<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akash-chang-2025-understanding">
    <titleInfo>
        <title>Understanding Cross-Domain Adaptation in Low-Resource Topic Modeling</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pritom</namePart>
        <namePart type="given">Saha</namePart>
        <namePart type="family">Akash</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kevin</namePart>
        <namePart type="given">Chen-Chuan</namePart>
        <namePart type="family">Chang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Wanxiang</namePart>
            <namePart type="family">Che</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Joyce</namePart>
            <namePart type="family">Nabende</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ekaterina</namePart>
            <namePart type="family">Shutova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohammad</namePart>
            <namePart type="given">Taher</namePart>
            <namePart type="family">Pilehvar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Vienna, Austria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-251-0</identifier>
    </relatedItem>
    <abstract>Topic modeling plays a vital role in uncovering hidden semantic structures within text corpora, but existing models struggle in low-resource settings where limited target-domain data leads to unstable and incoherent topic inference. We address this challenge by formally introducing domain adaptation for low-resource topic modeling, where a high-resource source domain informs a low-resource target domain without overwhelming it with irrelevant content. We establish a finite-sample generalization bound showing that effective knowledge transfer depends on robust performance in both domains, minimizing latent-space discrepancy, and preventing overfitting to the data. Guided by these insights, we propose DALTA (Domain-Aligned Latent Topic Adaptation), a new framework that employs a shared encoder for domain-invariant features, specialized decoders for domain-specific nuances, and adversarial alignment to selectively transfer relevant information. Experiments on diverse low-resource datasets demonstrate that DALTA consistently outperforms state-of-the-art methods in terms of topic coherence, stability, and transferability.</abstract>
    <identifier type="citekey">akash-chang-2025-understanding</identifier>
    <identifier type="doi">10.18653/v1/2025.acl-long.298</identifier>
    <location>
        <url>https://aclanthology.org/2025.acl-long.298/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>5988</start>
            <end>6001</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Understanding Cross-Domain Adaptation in Low-Resource Topic Modeling
%A Akash, Pritom Saha
%A Chang, Kevin Chen-Chuan
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F akash-chang-2025-understanding
%X Topic modeling plays a vital role in uncovering hidden semantic structures within text corpora, but existing models struggle in low-resource settings where limited target-domain data leads to unstable and incoherent topic inference. We address this challenge by formally introducing domain adaptation for low-resource topic modeling, where a high-resource source domain informs a low-resource target domain without overwhelming it with irrelevant content. We establish a finite-sample generalization bound showing that effective knowledge transfer depends on robust performance in both domains, minimizing latent-space discrepancy, and preventing overfitting to the data. Guided by these insights, we propose DALTA (Domain-Aligned Latent Topic Adaptation), a new framework that employs a shared encoder for domain-invariant features, specialized decoders for domain-specific nuances, and adversarial alignment to selectively transfer relevant information. Experiments on diverse low-resource datasets demonstrate that DALTA consistently outperforms state-of-the-art methods in terms of topic coherence, stability, and transferability.
%R 10.18653/v1/2025.acl-long.298
%U https://aclanthology.org/2025.acl-long.298/
%U https://doi.org/10.18653/v1/2025.acl-long.298
%P 5988-6001

Markdown (Informal)

[Understanding Cross-Domain Adaptation in Low-Resource Topic Modeling](https://aclanthology.org/2025.acl-long.298/) (Akash & Chang, ACL 2025)

• Understanding Cross-Domain Adaptation in Low-Resource Topic Modeling (Akash & Chang, ACL 2025)

ACL

• Pritom Saha Akash and Kevin Chen-Chuan Chang. 2025. Understanding Cross-Domain Adaptation in Low-Resource Topic Modeling. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5988–6001, Vienna, Austria. Association for Computational Linguistics.