<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gao-etal-2025-beyond">
    <titleInfo>
        <title>Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shengxiang</namePart>
        <namePart type="family">Gao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jey</namePart>
        <namePart type="given">Han</namePart>
        <namePart type="family">Lau</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jianzhong</namePart>
        <namePart type="family">Qi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Violet</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-332-6</identifier>
    </relatedItem>
    <abstract>Knowledge base question answering (KBQA) aims to answer user questions in natural language using rich human knowledge stored in large KBs. As current KBQA methods struggle with unseen knowledge base elements and their novel compositions at test time, we introduce SG-KBQA — a novel model that injects schema contexts into entity retrieval and logical form generation to tackle this issue. It exploits information about the semantics and structure of the knowledge base provided by schema contexts to enhance generalizability. We show that achieves strong generalizability, outperforming state-of-the-art models on two commonly used benchmark datasets across a variety of test settings. Our source code is available at https://github.com/gaosx2000/SG_KBQA.</abstract>
    <identifier type="citekey">gao-etal-2025-beyond</identifier>
    <identifier type="doi">10.18653/v1/2025.emnlp-main.442</identifier>
    <location>
        <url>https://aclanthology.org/2025.emnlp-main.442/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>8753</start>
            <end>8772</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation
%A Gao, Shengxiang
%A Lau, Jey Han
%A Qi, Jianzhong
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F gao-etal-2025-beyond
%X Knowledge base question answering (KBQA) aims to answer user questions in natural language using rich human knowledge stored in large KBs. As current KBQA methods struggle with unseen knowledge base elements and their novel compositions at test time, we introduce SG-KBQA — a novel model that injects schema contexts into entity retrieval and logical form generation to tackle this issue. It exploits information about the semantics and structure of the knowledge base provided by schema contexts to enhance generalizability. We show that achieves strong generalizability, outperforming state-of-the-art models on two commonly used benchmark datasets across a variety of test settings. Our source code is available at https://github.com/gaosx2000/SG_KBQA.
%R 10.18653/v1/2025.emnlp-main.442
%U https://aclanthology.org/2025.emnlp-main.442/
%U https://doi.org/10.18653/v1/2025.emnlp-main.442
%P 8753-8772

Markdown (Informal)

[Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation](https://aclanthology.org/2025.emnlp-main.442/) (Gao et al., EMNLP 2025)

• Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation (Gao et al., EMNLP 2025)

ACL

• Shengxiang Gao, Jey Han Lau, and Jianzhong Qi. 2025. Beyond Seen Data: Improving KBQA Generalization Through Schema-Guided Logical Form Generation. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 8753–8772, Suzhou, China. Association for Computational Linguistics.