@inproceedings{pappadopulo-farina-2024-non,
title = "Non-contrastive sentence representations via self-supervision",
author = "Pappadopulo, Duccio and
Farina, Marco",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-naacl.266",
pages = "4274--4284",
abstract = "Sample contrastive methods, typically referred to simply as contrastive are the foundation of most unsupervised methods to learn text and sentence embeddings. On the other hand, a different class of self-supervised non-contrastive loss functions and methods have been considered in the computer vision community and referred to as dimension contrastive. In this paper, we thoroughly compare this class of methods with the standard baseline for contrastive sentence embeddings, SimCSE. We find that self-supervised embeddings trained using dimension contrastive objectives can outperform SimCSE on downstream tasks without needing auxiliary loss functions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pappadopulo-farina-2024-non">
<titleInfo>
<title>Non-contrastive sentence representations via self-supervision</title>
</titleInfo>
<name type="personal">
<namePart type="given">Duccio</namePart>
<namePart type="family">Pappadopulo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Farina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Sample contrastive methods, typically referred to simply as contrastive are the foundation of most unsupervised methods to learn text and sentence embeddings. On the other hand, a different class of self-supervised non-contrastive loss functions and methods have been considered in the computer vision community and referred to as dimension contrastive. In this paper, we thoroughly compare this class of methods with the standard baseline for contrastive sentence embeddings, SimCSE. We find that self-supervised embeddings trained using dimension contrastive objectives can outperform SimCSE on downstream tasks without needing auxiliary loss functions.</abstract>
<identifier type="citekey">pappadopulo-farina-2024-non</identifier>
<location>
<url>https://aclanthology.org/2024.findings-naacl.266</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>4274</start>
<end>4284</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Non-contrastive sentence representations via self-supervision
%A Pappadopulo, Duccio
%A Farina, Marco
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Findings of the Association for Computational Linguistics: NAACL 2024
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F pappadopulo-farina-2024-non
%X Sample contrastive methods, typically referred to simply as contrastive are the foundation of most unsupervised methods to learn text and sentence embeddings. On the other hand, a different class of self-supervised non-contrastive loss functions and methods have been considered in the computer vision community and referred to as dimension contrastive. In this paper, we thoroughly compare this class of methods with the standard baseline for contrastive sentence embeddings, SimCSE. We find that self-supervised embeddings trained using dimension contrastive objectives can outperform SimCSE on downstream tasks without needing auxiliary loss functions.
%U https://aclanthology.org/2024.findings-naacl.266
%P 4274-4284
Markdown (Informal)
[Non-contrastive sentence representations via self-supervision](https://aclanthology.org/2024.findings-naacl.266) (Pappadopulo & Farina, Findings 2024)
ACL