Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning
Jason Wei, Chengyu Huang, Soroush Vosoughi, Yu Cheng, Shiqi Xu
Abstract
Few-shot text classification is a fundamental NLP task in which a model aims to classify text into a large number of categories, given only a few training examples per category. This paper explores data augmentation—a technique particularly suitable for training with limited data—for this few-shot, highly-multiclass text classification setting. On four diverse text classification tasks, we find that common data augmentation techniques can improve the performance of triplet networks by up to 3.0% on average. To further boost performance, we present a simple training strategy called curriculum data augmentation, which leverages curriculum learning by first training on only original examples and then introducing augmented data as training progresses. We explore a two-stage and a gradual schedule, and find that, compared with standard single-stage training, curriculum data augmentation trains faster, improves performance, and remains robust to high amounts of noising from augmentation.- Anthology ID:
- 2021.naacl-main.434
- Volume:
- Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- June
- Year:
- 2021
- Address:
- Online
- Editors:
- Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 5493–5500
- Language:
- URL:
- https://preview.aclanthology.org/icon-24-ingestion/2021.naacl-main.434/
- DOI:
- 10.18653/v1/2021.naacl-main.434
- Cite (ACL):
- Jason Wei, Chengyu Huang, Soroush Vosoughi, Yu Cheng, and Shiqi Xu. 2021. Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5493–5500, Online. Association for Computational Linguistics.
- Cite (Informal):
- Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning (Wei et al., NAACL 2021)
- PDF:
- https://preview.aclanthology.org/icon-24-ingestion/2021.naacl-main.434.pdf
- Code
- jasonwei20/triplet-loss
- Data
- FewRel