<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yano-etal-2025-frameeol">
    <titleInfo>
        <title>FrameEOL: Semantic Frame Induction using Causal Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chihiro</namePart>
        <namePart type="family">Yano</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kosuke</namePart>
        <namePart type="family">Yamada</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hayato</namePart>
        <namePart type="family">Tsukagoshi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ryohei</namePart>
        <namePart type="family">Sasano</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Koichi</namePart>
        <namePart type="family">Takeda</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>Semantic frame induction is the task of clustering frame-evoking words according to the semantic frames they evoke. In recent years, leveraging embeddings of frame-evoking words that are obtained using masked language models (MLMs) such as BERT has led to high-performance semantic frame induction. Although causal language models (CLMs) such as the GPT and Llama series succeed in a wide range of language comprehension tasks and can engage in dialogue as if they understood frames, they have not yet been applied to semantic frame induction. We propose a new method for semantic frame induction based on CLMs. Specifically, we introduce FrameEOL, a prompt-based method for obtaining Frame Embeddings that outputs One frame-name as a Label representing the given situation. To obtain embeddings more suitable for frame induction, we leverage in-context learning (ICL) and deep metric learning (DML). Frame induction is then performed by clustering the resulting embeddings. Experimental results on the English and Japanese FrameNet datasets demonstrate that the proposed methods outperform existing frame induction methods. In particular, for Japanese, which lacks extensive frame resources, the CLM-based method using only 5 ICL examples achieved comparable performance to the MLM-based method fine-tuned with DML.</abstract>
    <identifier type="citekey">yano-etal-2025-frameeol</identifier>
    <identifier type="doi">10.18653/v1/2025.findings-emnlp.623</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-emnlp.623/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>11620</start>
            <end>11632</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T FrameEOL: Semantic Frame Induction using Causal Language Models
%A Yano, Chihiro
%A Yamada, Kosuke
%A Tsukagoshi, Hayato
%A Sasano, Ryohei
%A Takeda, Koichi
%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 yano-etal-2025-frameeol
%X Semantic frame induction is the task of clustering frame-evoking words according to the semantic frames they evoke. In recent years, leveraging embeddings of frame-evoking words that are obtained using masked language models (MLMs) such as BERT has led to high-performance semantic frame induction. Although causal language models (CLMs) such as the GPT and Llama series succeed in a wide range of language comprehension tasks and can engage in dialogue as if they understood frames, they have not yet been applied to semantic frame induction. We propose a new method for semantic frame induction based on CLMs. Specifically, we introduce FrameEOL, a prompt-based method for obtaining Frame Embeddings that outputs One frame-name as a Label representing the given situation. To obtain embeddings more suitable for frame induction, we leverage in-context learning (ICL) and deep metric learning (DML). Frame induction is then performed by clustering the resulting embeddings. Experimental results on the English and Japanese FrameNet datasets demonstrate that the proposed methods outperform existing frame induction methods. In particular, for Japanese, which lacks extensive frame resources, the CLM-based method using only 5 ICL examples achieved comparable performance to the MLM-based method fine-tuned with DML.
%R 10.18653/v1/2025.findings-emnlp.623
%U https://aclanthology.org/2025.findings-emnlp.623/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.623
%P 11620-11632

Markdown (Informal)

[FrameEOL: Semantic Frame Induction using Causal Language Models](https://aclanthology.org/2025.findings-emnlp.623/) (Yano et al., Findings 2025)

• FrameEOL: Semantic Frame Induction using Causal Language Models (Yano et al., Findings 2025)

ACL

• Chihiro Yano, Kosuke Yamada, Hayato Tsukagoshi, Ryohei Sasano, and Koichi Takeda. 2025. FrameEOL: Semantic Frame Induction using Causal Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 11620–11632, Suzhou, China. Association for Computational Linguistics.