@inproceedings{cagatan-2024-unsee,
title = "{UNSEE}: Unsupervised Non-contrastive Sentence Embeddings",
author = {{\c{C}}a{\u{g}}atan, {\"O}mer},
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-long.23",
pages = "384--393",
abstract = "In this paper, we introduce UNSEE, which stands for Unsupervised Non-Contrastive Sentence Embeddings. UNSEE demonstrates better performance compared to SimCSE in the Massive Text Embedding (MTEB) benchmark. We begin by highlighting the issue of representation collapse that occurs with the replacement of contrastive objectives with non-contrastive objectives in SimCSE. Subsequently, we introduce a straightforward solution called the target network to mitigate this problem. This approach enables us to harness non-contrastive objectives while ensuring training stability and achieving performance improvements similar to those seen with contrastive objectives. We have reached peak performance in non-contrastive sentence embeddings through extensive fine-tuning and optimization. These efforts have resulted in superior sentence representation models, emphasizing the importance of careful tuning and optimization for non-contrastive objectives.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cagatan-2024-unsee">
<titleInfo>
<title>UNSEE: Unsupervised Non-contrastive Sentence Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ömer</namePart>
<namePart type="family">Çağatan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we introduce UNSEE, which stands for Unsupervised Non-Contrastive Sentence Embeddings. UNSEE demonstrates better performance compared to SimCSE in the Massive Text Embedding (MTEB) benchmark. We begin by highlighting the issue of representation collapse that occurs with the replacement of contrastive objectives with non-contrastive objectives in SimCSE. Subsequently, we introduce a straightforward solution called the target network to mitigate this problem. This approach enables us to harness non-contrastive objectives while ensuring training stability and achieving performance improvements similar to those seen with contrastive objectives. We have reached peak performance in non-contrastive sentence embeddings through extensive fine-tuning and optimization. These efforts have resulted in superior sentence representation models, emphasizing the importance of careful tuning and optimization for non-contrastive objectives.</abstract>
<identifier type="citekey">cagatan-2024-unsee</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-long.23</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>384</start>
<end>393</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UNSEE: Unsupervised Non-contrastive Sentence Embeddings
%A Çağatan, Ömer
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F cagatan-2024-unsee
%X In this paper, we introduce UNSEE, which stands for Unsupervised Non-Contrastive Sentence Embeddings. UNSEE demonstrates better performance compared to SimCSE in the Massive Text Embedding (MTEB) benchmark. We begin by highlighting the issue of representation collapse that occurs with the replacement of contrastive objectives with non-contrastive objectives in SimCSE. Subsequently, we introduce a straightforward solution called the target network to mitigate this problem. This approach enables us to harness non-contrastive objectives while ensuring training stability and achieving performance improvements similar to those seen with contrastive objectives. We have reached peak performance in non-contrastive sentence embeddings through extensive fine-tuning and optimization. These efforts have resulted in superior sentence representation models, emphasizing the importance of careful tuning and optimization for non-contrastive objectives.
%U https://aclanthology.org/2024.eacl-long.23
%P 384-393
Markdown (Informal)
[UNSEE: Unsupervised Non-contrastive Sentence Embeddings](https://aclanthology.org/2024.eacl-long.23) (Çağatan, EACL 2024)
ACL
- Ömer Çağatan. 2024. UNSEE: Unsupervised Non-contrastive Sentence Embeddings. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 384–393, St. Julian’s, Malta. Association for Computational Linguistics.