@inproceedings{hsu-etal-2023-visually,
title = "Visually-Enhanced Phrase Understanding",
author = "Hsu, Tsu-Yuan and
Li, Chen-An and
Huang, Chao-Wei and
Chen, Yun-Nung",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.363",
doi = "10.18653/v1/2023.findings-acl.363",
pages = "5879--5888",
abstract = "Large-scale vision-language pre-training has exhibited strong performance in various visual and textual understanding tasks. Recently, the textual encoders of multi-modal pre-trained models have been shown to generate high-quality textual representations, which often outperform models that are purely text-based, such as BERT. In this study, our objective is to utilize both textual and visual encoders of multi-modal pre-trained models to enhance language understanding tasks. We achieve this by generating an image associated with a textual prompt, thus enriching the representation of a phrase for downstream tasks. Results from experiments conducted on four benchmark datasets demonstrate that our proposed method, which leverages visually-enhanced text representations, significantly improves performance in the entity clustering task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hsu-etal-2023-visually">
<titleInfo>
<title>Visually-Enhanced Phrase Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tsu-Yuan</namePart>
<namePart type="family">Hsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen-An</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-Wei</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large-scale vision-language pre-training has exhibited strong performance in various visual and textual understanding tasks. Recently, the textual encoders of multi-modal pre-trained models have been shown to generate high-quality textual representations, which often outperform models that are purely text-based, such as BERT. In this study, our objective is to utilize both textual and visual encoders of multi-modal pre-trained models to enhance language understanding tasks. We achieve this by generating an image associated with a textual prompt, thus enriching the representation of a phrase for downstream tasks. Results from experiments conducted on four benchmark datasets demonstrate that our proposed method, which leverages visually-enhanced text representations, significantly improves performance in the entity clustering task.</abstract>
<identifier type="citekey">hsu-etal-2023-visually</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.363</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.363</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>5879</start>
<end>5888</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Visually-Enhanced Phrase Understanding
%A Hsu, Tsu-Yuan
%A Li, Chen-An
%A Huang, Chao-Wei
%A Chen, Yun-Nung
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F hsu-etal-2023-visually
%X Large-scale vision-language pre-training has exhibited strong performance in various visual and textual understanding tasks. Recently, the textual encoders of multi-modal pre-trained models have been shown to generate high-quality textual representations, which often outperform models that are purely text-based, such as BERT. In this study, our objective is to utilize both textual and visual encoders of multi-modal pre-trained models to enhance language understanding tasks. We achieve this by generating an image associated with a textual prompt, thus enriching the representation of a phrase for downstream tasks. Results from experiments conducted on four benchmark datasets demonstrate that our proposed method, which leverages visually-enhanced text representations, significantly improves performance in the entity clustering task.
%R 10.18653/v1/2023.findings-acl.363
%U https://aclanthology.org/2023.findings-acl.363
%U https://doi.org/10.18653/v1/2023.findings-acl.363
%P 5879-5888
Markdown (Informal)
[Visually-Enhanced Phrase Understanding](https://aclanthology.org/2023.findings-acl.363) (Hsu et al., Findings 2023)
ACL
- Tsu-Yuan Hsu, Chen-An Li, Chao-Wei Huang, and Yun-Nung Chen. 2023. Visually-Enhanced Phrase Understanding. In Findings of the Association for Computational Linguistics: ACL 2023, pages 5879–5888, Toronto, Canada. Association for Computational Linguistics.