@inproceedings{sawhney-etal-2021-hypmix,
title = "{H}yp{M}ix: Hyperbolic Interpolative Data Augmentation",
author = "Sawhney, Ramit and
Thakkar, Megh and
Agarwal, Shivam and
Jin, Di and
Yang, Diyi and
Flek, Lucie",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.776",
doi = "10.18653/v1/2021.emnlp-main.776",
pages = "9858--9868",
abstract = "Interpolation-based regularisation methods for data augmentation have proven to be effective for various tasks and modalities. These methods involve performing mathematical operations over the raw input samples or their latent states representations - vectors that often possess complex hierarchical geometries. However, these operations are performed in the Euclidean space, simplifying these representations, which may lead to distorted and noisy interpolations. We propose HypMix, a novel model-, data-, and modality-agnostic interpolative data augmentation technique operating in the hyperbolic space, which captures the complex geometry of input and hidden state hierarchies better than its contemporaries. We evaluate HypMix on benchmark and low resource datasets across speech, text, and vision modalities, showing that HypMix consistently outperforms state-of-the-art data augmentation techniques. In addition, we demonstrate the use of HypMix in semi-supervised settings. We further probe into the adversarial robustness and qualitative inferences we draw from HypMix that elucidate the efficacy of the Riemannian hyperbolic manifolds for interpolation-based data augmentation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sawhney-etal-2021-hypmix">
<titleInfo>
<title>HypMix: Hyperbolic Interpolative Data Augmentation</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">Megh</namePart>
<namePart type="family">Thakkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shivam</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucie</namePart>
<namePart type="family">Flek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Interpolation-based regularisation methods for data augmentation have proven to be effective for various tasks and modalities. These methods involve performing mathematical operations over the raw input samples or their latent states representations - vectors that often possess complex hierarchical geometries. However, these operations are performed in the Euclidean space, simplifying these representations, which may lead to distorted and noisy interpolations. We propose HypMix, a novel model-, data-, and modality-agnostic interpolative data augmentation technique operating in the hyperbolic space, which captures the complex geometry of input and hidden state hierarchies better than its contemporaries. We evaluate HypMix on benchmark and low resource datasets across speech, text, and vision modalities, showing that HypMix consistently outperforms state-of-the-art data augmentation techniques. In addition, we demonstrate the use of HypMix in semi-supervised settings. We further probe into the adversarial robustness and qualitative inferences we draw from HypMix that elucidate the efficacy of the Riemannian hyperbolic manifolds for interpolation-based data augmentation.</abstract>
<identifier type="citekey">sawhney-etal-2021-hypmix</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.776</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.776</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>9858</start>
<end>9868</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HypMix: Hyperbolic Interpolative Data Augmentation
%A Sawhney, Ramit
%A Thakkar, Megh
%A Agarwal, Shivam
%A Jin, Di
%A Yang, Diyi
%A Flek, Lucie
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F sawhney-etal-2021-hypmix
%X Interpolation-based regularisation methods for data augmentation have proven to be effective for various tasks and modalities. These methods involve performing mathematical operations over the raw input samples or their latent states representations - vectors that often possess complex hierarchical geometries. However, these operations are performed in the Euclidean space, simplifying these representations, which may lead to distorted and noisy interpolations. We propose HypMix, a novel model-, data-, and modality-agnostic interpolative data augmentation technique operating in the hyperbolic space, which captures the complex geometry of input and hidden state hierarchies better than its contemporaries. We evaluate HypMix on benchmark and low resource datasets across speech, text, and vision modalities, showing that HypMix consistently outperforms state-of-the-art data augmentation techniques. In addition, we demonstrate the use of HypMix in semi-supervised settings. We further probe into the adversarial robustness and qualitative inferences we draw from HypMix that elucidate the efficacy of the Riemannian hyperbolic manifolds for interpolation-based data augmentation.
%R 10.18653/v1/2021.emnlp-main.776
%U https://aclanthology.org/2021.emnlp-main.776
%U https://doi.org/10.18653/v1/2021.emnlp-main.776
%P 9858-9868
Markdown (Informal)
[HypMix: Hyperbolic Interpolative Data Augmentation](https://aclanthology.org/2021.emnlp-main.776) (Sawhney et al., EMNLP 2021)
ACL
- Ramit Sawhney, Megh Thakkar, Shivam Agarwal, Di Jin, Diyi Yang, and Lucie Flek. 2021. HypMix: Hyperbolic Interpolative Data Augmentation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9858–9868, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.