@inproceedings{klein-nabi-2022-scd,
title = "{SCD}: Self-Contrastive Decorrelation of Sentence Embeddings",
author = "Klein, Tassilo and
Nabi, Moin",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-short.44",
doi = "10.18653/v1/2022.acl-short.44",
pages = "394--400",
abstract = "In this paper, we propose Self-Contrastive Decorrelation (SCD), a self-supervised approach. Given an input sentence, it optimizes a joint self-contrastive and decorrelation objective. Learning a representation is facilitated by leveraging the contrast arising from the instantiation of standard dropout at different rates. The proposed method is conceptually simple yet empirically powerful. It achieves comparable results with state-of-the-art methods on multiple benchmarks without using contrastive pairs. This study opens up avenues for efficient self-supervised learning methods that are more robust than current contrastive methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="klein-nabi-2022-scd">
<titleInfo>
<title>SCD: Self-Contrastive Decorrelation of Sentence Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tassilo</namePart>
<namePart type="family">Klein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Moin</namePart>
<namePart type="family">Nabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we propose Self-Contrastive Decorrelation (SCD), a self-supervised approach. Given an input sentence, it optimizes a joint self-contrastive and decorrelation objective. Learning a representation is facilitated by leveraging the contrast arising from the instantiation of standard dropout at different rates. The proposed method is conceptually simple yet empirically powerful. It achieves comparable results with state-of-the-art methods on multiple benchmarks without using contrastive pairs. This study opens up avenues for efficient self-supervised learning methods that are more robust than current contrastive methods.</abstract>
<identifier type="citekey">klein-nabi-2022-scd</identifier>
<identifier type="doi">10.18653/v1/2022.acl-short.44</identifier>
<location>
<url>https://aclanthology.org/2022.acl-short.44</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>394</start>
<end>400</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SCD: Self-Contrastive Decorrelation of Sentence Embeddings
%A Klein, Tassilo
%A Nabi, Moin
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F klein-nabi-2022-scd
%X In this paper, we propose Self-Contrastive Decorrelation (SCD), a self-supervised approach. Given an input sentence, it optimizes a joint self-contrastive and decorrelation objective. Learning a representation is facilitated by leveraging the contrast arising from the instantiation of standard dropout at different rates. The proposed method is conceptually simple yet empirically powerful. It achieves comparable results with state-of-the-art methods on multiple benchmarks without using contrastive pairs. This study opens up avenues for efficient self-supervised learning methods that are more robust than current contrastive methods.
%R 10.18653/v1/2022.acl-short.44
%U https://aclanthology.org/2022.acl-short.44
%U https://doi.org/10.18653/v1/2022.acl-short.44
%P 394-400
Markdown (Informal)
[SCD: Self-Contrastive Decorrelation of Sentence Embeddings](https://aclanthology.org/2022.acl-short.44) (Klein & Nabi, ACL 2022)
ACL