@inproceedings{qin-etal-2023-cliptext,
title = "{CLIPT}ext: A New Paradigm for Zero-shot Text Classification",
author = "Qin, Libo and
Wang, Weiyun and
Chen, Qiguang and
Che, Wanxiang",
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.69",
doi = "10.18653/v1/2023.findings-acl.69",
pages = "1077--1088",
abstract = "While CLIP models are useful for zero-shot vision-and-language (VL) tasks or computer vision tasks, little attention has been paid to the application of CLIP for language tasks. Intuitively, CLIP model have a rich representation pre-trained with natural language supervision, in which we argue that it is useful for language tasks. Hence, this work bridge this gap by investigating a CLIP model for zero-shot text classification. Specifically, we introduce CLIPText, a novel paradigm for zero-shot text classification, which reformulates zero-shot text classification into a text-image matching problem that CLIP can be applied to. In addition, we further incorporate prompt into CLIPText (Prompt-CLIPText) to better derive knowledge from CLIP. Experimental results on seven publicly available zero-shot text classification datasets show that both CLIPText and Prompt-CLIPText attain promising performance. Besides, extensive analysis further verifies that knowledge from CLIP can benefit zero-shot text classification task. We hope this work can attract more breakthroughs on applying VL pre-trained models for language tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qin-etal-2023-cliptext">
<titleInfo>
<title>CLIPText: A New Paradigm for Zero-shot Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Libo</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiyun</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qiguang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</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>While CLIP models are useful for zero-shot vision-and-language (VL) tasks or computer vision tasks, little attention has been paid to the application of CLIP for language tasks. Intuitively, CLIP model have a rich representation pre-trained with natural language supervision, in which we argue that it is useful for language tasks. Hence, this work bridge this gap by investigating a CLIP model for zero-shot text classification. Specifically, we introduce CLIPText, a novel paradigm for zero-shot text classification, which reformulates zero-shot text classification into a text-image matching problem that CLIP can be applied to. In addition, we further incorporate prompt into CLIPText (Prompt-CLIPText) to better derive knowledge from CLIP. Experimental results on seven publicly available zero-shot text classification datasets show that both CLIPText and Prompt-CLIPText attain promising performance. Besides, extensive analysis further verifies that knowledge from CLIP can benefit zero-shot text classification task. We hope this work can attract more breakthroughs on applying VL pre-trained models for language tasks.</abstract>
<identifier type="citekey">qin-etal-2023-cliptext</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.69</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.69</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1077</start>
<end>1088</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CLIPText: A New Paradigm for Zero-shot Text Classification
%A Qin, Libo
%A Wang, Weiyun
%A Chen, Qiguang
%A Che, Wanxiang
%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 qin-etal-2023-cliptext
%X While CLIP models are useful for zero-shot vision-and-language (VL) tasks or computer vision tasks, little attention has been paid to the application of CLIP for language tasks. Intuitively, CLIP model have a rich representation pre-trained with natural language supervision, in which we argue that it is useful for language tasks. Hence, this work bridge this gap by investigating a CLIP model for zero-shot text classification. Specifically, we introduce CLIPText, a novel paradigm for zero-shot text classification, which reformulates zero-shot text classification into a text-image matching problem that CLIP can be applied to. In addition, we further incorporate prompt into CLIPText (Prompt-CLIPText) to better derive knowledge from CLIP. Experimental results on seven publicly available zero-shot text classification datasets show that both CLIPText and Prompt-CLIPText attain promising performance. Besides, extensive analysis further verifies that knowledge from CLIP can benefit zero-shot text classification task. We hope this work can attract more breakthroughs on applying VL pre-trained models for language tasks.
%R 10.18653/v1/2023.findings-acl.69
%U https://aclanthology.org/2023.findings-acl.69
%U https://doi.org/10.18653/v1/2023.findings-acl.69
%P 1077-1088
Markdown (Informal)
[CLIPText: A New Paradigm for Zero-shot Text Classification](https://aclanthology.org/2023.findings-acl.69) (Qin et al., Findings 2023)
ACL