@inproceedings{nishikawa-etal-2022-ease,
title = "{EASE}: Entity-Aware Contrastive Learning of Sentence Embedding",
author = "Nishikawa, Sosuke and
Ri, Ryokan and
Yamada, Ikuya and
Tsuruoka, Yoshimasa and
Echizen, Isao",
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.284/",
doi = "10.18653/v1/2022.naacl-main.284",
pages = "3870--3885",
abstract = "We present EASE, a novel method for learning sentence embeddings via contrastive learning between sentences and their related entities. The advantage of using entity supervision is twofold: (1) entities have been shown to be a strong indicator of text semantics and thus should provide rich training signals for sentence embeddings; (2) entities are defined independently of languages and thus offer useful cross-lingual alignment supervision. We evaluate EASE against other unsupervised models both in monolingual and multilingual settings. We show that EASE exhibits competitive or better performance in English semantic textual similarity (STS) and short text clustering (STC) tasks and it significantly outperforms baseline methods in multilingual settings on a variety of tasks. Our source code, pre-trained models, and newly constructed multi-lingual STC dataset are available at \url{https://github.com/studio-ousia/ease}."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nishikawa-etal-2022-ease">
<titleInfo>
<title>EASE: Entity-Aware Contrastive Learning of Sentence Embedding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sosuke</namePart>
<namePart type="family">Nishikawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryokan</namePart>
<namePart type="family">Ri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ikuya</namePart>
<namePart type="family">Yamada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoshimasa</namePart>
<namePart type="family">Tsuruoka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isao</namePart>
<namePart type="family">Echizen</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>We present EASE, a novel method for learning sentence embeddings via contrastive learning between sentences and their related entities. The advantage of using entity supervision is twofold: (1) entities have been shown to be a strong indicator of text semantics and thus should provide rich training signals for sentence embeddings; (2) entities are defined independently of languages and thus offer useful cross-lingual alignment supervision. We evaluate EASE against other unsupervised models both in monolingual and multilingual settings. We show that EASE exhibits competitive or better performance in English semantic textual similarity (STS) and short text clustering (STC) tasks and it significantly outperforms baseline methods in multilingual settings on a variety of tasks. Our source code, pre-trained models, and newly constructed multi-lingual STC dataset are available at https://github.com/studio-ousia/ease.</abstract>
<identifier type="citekey">nishikawa-etal-2022-ease</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.284</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.284/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>3870</start>
<end>3885</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EASE: Entity-Aware Contrastive Learning of Sentence Embedding
%A Nishikawa, Sosuke
%A Ri, Ryokan
%A Yamada, Ikuya
%A Tsuruoka, Yoshimasa
%A Echizen, Isao
%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 nishikawa-etal-2022-ease
%X We present EASE, a novel method for learning sentence embeddings via contrastive learning between sentences and their related entities. The advantage of using entity supervision is twofold: (1) entities have been shown to be a strong indicator of text semantics and thus should provide rich training signals for sentence embeddings; (2) entities are defined independently of languages and thus offer useful cross-lingual alignment supervision. We evaluate EASE against other unsupervised models both in monolingual and multilingual settings. We show that EASE exhibits competitive or better performance in English semantic textual similarity (STS) and short text clustering (STC) tasks and it significantly outperforms baseline methods in multilingual settings on a variety of tasks. Our source code, pre-trained models, and newly constructed multi-lingual STC dataset are available at https://github.com/studio-ousia/ease.
%R 10.18653/v1/2022.naacl-main.284
%U https://aclanthology.org/2022.naacl-main.284/
%U https://doi.org/10.18653/v1/2022.naacl-main.284
%P 3870-3885
Markdown (Informal)
[EASE: Entity-Aware Contrastive Learning of Sentence Embedding](https://aclanthology.org/2022.naacl-main.284/) (Nishikawa et al., NAACL 2022)
ACL
- Sosuke Nishikawa, Ryokan Ri, Ikuya Yamada, Yoshimasa Tsuruoka, and Isao Echizen. 2022. EASE: Entity-Aware Contrastive Learning of Sentence Embedding. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3870–3885, Seattle, United States. Association for Computational Linguistics.