<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yan-etal-2024-multi">
    <titleInfo>
        <title>Multi-modal Concept Alignment Pre-training for Generative Medical Visual Question Answering</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Quan</namePart>
        <namePart type="family">Yan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Junwen</namePart>
        <namePart type="family">Duan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jianxin</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics ACL 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Lun-Wei</namePart>
            <namePart type="family">Ku</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andre</namePart>
            <namePart type="family">Martins</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vivek</namePart>
            <namePart type="family">Srikumar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Medical Visual Question Answering (Med-VQA) seeks to accurately respond to queries regarding medical images, a task particularly challenging for open-ended questions. This study unveils the Multi-modal Concept Alignment Pre-training (MMCAP) approach for generative Med-VQA, leveraging a knowledge graph sourced from medical image-caption datasets and the Unified Medical Language System. MMCAP advances the fusion of visual and textual medical knowledge via a graph attention network and a transformer decoder. Additionally, it incorporates a Type Conditional Prompt in the fine-tuning phase, markedly boosting the accuracy and relevance of answers to open-ended questions. Our tests on benchmark datasets illustrate MMCAP’s superiority over existing methods, demonstrating its high efficiency in data-limited settings and effective knowledge-image alignment capability.</abstract>
    <identifier type="citekey">yan-etal-2024-multi</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-acl.319</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>5378</start>
            <end>5389</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multi-modal Concept Alignment Pre-training for Generative Medical Visual Question Answering
%A Yan, Quan
%A Duan, Junwen
%A Wang, Jianxin
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F yan-etal-2024-multi
%X Medical Visual Question Answering (Med-VQA) seeks to accurately respond to queries regarding medical images, a task particularly challenging for open-ended questions. This study unveils the Multi-modal Concept Alignment Pre-training (MMCAP) approach for generative Med-VQA, leveraging a knowledge graph sourced from medical image-caption datasets and the Unified Medical Language System. MMCAP advances the fusion of visual and textual medical knowledge via a graph attention network and a transformer decoder. Additionally, it incorporates a Type Conditional Prompt in the fine-tuning phase, markedly boosting the accuracy and relevance of answers to open-ended questions. Our tests on benchmark datasets illustrate MMCAP’s superiority over existing methods, demonstrating its high efficiency in data-limited settings and effective knowledge-image alignment capability.
%U https://aclanthology.org/2024.findings-acl.319
%P 5378-5389

Markdown (Informal)

[Multi-modal Concept Alignment Pre-training for Generative Medical Visual Question Answering](https://aclanthology.org/2024.findings-acl.319) (Yan et al., Findings 2024)

• Multi-modal Concept Alignment Pre-training for Generative Medical Visual Question Answering (Yan et al., Findings 2024)

ACL

• Quan Yan, Junwen Duan, and Jianxin Wang. 2024. Multi-modal Concept Alignment Pre-training for Generative Medical Visual Question Answering. In Findings of the Association for Computational Linguistics ACL 2024, pages 5378–5389, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.