@inproceedings{xiao-2024-extremely,
title = "Extremely Weakly-supervised Text Classification with Wordsets Mining and Sync-Denoising",
author = "Xiao, Lysa",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.397",
pages = "7167--7179",
abstract = "Extremely weakly-supervised text classification aims to classify texts without any labeled data, but only relying on class names as supervision. Existing works include prompt-based and seed-based methods. Prompt-based methods prompt language model with instructions, while seed-based methods generate pseudo-labels with word matching. Both of them have significant flaws, including zero-shot instability and context-dependent ambiguities. This paper introduces SetSync, which follows a new paradigm, i.e. wordset-based, which can avoid the above problems. In SetSync, a class is represented with wordsets, and pseudo-labels are generated with wordsets matching. To facilitate this, we propose to use information bottleneck to identify class-relevant wordsets. Moreover, we regard the classifier training as a hybrid learning of semi-supervised and noisy-labels, and propose a new training strategy, termed sync-denoising. Extensive experiments on 11 datasets show that SetSync outperforms all existing prompt and seed methods, exceeding SOTA by an impressive average of 8 points.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiao-2024-extremely">
<titleInfo>
<title>Extremely Weakly-supervised Text Classification with Wordsets Mining and Sync-Denoising</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lysa</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Extremely weakly-supervised text classification aims to classify texts without any labeled data, but only relying on class names as supervision. Existing works include prompt-based and seed-based methods. Prompt-based methods prompt language model with instructions, while seed-based methods generate pseudo-labels with word matching. Both of them have significant flaws, including zero-shot instability and context-dependent ambiguities. This paper introduces SetSync, which follows a new paradigm, i.e. wordset-based, which can avoid the above problems. In SetSync, a class is represented with wordsets, and pseudo-labels are generated with wordsets matching. To facilitate this, we propose to use information bottleneck to identify class-relevant wordsets. Moreover, we regard the classifier training as a hybrid learning of semi-supervised and noisy-labels, and propose a new training strategy, termed sync-denoising. Extensive experiments on 11 datasets show that SetSync outperforms all existing prompt and seed methods, exceeding SOTA by an impressive average of 8 points.</abstract>
<identifier type="citekey">xiao-2024-extremely</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.397</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>7167</start>
<end>7179</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Extremely Weakly-supervised Text Classification with Wordsets Mining and Sync-Denoising
%A Xiao, Lysa
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F xiao-2024-extremely
%X Extremely weakly-supervised text classification aims to classify texts without any labeled data, but only relying on class names as supervision. Existing works include prompt-based and seed-based methods. Prompt-based methods prompt language model with instructions, while seed-based methods generate pseudo-labels with word matching. Both of them have significant flaws, including zero-shot instability and context-dependent ambiguities. This paper introduces SetSync, which follows a new paradigm, i.e. wordset-based, which can avoid the above problems. In SetSync, a class is represented with wordsets, and pseudo-labels are generated with wordsets matching. To facilitate this, we propose to use information bottleneck to identify class-relevant wordsets. Moreover, we regard the classifier training as a hybrid learning of semi-supervised and noisy-labels, and propose a new training strategy, termed sync-denoising. Extensive experiments on 11 datasets show that SetSync outperforms all existing prompt and seed methods, exceeding SOTA by an impressive average of 8 points.
%U https://aclanthology.org/2024.naacl-long.397
%P 7167-7179
Markdown (Informal)
[Extremely Weakly-supervised Text Classification with Wordsets Mining and Sync-Denoising](https://aclanthology.org/2024.naacl-long.397) (Xiao, NAACL 2024)
ACL