@inproceedings{xu-etal-2024-exploring,
title = "Exploring Chain-of-Thought for Multi-modal Metaphor Detection",
author = "Xu, Yanzhi and
Hua, Yueying and
Li, Shichen and
Wang, Zhongqing",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.6",
doi = "10.18653/v1/2024.acl-long.6",
pages = "91--101",
abstract = "Metaphors are commonly found in advertising and internet memes. However, the free form of internet memes often leads to a lack of high-quality textual data. Metaphor detection demands a deep interpretation of both textual and visual elements, requiring extensive common-sense knowledge, which poses a challenge to language models. To address these challenges, we propose a compact framework called C4MMD, which utilizes a \textbf{C}hain-of-Thought(CoT) method \textbf{for} \textbf{M}ulti-modal \textbf{M}etaphor \textbf{D}etection. Specifically, our approach designs a three-step process inspired by CoT that extracts and integrates knowledge from Multi-modal Large Language Models(MLLMs) into smaller ones. We also developed a modality fusion architecture to transform knowledge from large models into metaphor features, supplemented by auxiliary tasks to improve model performance. Experimental results on the MET-MEME dataset demonstrate that our method not only effectively enhances the metaphor detection capabilities of small models but also outperforms existing models. To our knowledge, this is the first systematic study leveraging MLLMs in metaphor detection tasks. The code for our method is publicly available at \url{https://github.com/xyz189411yt/C4MMD}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2024-exploring">
<titleInfo>
<title>Exploring Chain-of-Thought for Multi-modal Metaphor Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yanzhi</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yueying</namePart>
<namePart type="family">Hua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shichen</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongqing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Metaphors are commonly found in advertising and internet memes. However, the free form of internet memes often leads to a lack of high-quality textual data. Metaphor detection demands a deep interpretation of both textual and visual elements, requiring extensive common-sense knowledge, which poses a challenge to language models. To address these challenges, we propose a compact framework called C4MMD, which utilizes a Chain-of-Thought(CoT) method for Multi-modal Metaphor Detection. Specifically, our approach designs a three-step process inspired by CoT that extracts and integrates knowledge from Multi-modal Large Language Models(MLLMs) into smaller ones. We also developed a modality fusion architecture to transform knowledge from large models into metaphor features, supplemented by auxiliary tasks to improve model performance. Experimental results on the MET-MEME dataset demonstrate that our method not only effectively enhances the metaphor detection capabilities of small models but also outperforms existing models. To our knowledge, this is the first systematic study leveraging MLLMs in metaphor detection tasks. The code for our method is publicly available at https://github.com/xyz189411yt/C4MMD.</abstract>
<identifier type="citekey">xu-etal-2024-exploring</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.6</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.6</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>91</start>
<end>101</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Chain-of-Thought for Multi-modal Metaphor Detection
%A Xu, Yanzhi
%A Hua, Yueying
%A Li, Shichen
%A Wang, Zhongqing
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F xu-etal-2024-exploring
%X Metaphors are commonly found in advertising and internet memes. However, the free form of internet memes often leads to a lack of high-quality textual data. Metaphor detection demands a deep interpretation of both textual and visual elements, requiring extensive common-sense knowledge, which poses a challenge to language models. To address these challenges, we propose a compact framework called C4MMD, which utilizes a Chain-of-Thought(CoT) method for Multi-modal Metaphor Detection. Specifically, our approach designs a three-step process inspired by CoT that extracts and integrates knowledge from Multi-modal Large Language Models(MLLMs) into smaller ones. We also developed a modality fusion architecture to transform knowledge from large models into metaphor features, supplemented by auxiliary tasks to improve model performance. Experimental results on the MET-MEME dataset demonstrate that our method not only effectively enhances the metaphor detection capabilities of small models but also outperforms existing models. To our knowledge, this is the first systematic study leveraging MLLMs in metaphor detection tasks. The code for our method is publicly available at https://github.com/xyz189411yt/C4MMD.
%R 10.18653/v1/2024.acl-long.6
%U https://aclanthology.org/2024.acl-long.6
%U https://doi.org/10.18653/v1/2024.acl-long.6
%P 91-101
Markdown (Informal)
[Exploring Chain-of-Thought for Multi-modal Metaphor Detection](https://aclanthology.org/2024.acl-long.6) (Xu et al., ACL 2024)
ACL
- Yanzhi Xu, Yueying Hua, Shichen Li, and Zhongqing Wang. 2024. Exploring Chain-of-Thought for Multi-modal Metaphor Detection. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 91–101, Bangkok, Thailand. Association for Computational Linguistics.