Abstract
This paper asks whether extrapolating the hidden space distribution of text examples from one class onto another is a valid inductive bias for data augmentation. To operationalize this question, I propose a simple data augmentation protocol called “good-enough example extrapolation” (GE3). GE3 is lightweight and has no hyperparameters. Applied to three text classification datasets for various data imbalance scenarios, GE3 improves performance more than upsampling and other hidden-space data augmentation methods.- Anthology ID:
- 2021.emnlp-main.479
- Volume:
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2021
- Address:
- Online and Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5923–5929
- Language:
- URL:
- https://aclanthology.org/2021.emnlp-main.479
- DOI:
- 10.18653/v1/2021.emnlp-main.479
- Cite (ACL):
- Jason Wei. 2021. Good-Enough Example Extrapolation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 5923–5929, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- Good-Enough Example Extrapolation (Wei, EMNLP 2021)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2021.emnlp-main.479.pdf
- Data
- FewRel, SNIPS