<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-etal-2025-danet">
    <titleInfo>
        <title>DaNet: Dual-Aware Enhanced Alignment Network for Multimodal Aspect-Based Sentiment Analysis</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Aoqiang</namePart>
        <namePart type="family">Zhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Min</namePart>
        <namePart type="family">Hu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaohua</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiaoyun</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yiming</namePart>
        <namePart type="family">Tang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ning</namePart>
        <namePart type="family">An</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>Findings of the Association for Computational Linguistics: ACL 2025</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">979-8-89176-256-5</identifier>
    </relatedItem>
    <abstract>Multimodal Aspect-Based Sentiment Analysis (MABSA) aims to extract aspect-sentiment pairs from text and image data. While significant progress has been made in image-aspect alignment, due to the subtlety and complexity of language expressions, there are not always explicit aspect words in the language to align with images. Existing methods typically assume a direct alignment between images and aspects, matching the entire image with a corresponding aspect. This rough alignment of images and aspects introduces noise. To address the above issues, this paper proposes a Dual-Aware Enhanced Alignment Network (DaNet) designed for fine-grained multimodal aspect-image alignment and denoising. Specifically, we first introduce a Multimodal Denoising Encoder (MDE) that jointly image and text to guide the compression and denoising of visual sequences. And then, aspect-aware and sentiment-aware networks are constructed to jointly enhance fine-grained alignment and denoising of text-image information. To better align implicit aspects, an Implicit Aspect Opinion Generation (IAOG) pretraining is designed under the guidance of large language model. Extensive experiments across three MABSA subtasks demonstrate that DaNet outperforms existing methods. Code will be available at https://github.com/***/DaNet.</abstract>
    <identifier type="citekey">zhu-etal-2025-danet</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-acl.741</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-acl.741/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>14369</start>
            <end>14381</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T DaNet: Dual-Aware Enhanced Alignment Network for Multimodal Aspect-Based Sentiment Analysis
%A Zhu, Aoqiang
%A Hu, Min
%A Wang, Xiaohua
%A Yang, Jiaoyun
%A Tang, Yiming
%A An, Ning
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F zhu-etal-2025-danet
%X Multimodal Aspect-Based Sentiment Analysis (MABSA) aims to extract aspect-sentiment pairs from text and image data. While significant progress has been made in image-aspect alignment, due to the subtlety and complexity of language expressions, there are not always explicit aspect words in the language to align with images. Existing methods typically assume a direct alignment between images and aspects, matching the entire image with a corresponding aspect. This rough alignment of images and aspects introduces noise. To address the above issues, this paper proposes a Dual-Aware Enhanced Alignment Network (DaNet) designed for fine-grained multimodal aspect-image alignment and denoising. Specifically, we first introduce a Multimodal Denoising Encoder (MDE) that jointly image and text to guide the compression and denoising of visual sequences. And then, aspect-aware and sentiment-aware networks are constructed to jointly enhance fine-grained alignment and denoising of text-image information. To better align implicit aspects, an Implicit Aspect Opinion Generation (IAOG) pretraining is designed under the guidance of large language model. Extensive experiments across three MABSA subtasks demonstrate that DaNet outperforms existing methods. Code will be available at https://github.com/***/DaNet.
%R 10.18653/v1/2025.findings-acl.741
%U https://aclanthology.org/2025.findings-acl.741/
%U https://doi.org/10.18653/v1/2025.findings-acl.741
%P 14369-14381

Markdown (Informal)

[DaNet: Dual-Aware Enhanced Alignment Network for Multimodal Aspect-Based Sentiment Analysis](https://aclanthology.org/2025.findings-acl.741/) (Zhu et al., Findings 2025)

• DaNet: Dual-Aware Enhanced Alignment Network for Multimodal Aspect-Based Sentiment Analysis (Zhu et al., Findings 2025)

ACL

• Aoqiang Zhu, Min Hu, Xiaohua Wang, Jiaoyun Yang, Yiming Tang, and Ning An. 2025. DaNet: Dual-Aware Enhanced Alignment Network for Multimodal Aspect-Based Sentiment Analysis. In Findings of the Association for Computational Linguistics: ACL 2025, pages 14369–14381, Vienna, Austria. Association for Computational Linguistics.