<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jun-lee-2025-dynamic">
    <titleInfo>
        <title>Dynamic Order Template Prediction for Generative Aspect-Based Sentiment Analysis</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yonghyun</namePart>
        <namePart type="family">Jun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hwanhee</namePart>
        <namePart type="family">Lee</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>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</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">979-8-89176-252-7</identifier>
    </relatedItem>
    <abstract>Aspect-based sentiment analysis (ABSA) assesses sentiments towards specific aspects within texts, resulting in detailed sentiment tuples.Previous ABSA models often used static templates to predict all the elements in the tuples, and these models often failed to accurately capture dependencies between elements. Multi-view prompting method improves the performance of ABSA by predicting tuples with various templates and then assembling the results. However, this method suffers from inefficiencies and out-of-distribution errors. In this paper, we propose a Dynamic Order Template (DOT) method for ABSA, which dynamically creates an order template that contains only the necessary views for each instance. Ensuring the diverse and relevant view generation, our proposed method improves F1 scores on ASQP and ACOS datasets while significantly reducing inference time.</abstract>
    <identifier type="citekey">jun-lee-2025-dynamic</identifier>
    <identifier type="doi">10.18653/v1/2025.acl-short.48</identifier>
    <location>
        <url>https://aclanthology.org/2025.acl-short.48/</url>
    </location>
    <part>
        <date>2025-07</date>
        <extent unit="page">
            <start>614</start>
            <end>626</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Dynamic Order Template Prediction for Generative Aspect-Based Sentiment Analysis
%A Jun, Yonghyun
%A Lee, Hwanhee
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-252-7
%F jun-lee-2025-dynamic
%X Aspect-based sentiment analysis (ABSA) assesses sentiments towards specific aspects within texts, resulting in detailed sentiment tuples.Previous ABSA models often used static templates to predict all the elements in the tuples, and these models often failed to accurately capture dependencies between elements. Multi-view prompting method improves the performance of ABSA by predicting tuples with various templates and then assembling the results. However, this method suffers from inefficiencies and out-of-distribution errors. In this paper, we propose a Dynamic Order Template (DOT) method for ABSA, which dynamically creates an order template that contains only the necessary views for each instance. Ensuring the diverse and relevant view generation, our proposed method improves F1 scores on ASQP and ACOS datasets while significantly reducing inference time.
%R 10.18653/v1/2025.acl-short.48
%U https://aclanthology.org/2025.acl-short.48/
%U https://doi.org/10.18653/v1/2025.acl-short.48
%P 614-626

Markdown (Informal)

[Dynamic Order Template Prediction for Generative Aspect-Based Sentiment Analysis](https://aclanthology.org/2025.acl-short.48/) (Jun & Lee, ACL 2025)

• Dynamic Order Template Prediction for Generative Aspect-Based Sentiment Analysis (Jun & Lee, ACL 2025)

ACL

• Yonghyun Jun and Hwanhee Lee. 2025. Dynamic Order Template Prediction for Generative Aspect-Based Sentiment Analysis. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 614–626, Vienna, Austria. Association for Computational Linguistics.