors want to withdraw the paper.
Abstract
Interpolation-based regularisation methods have proven to be effective for various tasks and modalities. Mixup is a data augmentation method that generates virtual training samples from convex combinations of individual inputs and labels. We extend Mixup and propose DMix, distance-constrained interpolative Mixup for sentence classification leveraging the hyperbolic space. DMix achieves state-of-the-art results on sentence classification over existing data augmentation methods across datasets in four languages.- Anthology ID:
- 2021.mrl-1.21
- Original:
- 2021.mrl-1.21v1
- Version 2:
- 2021.mrl-1.21v2
- Volume:
- Proceedings of the 1st Workshop on Multilingual Representation Learning
- Month:
- November
- Year:
- 2021
- Address:
- Punta Cana, Dominican Republic
- Venue:
- MRL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 242–244
- Language:
- URL:
- https://aclanthology.org/2021.mrl-1.21
- DOI:
- 10.18653/v1/2021.mrl-1.21
- PDF:
- https://preview.aclanthology.org/nodalida-main-page/2021.mrl-1.21.pdf