<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2023-prototype">
    <titleInfo>
        <title>Prototype-Guided Pseudo Labeling for Semi-Supervised Text Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Weiyi</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Richong</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Junfan</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lihong</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jaein</namePart>
        <namePart type="family">Kim</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>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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>Semi-supervised text classification (SSTC) aims at text classification with few labeled data and massive unlabeled data. Recent works achieve this task by pseudo-labeling methods, with the belief that the unlabeled and labeled data have identical data distribution, and assign the unlabeled data with pseudo-labels as additional supervision. However, existing pseudo-labeling methods usually suffer from ambiguous categorical boundary issues when training the pseudo-labeling phase, and simply select pseudo-labels without considering the unbalanced categorical distribution of the unlabeled data, making it difficult to generate reliable pseudo-labels for each category. We propose a novel semi-supervised framework, namely ProtoS2, with prototypical cluster separation (PCS) and prototypical-center data selection (CDS) technology to address the issue. Particularly, PCS exploits categorical prototypes to assimilate instance representations within the same category, thus emphasizing low-density separation for the pseudo-labeled data to alleviate ambiguous boundaries. Besides, CDS selects central pseudo-labeled data considering the categorical distribution, avoiding the model from biasing on dominant categories. Empirical studies and extensive analysis with four benchmarks demonstrate the effectiveness of the proposed model.</abstract>
    <identifier type="citekey">yang-etal-2023-prototype</identifier>
    <identifier type="doi">10.18653/v1/2023.acl-long.904</identifier>
    <location>
        <url>https://aclanthology.org/2023.acl-long.904</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>16369</start>
            <end>16382</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Prototype-Guided Pseudo Labeling for Semi-Supervised Text Classification
%A Yang, Weiyi
%A Zhang, Richong
%A Chen, Junfan
%A Wang, Lihong
%A Kim, Jaein
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F yang-etal-2023-prototype
%X Semi-supervised text classification (SSTC) aims at text classification with few labeled data and massive unlabeled data. Recent works achieve this task by pseudo-labeling methods, with the belief that the unlabeled and labeled data have identical data distribution, and assign the unlabeled data with pseudo-labels as additional supervision. However, existing pseudo-labeling methods usually suffer from ambiguous categorical boundary issues when training the pseudo-labeling phase, and simply select pseudo-labels without considering the unbalanced categorical distribution of the unlabeled data, making it difficult to generate reliable pseudo-labels for each category. We propose a novel semi-supervised framework, namely ProtoS2, with prototypical cluster separation (PCS) and prototypical-center data selection (CDS) technology to address the issue. Particularly, PCS exploits categorical prototypes to assimilate instance representations within the same category, thus emphasizing low-density separation for the pseudo-labeled data to alleviate ambiguous boundaries. Besides, CDS selects central pseudo-labeled data considering the categorical distribution, avoiding the model from biasing on dominant categories. Empirical studies and extensive analysis with four benchmarks demonstrate the effectiveness of the proposed model.
%R 10.18653/v1/2023.acl-long.904
%U https://aclanthology.org/2023.acl-long.904
%U https://doi.org/10.18653/v1/2023.acl-long.904
%P 16369-16382

Markdown (Informal)

[Prototype-Guided Pseudo Labeling for Semi-Supervised Text Classification](https://aclanthology.org/2023.acl-long.904) (Yang et al., ACL 2023)

• Prototype-Guided Pseudo Labeling for Semi-Supervised Text Classification (Yang et al., ACL 2023)

ACL

• Weiyi Yang, Richong Zhang, Junfan Chen, Lihong Wang, and Jaein Kim. 2023. Prototype-Guided Pseudo Labeling for Semi-Supervised Text Classification. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 16369–16382, Toronto, Canada. Association for Computational Linguistics.