<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="park-etal-2023-cross">
    <titleInfo>
        <title>Cross-task Knowledge Transfer for Extremely Weakly Supervised Text Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Seongmin</namePart>
        <namePart type="family">Park</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kyungho</namePart>
        <namePart type="family">Kim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jihwa</namePart>
        <namePart type="family">Lee</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>Text classification with extremely weak supervision (EWS) imposes stricter supervision constraints compared to regular weakly supervise classification. Absolutely no labeled training samples or hand-crafted rules specific to the evaluation data are allowed. Such restrictions limit state-of-the-art EWS classification methods to indirect weak labeling techniques that assign unnatural label uncertainty estimates. We present PLAT, a framework that creates weak labels by leveraging recent developments in zero-shot text classification. PLAT employs models trained for sub-tasks other than classification to label documents. Most importantly, PLAT refrains from assigning overly confident weak labels and improves soft-label training performance for downstream classifiers. Classifiers trained with PLAT significantly outperform those trained on weak labels generated by the previous state-of-the-art in extremely weakly supervised text classification.</abstract>
    <identifier type="citekey">park-etal-2023-cross</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.328</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.328</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>5329</start>
            <end>5341</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Cross-task Knowledge Transfer for Extremely Weakly Supervised Text Classification
%A Park, Seongmin
%A Kim, Kyungho
%A Lee, Jihwa
%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 park-etal-2023-cross
%X Text classification with extremely weak supervision (EWS) imposes stricter supervision constraints compared to regular weakly supervise classification. Absolutely no labeled training samples or hand-crafted rules specific to the evaluation data are allowed. Such restrictions limit state-of-the-art EWS classification methods to indirect weak labeling techniques that assign unnatural label uncertainty estimates. We present PLAT, a framework that creates weak labels by leveraging recent developments in zero-shot text classification. PLAT employs models trained for sub-tasks other than classification to label documents. Most importantly, PLAT refrains from assigning overly confident weak labels and improves soft-label training performance for downstream classifiers. Classifiers trained with PLAT significantly outperform those trained on weak labels generated by the previous state-of-the-art in extremely weakly supervised text classification.
%R 10.18653/v1/2023.findings-acl.328
%U https://aclanthology.org/2023.findings-acl.328
%U https://doi.org/10.18653/v1/2023.findings-acl.328
%P 5329-5341

Markdown (Informal)

[Cross-task Knowledge Transfer for Extremely Weakly Supervised Text Classification](https://aclanthology.org/2023.findings-acl.328) (Park et al., Findings 2023)

• Cross-task Knowledge Transfer for Extremely Weakly Supervised Text Classification (Park et al., Findings 2023)

ACL

• Seongmin Park, Kyungho Kim, and Jihwa Lee. 2023. Cross-task Knowledge Transfer for Extremely Weakly Supervised Text Classification. In Findings of the Association for Computational Linguistics: ACL 2023, pages 5329–5341, Toronto, Canada. Association for Computational Linguistics.