<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-multimodal-document">
    <titleInfo>
        <title>Multimodal Document-level Triple Extraction via Dynamic Graph Enhancement and Relation-Aware Reflection</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xiang</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Runhai</namePart>
        <namePart type="family">Jiao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhou</namePart>
        <namePart type="family">Changyu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shoupeng</namePart>
        <namePart type="family">Qiao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ruojiao</namePart>
        <namePart type="family">Qiao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ruifan</namePart>
        <namePart type="family">Li</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>Findings of the Association for Computational Linguistics: EMNLP 2025</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">979-8-89176-335-7</identifier>
    </relatedItem>
    <abstract>Multimodal documents, which are among the most prevalent data formats, combine a large amount of textual and visual content. Extracting structured triples knowledge from these documents is a highly valuable task, aimed at helping users efficiently acquire key entities and their relationships. However, existing methods face limitations in simultaneously processing long textual content and multiple associated images for triple extraction. Therefore, we propose a Multimodal Document-level Triple Extraction (MDocTE) framework. Specifically, we introduce a dynamic document graph construction method that extends the model’s scope to the entire document and the external world, while adaptively optimizing the graph structure. Next, we inject the global information and external knowledge learned by the graph neural network into the large language model, generating structured triples after deep interaction. Finally, we design a multimodal relation-aware mechanism and loss function to guide the model in reflecting on the shared information between text and visuals. We release a new triple extraction dataset for multimodal documents and conduct extensive experiments. The results demonstrate that the proposed framework outperforms the state-of-the-art baselines, thus filling the gap in multimodal document extraction. Our data is available at https://github.com/XiangLiphd/Triple-extraction-dataset-for-multimodal-documents.</abstract>
    <identifier type="citekey">li-etal-2025-multimodal-document</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-emnlp.171/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>3212</start>
            <end>3223</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multimodal Document-level Triple Extraction via Dynamic Graph Enhancement and Relation-Aware Reflection
%A Li, Xiang
%A Jiao, Runhai
%A Changyu, Zhou
%A Qiao, Shoupeng
%A Qiao, Ruojiao
%A Li, Ruifan
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F li-etal-2025-multimodal-document
%X Multimodal documents, which are among the most prevalent data formats, combine a large amount of textual and visual content. Extracting structured triples knowledge from these documents is a highly valuable task, aimed at helping users efficiently acquire key entities and their relationships. However, existing methods face limitations in simultaneously processing long textual content and multiple associated images for triple extraction. Therefore, we propose a Multimodal Document-level Triple Extraction (MDocTE) framework. Specifically, we introduce a dynamic document graph construction method that extends the model’s scope to the entire document and the external world, while adaptively optimizing the graph structure. Next, we inject the global information and external knowledge learned by the graph neural network into the large language model, generating structured triples after deep interaction. Finally, we design a multimodal relation-aware mechanism and loss function to guide the model in reflecting on the shared information between text and visuals. We release a new triple extraction dataset for multimodal documents and conduct extensive experiments. The results demonstrate that the proposed framework outperforms the state-of-the-art baselines, thus filling the gap in multimodal document extraction. Our data is available at https://github.com/XiangLiphd/Triple-extraction-dataset-for-multimodal-documents.
%U https://aclanthology.org/2025.findings-emnlp.171/
%P 3212-3223

Markdown (Informal)

[Multimodal Document-level Triple Extraction via Dynamic Graph Enhancement and Relation-Aware Reflection](https://aclanthology.org/2025.findings-emnlp.171/) (Li et al., Findings 2025)

• Multimodal Document-level Triple Extraction via Dynamic Graph Enhancement and Relation-Aware Reflection (Li et al., Findings 2025)

ACL

• Xiang Li, Runhai Jiao, Zhou Changyu, Shoupeng Qiao, Ruojiao Qiao, and Ruifan Li. 2025. Multimodal Document-level Triple Extraction via Dynamic Graph Enhancement and Relation-Aware Reflection. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 3212–3223, Suzhou, China. Association for Computational Linguistics.