CIAug: Equipping Interpolative Augmentation with Curriculum Learning
Ramit Sawhney, Ritesh Soun, Shrey Pandit, Megh Thakkar, Sarvagya Malaviya, Yuval Pinter
Abstract
Interpolative data augmentation has proven to be effective for NLP tasks. Despite its merits, the sample selection process in mixup is random, which might make it difficult for the model to generalize better and converge faster. We propose CIAug, a novel curriculum-based learning method that builds upon mixup. It leverages the relative position of samples in hyperbolic embedding space as a complexity measure to gradually mix up increasingly difficult and diverse samples along training. CIAug achieves state-of-the-art results over existing interpolative augmentation methods on 10 benchmark datasets across 4 languages in text classification and named-entity recognition tasks. It also converges and achieves benchmark F1 scores 3 times faster. We empirically analyze the various components of CIAug, and evaluate its robustness against adversarial attacks.
BibTeX
@inproceedings{sawhney-etal-2022-ciaug,
title = "{CIA}ug: Equipping Interpolative Augmentation with Curriculum Learning",
author = "Sawhney, Ramit and
Soun, Ritesh and
Pandit, Shrey and
Thakkar, Megh and
Malaviya, Sarvagya and
Pinter, Yuval",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.127/",
doi = "10.18653/v1/2022.naacl-main.127",
pages = "1758--1764"
}