<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ibrohim-etal-2025-modeling">
    <titleInfo>
        <title>Modeling Background Knowledge with Frame Semantics for Fine-grained Sentiment Classification</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Muhammad</namePart>
        <namePart type="given">Okky</namePart>
        <namePart type="family">Ibrohim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Valerio</namePart>
        <namePart type="family">Basile</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Danilo</namePart>
        <namePart type="family">Croce</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Cristina</namePart>
        <namePart type="family">Bosco</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Roberto</namePart>
        <namePart type="family">Basili</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2nd Workshop on Analogical Abstraction in Cognition, Perception, and Language (Analogy-Angle II)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Giulia</namePart>
            <namePart type="family">Rambelli</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Filip</namePart>
            <namePart type="family">Ilievski</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marianna</namePart>
            <namePart type="family">Bolognesi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Pia</namePart>
            <namePart type="family">Sommerauer</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">979-8-89176-274-9</identifier>
    </relatedItem>
    <abstract>Few-shot learning via in-context learning (ICL) is widely used in NLP, but its effectiveness is highly sensitive to example selection, often leading to unstable performance. To address this, we introduce BacKGen, a framework for generating structured Background Knowledge (BK) as an alternative to instance-based prompting. Our approach leverages Frame Semantics to uncover recurring conceptual patterns across data instances, clustering examples based on shared event structures and semantic roles. These patterns are then synthesized into generalized knowledge statements using a large language model (LLM) and injected into prompts to support contextual reasoning beyond surface-level cues. We apply BacKGen to Sentiment Phrase Classification (SPC), a task where polarity judgments frequently depend on implicit commonsense knowledge. In this setting, BK serves as an abstract representation of prototypical scenarios, enabling schematic generalization to help the model perform analogical reasoning by mapping new inputs onto generalized event structures. Experimental results with Mistral-7B and Llama3-8B demonstrate that BK-based prompting consistently outperforms standard few-shot approaches, achieving up to 29.94% error reduction.</abstract>
    <identifier type="citekey">ibrohim-etal-2025-modeling</identifier>
    <identifier type="doi">10.18653/v1/2025.analogyangle-1.3</identifier>
    <location>
        <url>https://aclanthology.org/2025.analogyangle-1.3/</url>
    </location>
    <part>
        <date>2025-08</date>
        <extent unit="page">
            <start>22</start>
            <end>36</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Modeling Background Knowledge with Frame Semantics for Fine-grained Sentiment Classification
%A Ibrohim, Muhammad Okky
%A Basile, Valerio
%A Croce, Danilo
%A Bosco, Cristina
%A Basili, Roberto
%Y Rambelli, Giulia
%Y Ilievski, Filip
%Y Bolognesi, Marianna
%Y Sommerauer, Pia
%S Proceedings of the 2nd Workshop on Analogical Abstraction in Cognition, Perception, and Language (Analogy-Angle II)
%D 2025
%8 August
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-274-9
%F ibrohim-etal-2025-modeling
%X Few-shot learning via in-context learning (ICL) is widely used in NLP, but its effectiveness is highly sensitive to example selection, often leading to unstable performance. To address this, we introduce BacKGen, a framework for generating structured Background Knowledge (BK) as an alternative to instance-based prompting. Our approach leverages Frame Semantics to uncover recurring conceptual patterns across data instances, clustering examples based on shared event structures and semantic roles. These patterns are then synthesized into generalized knowledge statements using a large language model (LLM) and injected into prompts to support contextual reasoning beyond surface-level cues. We apply BacKGen to Sentiment Phrase Classification (SPC), a task where polarity judgments frequently depend on implicit commonsense knowledge. In this setting, BK serves as an abstract representation of prototypical scenarios, enabling schematic generalization to help the model perform analogical reasoning by mapping new inputs onto generalized event structures. Experimental results with Mistral-7B and Llama3-8B demonstrate that BK-based prompting consistently outperforms standard few-shot approaches, achieving up to 29.94% error reduction.
%R 10.18653/v1/2025.analogyangle-1.3
%U https://aclanthology.org/2025.analogyangle-1.3/
%U https://doi.org/10.18653/v1/2025.analogyangle-1.3
%P 22-36

Markdown (Informal)

[Modeling Background Knowledge with Frame Semantics for Fine-grained Sentiment Classification](https://aclanthology.org/2025.analogyangle-1.3/) (Ibrohim et al., Analogy-Angle 2025)

• Modeling Background Knowledge with Frame Semantics for Fine-grained Sentiment Classification (Ibrohim et al., Analogy-Angle 2025)

ACL

• Muhammad Okky Ibrohim, Valerio Basile, Danilo Croce, Cristina Bosco, and Roberto Basili. 2025. Modeling Background Knowledge with Frame Semantics for Fine-grained Sentiment Classification. In Proceedings of the 2nd Workshop on Analogical Abstraction in Cognition, Perception, and Language (Analogy-Angle II), pages 22–36, Vienna, Austria. Association for Computational Linguistics.