<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2025-taxopro">
    <titleInfo>
        <title>TaxoPro: A Plug-In LoRA-based Cross-Domain Method for Low-Resource Taxonomy Completion</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hongyuan</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuhang</namePart>
        <namePart type="family">Niu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ciyi</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yanlong</namePart>
        <namePart type="family">Wen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaojie</namePart>
        <namePart type="family">Yuan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>Low-resource taxonomy completion aims to automatically insert new concepts into the existing taxonomy, in which only a few in-domain training samples are available. Recent studies have achieved considerable progress by incorporating prior knowledge from pre-trained language models (PLMs). However, these studies tend to overly rely on such knowledge and neglect the shareable knowledge across different taxonomies. In this paper, we propose TaxoPro, a plug-in LoRA-based cross-domain method, that captures shareable knowledge from the high- resource taxonomy to improve PLM-based low-resource taxonomy completion techniques. To prevent negative interference between domain-specific and domain-shared knowledge, TaxoPro decomposes cross- domain knowledge into domain-shared and domain-specific components, storing them using low-rank matrices (LoRA). Additionally, TaxoPro employs two auxiliary losses to regulate the flow of shareable knowledge. Experimental results demonstrate that TaxoPro improves PLM-based techniques, achieving state-of-the-art performance in completing low-resource taxonomies. Code is available at https://github.com/cyclexu/TaxoPro.</abstract>
    <identifier type="citekey">xu-etal-2025-taxopro</identifier>
    <identifier type="doi">10.1162/tacl_a_00755</identifier>
    <location>
        <url>https://aclanthology.org/2025.tacl-1.27/</url>
    </location>
    <part>
        <date>2025</date>
        <detail type="volume"><number>13</number></detail>
        <extent unit="page">
            <start>557</start>
            <end>576</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T TaxoPro: A Plug-In LoRA-based Cross-Domain Method for Low-Resource Taxonomy Completion
%A Xu, Hongyuan
%A Niu, Yuhang
%A Liu, Ciyi
%A Wen, Yanlong
%A Yuan, Xiaojie
%J Transactions of the Association for Computational Linguistics
%D 2025
%V 13
%I MIT Press
%C Cambridge, MA
%F xu-etal-2025-taxopro
%X Low-resource taxonomy completion aims to automatically insert new concepts into the existing taxonomy, in which only a few in-domain training samples are available. Recent studies have achieved considerable progress by incorporating prior knowledge from pre-trained language models (PLMs). However, these studies tend to overly rely on such knowledge and neglect the shareable knowledge across different taxonomies. In this paper, we propose TaxoPro, a plug-in LoRA-based cross-domain method, that captures shareable knowledge from the high- resource taxonomy to improve PLM-based low-resource taxonomy completion techniques. To prevent negative interference between domain-specific and domain-shared knowledge, TaxoPro decomposes cross- domain knowledge into domain-shared and domain-specific components, storing them using low-rank matrices (LoRA). Additionally, TaxoPro employs two auxiliary losses to regulate the flow of shareable knowledge. Experimental results demonstrate that TaxoPro improves PLM-based techniques, achieving state-of-the-art performance in completing low-resource taxonomies. Code is available at https://github.com/cyclexu/TaxoPro.
%R 10.1162/tacl_a_00755
%U https://aclanthology.org/2025.tacl-1.27/
%U https://doi.org/10.1162/tacl_a_00755
%P 557-576

Markdown (Informal)

[TaxoPro: A Plug-In LoRA-based Cross-Domain Method for Low-Resource Taxonomy Completion](https://aclanthology.org/2025.tacl-1.27/) (Xu et al., TACL 2025)

• TaxoPro: A Plug-In LoRA-based Cross-Domain Method for Low-Resource Taxonomy Completion (Xu et al., TACL 2025)

ACL

• Hongyuan Xu, Yuhang Niu, Ciyi Liu, Yanlong Wen, and Xiaojie Yuan. 2025. TaxoPro: A Plug-In LoRA-based Cross-Domain Method for Low-Resource Taxonomy Completion. Transactions of the Association for Computational Linguistics, 13:557–576.