@inproceedings{yang-etal-2025-cultural,
title = "Cultural Bias Matters: A Cross-Cultural Benchmark Dataset and Sentiment-Enriched Model for Understanding Multimodal Metaphors",
author = "Yang, Senqi and
Zhang, Dongyu and
Ren, Jing and
Xu, Ziqi and
Zhang, Xiuzhen and
Song, Yiliao and
Lin, Hongfei and
Xia, Feng",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1275/",
doi = "10.18653/v1/2025.acl-long.1275",
pages = "26301--26317",
ISBN = "979-8-89176-251-0",
abstract = "Metaphors are pervasive in communication, making them crucial for natural language processing (NLP). Previous research on automatic metaphor processing predominantly relies on training data consisting of English samples, which often reflect Western European or North American biases. This cultural skew can lead to an overestimation of model performance and contributions to NLP progress. However, the impact of cultural bias on metaphor processing, particularly in multimodal contexts, remains largely unexplored. To address this gap, we introduce MultiMM, a Multicultural Multimodal Metaphor dataset designed for cross-cultural studies of metaphor in Chinese and English. MultiMM consists of 8,461 text-image advertisement pairs, each accompanied by fine-grained annotations, providing a deeper understanding of multimodal metaphors beyond a single cultural domain. Additionally, we propose Sentiment-Enriched Metaphor Detection (SEMD), a baseline model that integrates sentiment embeddings to enhance metaphor comprehension across cultural backgrounds. Experimental results validate the effectiveness of SEMD on metaphor detection and sentiment analysis tasks. We hope this work increases awareness of cultural bias in NLP research and contributes to the development of fairer and more inclusive language models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2025-cultural">
<titleInfo>
<title>Cultural Bias Matters: A Cross-Cultural Benchmark Dataset and Sentiment-Enriched Model for Understanding Multimodal Metaphors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Senqi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziqi</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiuzhen</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiliao</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongfei</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feng</namePart>
<namePart type="family">Xia</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 1: Long 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">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Metaphors are pervasive in communication, making them crucial for natural language processing (NLP). Previous research on automatic metaphor processing predominantly relies on training data consisting of English samples, which often reflect Western European or North American biases. This cultural skew can lead to an overestimation of model performance and contributions to NLP progress. However, the impact of cultural bias on metaphor processing, particularly in multimodal contexts, remains largely unexplored. To address this gap, we introduce MultiMM, a Multicultural Multimodal Metaphor dataset designed for cross-cultural studies of metaphor in Chinese and English. MultiMM consists of 8,461 text-image advertisement pairs, each accompanied by fine-grained annotations, providing a deeper understanding of multimodal metaphors beyond a single cultural domain. Additionally, we propose Sentiment-Enriched Metaphor Detection (SEMD), a baseline model that integrates sentiment embeddings to enhance metaphor comprehension across cultural backgrounds. Experimental results validate the effectiveness of SEMD on metaphor detection and sentiment analysis tasks. We hope this work increases awareness of cultural bias in NLP research and contributes to the development of fairer and more inclusive language models.</abstract>
<identifier type="citekey">yang-etal-2025-cultural</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1275</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1275/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>26301</start>
<end>26317</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cultural Bias Matters: A Cross-Cultural Benchmark Dataset and Sentiment-Enriched Model for Understanding Multimodal Metaphors
%A Yang, Senqi
%A Zhang, Dongyu
%A Ren, Jing
%A Xu, Ziqi
%A Zhang, Xiuzhen
%A Song, Yiliao
%A Lin, Hongfei
%A Xia, Feng
%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 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F yang-etal-2025-cultural
%X Metaphors are pervasive in communication, making them crucial for natural language processing (NLP). Previous research on automatic metaphor processing predominantly relies on training data consisting of English samples, which often reflect Western European or North American biases. This cultural skew can lead to an overestimation of model performance and contributions to NLP progress. However, the impact of cultural bias on metaphor processing, particularly in multimodal contexts, remains largely unexplored. To address this gap, we introduce MultiMM, a Multicultural Multimodal Metaphor dataset designed for cross-cultural studies of metaphor in Chinese and English. MultiMM consists of 8,461 text-image advertisement pairs, each accompanied by fine-grained annotations, providing a deeper understanding of multimodal metaphors beyond a single cultural domain. Additionally, we propose Sentiment-Enriched Metaphor Detection (SEMD), a baseline model that integrates sentiment embeddings to enhance metaphor comprehension across cultural backgrounds. Experimental results validate the effectiveness of SEMD on metaphor detection and sentiment analysis tasks. We hope this work increases awareness of cultural bias in NLP research and contributes to the development of fairer and more inclusive language models.
%R 10.18653/v1/2025.acl-long.1275
%U https://aclanthology.org/2025.acl-long.1275/
%U https://doi.org/10.18653/v1/2025.acl-long.1275
%P 26301-26317
Markdown (Informal)
[Cultural Bias Matters: A Cross-Cultural Benchmark Dataset and Sentiment-Enriched Model for Understanding Multimodal Metaphors](https://aclanthology.org/2025.acl-long.1275/) (Yang et al., ACL 2025)
ACL
- Senqi Yang, Dongyu Zhang, Jing Ren, Ziqi Xu, Xiuzhen Zhang, Yiliao Song, Hongfei Lin, and Feng Xia. 2025. Cultural Bias Matters: A Cross-Cultural Benchmark Dataset and Sentiment-Enriched Model for Understanding Multimodal Metaphors. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 26301–26317, Vienna, Austria. Association for Computational Linguistics.