@inproceedings{29c35323d60041a5be940f538b2fbfbe,
title = "CIAug: Equipping Interpolative Augmentation with Curriculum Learning",
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.",
author = "Ramit Sawhney and Ritesh Soun and Shrey Pandit and Megh Thakkar and Sarvagya Malaviya and Yuval Pinter",
note = "Publisher Copyright: {\textcopyright} 2022 Association for Computational Linguistics.; 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022 ; Conference date: 10-07-2022 Through 15-07-2022",
year = "2022",
month = jan,
day = "1",
language = "English",
series = "NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",
pages = "1758--1764",
booktitle = "NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics",
address = "United States",
}