@inproceedings{de-silva-etal-2023-semantic,
title = "Semantic matching for text classification with complex class descriptions",
author = "De Silva, Brian and
Huang, Kuan-Wen and
Lee, Gwang and
Hovsepian, Karen and
Xu, Yan and
Shen, Mingwei",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.475",
doi = "10.18653/v1/2023.emnlp-main.475",
pages = "7654--7680",
abstract = "Text classifiers are an indispensable tool for machine learning practitioners, but adapting them to new classes is expensive. To reduce the cost of new classes, previous work exploits class descriptions and/or labels from existing classes. However, these approaches leave a gap in the model development cycle as they support either zero- or few-shot learning, but not both. Existing classifiers either do not work on zero-shot problems, or fail to improve much with few-shot labels. Further, prior work is aimed at concise class descriptions, which may be insufficient for complex classes. We overcome these shortcomings by casting text classification as a matching problem, where a model matches examples with relevant class descriptions. This formulation lets us leverage labels and complex class descriptions to perform zero- and few-shot learning on new classes. We compare this approach with numerous baselines on text classification tasks with complex class descriptions and find that it achieves strong zero-shot performance and scales well with few-shot samples, beating strong baselines by 22.48{\%} (average precision) in the 10-shot setting. Furthermore, we extend the popular Model-Agnostic Meta-Learning algorithm to the zero-shot matching setting and show it improves zero-shot performance by 4.29{\%}. Our results show that expressing text classification as a matching problem is a cost-effective way to address new classes. This strategy enables zero-shot learning for cold-start scenarios and few-shot learning so the model can improve until it is capable enough to deploy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-silva-etal-2023-semantic">
<titleInfo>
<title>Semantic matching for text classification with complex class descriptions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">De Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kuan-Wen</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gwang</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karen</namePart>
<namePart type="family">Hovsepian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingwei</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text classifiers are an indispensable tool for machine learning practitioners, but adapting them to new classes is expensive. To reduce the cost of new classes, previous work exploits class descriptions and/or labels from existing classes. However, these approaches leave a gap in the model development cycle as they support either zero- or few-shot learning, but not both. Existing classifiers either do not work on zero-shot problems, or fail to improve much with few-shot labels. Further, prior work is aimed at concise class descriptions, which may be insufficient for complex classes. We overcome these shortcomings by casting text classification as a matching problem, where a model matches examples with relevant class descriptions. This formulation lets us leverage labels and complex class descriptions to perform zero- and few-shot learning on new classes. We compare this approach with numerous baselines on text classification tasks with complex class descriptions and find that it achieves strong zero-shot performance and scales well with few-shot samples, beating strong baselines by 22.48% (average precision) in the 10-shot setting. Furthermore, we extend the popular Model-Agnostic Meta-Learning algorithm to the zero-shot matching setting and show it improves zero-shot performance by 4.29%. Our results show that expressing text classification as a matching problem is a cost-effective way to address new classes. This strategy enables zero-shot learning for cold-start scenarios and few-shot learning so the model can improve until it is capable enough to deploy.</abstract>
<identifier type="citekey">de-silva-etal-2023-semantic</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.475</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.475</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>7654</start>
<end>7680</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semantic matching for text classification with complex class descriptions
%A De Silva, Brian
%A Huang, Kuan-Wen
%A Lee, Gwang
%A Hovsepian, Karen
%A Xu, Yan
%A Shen, Mingwei
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F de-silva-etal-2023-semantic
%X Text classifiers are an indispensable tool for machine learning practitioners, but adapting them to new classes is expensive. To reduce the cost of new classes, previous work exploits class descriptions and/or labels from existing classes. However, these approaches leave a gap in the model development cycle as they support either zero- or few-shot learning, but not both. Existing classifiers either do not work on zero-shot problems, or fail to improve much with few-shot labels. Further, prior work is aimed at concise class descriptions, which may be insufficient for complex classes. We overcome these shortcomings by casting text classification as a matching problem, where a model matches examples with relevant class descriptions. This formulation lets us leverage labels and complex class descriptions to perform zero- and few-shot learning on new classes. We compare this approach with numerous baselines on text classification tasks with complex class descriptions and find that it achieves strong zero-shot performance and scales well with few-shot samples, beating strong baselines by 22.48% (average precision) in the 10-shot setting. Furthermore, we extend the popular Model-Agnostic Meta-Learning algorithm to the zero-shot matching setting and show it improves zero-shot performance by 4.29%. Our results show that expressing text classification as a matching problem is a cost-effective way to address new classes. This strategy enables zero-shot learning for cold-start scenarios and few-shot learning so the model can improve until it is capable enough to deploy.
%R 10.18653/v1/2023.emnlp-main.475
%U https://aclanthology.org/2023.emnlp-main.475
%U https://doi.org/10.18653/v1/2023.emnlp-main.475
%P 7654-7680
Markdown (Informal)
[Semantic matching for text classification with complex class descriptions](https://aclanthology.org/2023.emnlp-main.475) (De Silva et al., EMNLP 2023)
ACL