@inproceedings{clarke-etal-2023-label,
title = "Label Agnostic Pre-training for Zero-shot Text Classification",
author = "Clarke, Christopher and
Heng, Yuzhao and
Kang, Yiping and
Flautner, Krisztian and
Tang, Lingjia and
Mars, Jason",
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.64",
doi = "10.18653/v1/2023.findings-acl.64",
pages = "1009--1021",
abstract = "Conventional approaches to text classification typically assume the existence of a fixed set of predefined labels to which a given text can be classified. However, in real-world applications, there exists an infinite label space for describing a given text. In addition, depending on the aspect (sentiment, topic, etc.) and domain of the text (finance, legal, etc.), the interpretation of the label can vary greatly. This makes the task of text classification, particularly in the zero-shot scenario, extremely challenging. In this paper, we investigate the task of zero-shot text classification with the aim of improving the ability of pre-trained language models (PLMs) to generalize to both seen and unseen data across varying aspects and domains. To solve this we introduce two new simple yet effective pre-training strategies, Implicit and Explicit pre-training. These methods inject aspect-level understanding into the model at train time with the goal of conditioning the model to build task-level understanding. To evaluate this, we construct and release UTCD, a new benchmark dataset for evaluating text classification in zero-shot settings. Experimental results on UTCD show that our approach achieves improved zero-shot generalization on a suite of challenging datasets across an array of zero-shot formalizations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="clarke-etal-2023-label">
<titleInfo>
<title>Label Agnostic Pre-training for Zero-shot Text Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Clarke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuzhao</namePart>
<namePart type="family">Heng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiping</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krisztian</namePart>
<namePart type="family">Flautner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lingjia</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Mars</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>Conventional approaches to text classification typically assume the existence of a fixed set of predefined labels to which a given text can be classified. However, in real-world applications, there exists an infinite label space for describing a given text. In addition, depending on the aspect (sentiment, topic, etc.) and domain of the text (finance, legal, etc.), the interpretation of the label can vary greatly. This makes the task of text classification, particularly in the zero-shot scenario, extremely challenging. In this paper, we investigate the task of zero-shot text classification with the aim of improving the ability of pre-trained language models (PLMs) to generalize to both seen and unseen data across varying aspects and domains. To solve this we introduce two new simple yet effective pre-training strategies, Implicit and Explicit pre-training. These methods inject aspect-level understanding into the model at train time with the goal of conditioning the model to build task-level understanding. To evaluate this, we construct and release UTCD, a new benchmark dataset for evaluating text classification in zero-shot settings. Experimental results on UTCD show that our approach achieves improved zero-shot generalization on a suite of challenging datasets across an array of zero-shot formalizations.</abstract>
<identifier type="citekey">clarke-etal-2023-label</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.64</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.64</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1009</start>
<end>1021</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Label Agnostic Pre-training for Zero-shot Text Classification
%A Clarke, Christopher
%A Heng, Yuzhao
%A Kang, Yiping
%A Flautner, Krisztian
%A Tang, Lingjia
%A Mars, Jason
%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 clarke-etal-2023-label
%X Conventional approaches to text classification typically assume the existence of a fixed set of predefined labels to which a given text can be classified. However, in real-world applications, there exists an infinite label space for describing a given text. In addition, depending on the aspect (sentiment, topic, etc.) and domain of the text (finance, legal, etc.), the interpretation of the label can vary greatly. This makes the task of text classification, particularly in the zero-shot scenario, extremely challenging. In this paper, we investigate the task of zero-shot text classification with the aim of improving the ability of pre-trained language models (PLMs) to generalize to both seen and unseen data across varying aspects and domains. To solve this we introduce two new simple yet effective pre-training strategies, Implicit and Explicit pre-training. These methods inject aspect-level understanding into the model at train time with the goal of conditioning the model to build task-level understanding. To evaluate this, we construct and release UTCD, a new benchmark dataset for evaluating text classification in zero-shot settings. Experimental results on UTCD show that our approach achieves improved zero-shot generalization on a suite of challenging datasets across an array of zero-shot formalizations.
%R 10.18653/v1/2023.findings-acl.64
%U https://aclanthology.org/2023.findings-acl.64
%U https://doi.org/10.18653/v1/2023.findings-acl.64
%P 1009-1021
Markdown (Informal)
[Label Agnostic Pre-training for Zero-shot Text Classification](https://aclanthology.org/2023.findings-acl.64) (Clarke et al., Findings 2023)
ACL
- Christopher Clarke, Yuzhao Heng, Yiping Kang, Krisztian Flautner, Lingjia Tang, and Jason Mars. 2023. Label Agnostic Pre-training for Zero-shot Text Classification. In Findings of the Association for Computational Linguistics: ACL 2023, pages 1009–1021, Toronto, Canada. Association for Computational Linguistics.