@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",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sawhney-etal-2022-ciaug">
<titleInfo>
<title>CIAug: Equipping Interpolative Augmentation with Curriculum Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ramit</namePart>
<namePart type="family">Sawhney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Soun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shrey</namePart>
<namePart type="family">Pandit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Megh</namePart>
<namePart type="family">Thakkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarvagya</namePart>
<namePart type="family">Malaviya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuval</namePart>
<namePart type="family">Pinter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">sawhney-etal-2022-ciaug</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.127</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.127</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1758</start>
<end>1764</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CIAug: Equipping Interpolative Augmentation with Curriculum Learning
%A Sawhney, Ramit
%A Soun, Ritesh
%A Pandit, Shrey
%A Thakkar, Megh
%A Malaviya, Sarvagya
%A Pinter, Yuval
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F sawhney-etal-2022-ciaug
%X 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.
%R 10.18653/v1/2022.naacl-main.127
%U https://aclanthology.org/2022.naacl-main.127
%U https://doi.org/10.18653/v1/2022.naacl-main.127
%P 1758-1764
Markdown (Informal)
[CIAug: Equipping Interpolative Augmentation with Curriculum Learning](https://aclanthology.org/2022.naacl-main.127) (Sawhney et al., NAACL 2022)
ACL
- Ramit Sawhney, Ritesh Soun, Shrey Pandit, Megh Thakkar, Sarvagya Malaviya, and Yuval Pinter. 2022. CIAug: Equipping Interpolative Augmentation with Curriculum Learning. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1758–1764, Seattle, United States. Association for Computational Linguistics.