@inproceedings{lugli-strapparava-2024-multimodal,
title = "Multimodal Chain-of-Thought Prompting for Metaphor Generation",
author = "Lugli, Sofia and
Strapparava, Carlo",
editor = "Dell'Orletta, Felice and
Lenci, Alessandro and
Montemagni, Simonetta and
Sprugnoli, Rachele",
booktitle = "Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)",
month = dec,
year = "2024",
address = "Pisa, Italy",
publisher = "CEUR Workshop Proceedings",
url = "https://aclanthology.org/2024.clicit-1.62/",
pages = "523--530",
ISBN = "979-12-210-7060-6",
abstract = "This paper introduces an exploratory approach in the field of metaphorical and visual reasoning by proposing the Multimodal Chain-of-Thought Prompting for Metaphor Generation task aimed to generate metaphorical linguistic expressions from non-metaphorical images by using the multimodal LLaVA 1.5 model and the two-step approach of multimodal chain-of- thought prompting. The generated metaphors were evaluated in two ways: using BERTscore and by five human workers on Amazon Mechanical Turk. Concerning the automatic evaluation, each generated metaphorical expression was paired with a corresponding human metaphorical expressions. The overall BERTscore was the following: precision= 0.41, recall= 0.43, and F1= 0.42, suggesting that generated and human metaphors might not have captured the same semantic meaning. The human evaluation showed the model`s ability to generate metaphorical expressions, as 92{\%} of them were classified as metaphors by the majority of the workers. Additionally, the evaluation revealed interesting patterns in terms of metaphoricity, familiarity and appeal scores across the generated metaphors: as the metaphoricity and appeal scores increased, the familiarity score decreased, suggesting that the model exhibited a certain degree of creativity, as it has also generated novel or unconventional metaphorical expressions. It is important to acknowledge that this work is exploratory in nature and has certain limitations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lugli-strapparava-2024-multimodal">
<titleInfo>
<title>Multimodal Chain-of-Thought Prompting for Metaphor Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sofia</namePart>
<namePart type="family">Lugli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlo</namePart>
<namePart type="family">Strapparava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Felice</namePart>
<namePart type="family">Dell’Orletta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simonetta</namePart>
<namePart type="family">Montemagni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>CEUR Workshop Proceedings</publisher>
<place>
<placeTerm type="text">Pisa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-12-210-7060-6</identifier>
</relatedItem>
<abstract>This paper introduces an exploratory approach in the field of metaphorical and visual reasoning by proposing the Multimodal Chain-of-Thought Prompting for Metaphor Generation task aimed to generate metaphorical linguistic expressions from non-metaphorical images by using the multimodal LLaVA 1.5 model and the two-step approach of multimodal chain-of- thought prompting. The generated metaphors were evaluated in two ways: using BERTscore and by five human workers on Amazon Mechanical Turk. Concerning the automatic evaluation, each generated metaphorical expression was paired with a corresponding human metaphorical expressions. The overall BERTscore was the following: precision= 0.41, recall= 0.43, and F1= 0.42, suggesting that generated and human metaphors might not have captured the same semantic meaning. The human evaluation showed the model‘s ability to generate metaphorical expressions, as 92% of them were classified as metaphors by the majority of the workers. Additionally, the evaluation revealed interesting patterns in terms of metaphoricity, familiarity and appeal scores across the generated metaphors: as the metaphoricity and appeal scores increased, the familiarity score decreased, suggesting that the model exhibited a certain degree of creativity, as it has also generated novel or unconventional metaphorical expressions. It is important to acknowledge that this work is exploratory in nature and has certain limitations.</abstract>
<identifier type="citekey">lugli-strapparava-2024-multimodal</identifier>
<location>
<url>https://aclanthology.org/2024.clicit-1.62/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>523</start>
<end>530</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multimodal Chain-of-Thought Prompting for Metaphor Generation
%A Lugli, Sofia
%A Strapparava, Carlo
%Y Dell’Orletta, Felice
%Y Lenci, Alessandro
%Y Montemagni, Simonetta
%Y Sprugnoli, Rachele
%S Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)
%D 2024
%8 December
%I CEUR Workshop Proceedings
%C Pisa, Italy
%@ 979-12-210-7060-6
%F lugli-strapparava-2024-multimodal
%X This paper introduces an exploratory approach in the field of metaphorical and visual reasoning by proposing the Multimodal Chain-of-Thought Prompting for Metaphor Generation task aimed to generate metaphorical linguistic expressions from non-metaphorical images by using the multimodal LLaVA 1.5 model and the two-step approach of multimodal chain-of- thought prompting. The generated metaphors were evaluated in two ways: using BERTscore and by five human workers on Amazon Mechanical Turk. Concerning the automatic evaluation, each generated metaphorical expression was paired with a corresponding human metaphorical expressions. The overall BERTscore was the following: precision= 0.41, recall= 0.43, and F1= 0.42, suggesting that generated and human metaphors might not have captured the same semantic meaning. The human evaluation showed the model‘s ability to generate metaphorical expressions, as 92% of them were classified as metaphors by the majority of the workers. Additionally, the evaluation revealed interesting patterns in terms of metaphoricity, familiarity and appeal scores across the generated metaphors: as the metaphoricity and appeal scores increased, the familiarity score decreased, suggesting that the model exhibited a certain degree of creativity, as it has also generated novel or unconventional metaphorical expressions. It is important to acknowledge that this work is exploratory in nature and has certain limitations.
%U https://aclanthology.org/2024.clicit-1.62/
%P 523-530
Markdown (Informal)
[Multimodal Chain-of-Thought Prompting for Metaphor Generation](https://aclanthology.org/2024.clicit-1.62/) (Lugli & Strapparava, CLiC-it 2024)
ACL