MERMAID: A dataset and framework for multimodal meme semantic understanding

Memes are widely used to convey cultural and societal issues and have a significant impact on public opinion. However, little work has been done on understanding and explaining the semantics expressed in multimodal memes. To fill this research gap, we introduce MERMAID, a dataset consisting of 3,633...

Full description

Saved in:
Bibliographic Details
Main Authors: TOH, Shaun, KUEK, Adriel, CHONG, Wen Haw, LEE, Roy Ka Wei
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2023
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/8746
https://ink.library.smu.edu.sg/context/sis_research/article/9749/viewcontent/MERMAID_av.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-9749
record_format dspace
spelling sg-smu-ink.sis_research-97492024-05-03T07:48:16Z MERMAID: A dataset and framework for multimodal meme semantic understanding TOH, Shaun KUEK, Adriel CHONG, Wen Haw LEE, Roy Ka Wei Memes are widely used to convey cultural and societal issues and have a significant impact on public opinion. However, little work has been done on understanding and explaining the semantics expressed in multimodal memes. To fill this research gap, we introduce MERMAID, a dataset consisting of 3,633 memes annotated with their entities and relations, and propose a novel MERF pipeline that extracts entities and their relationships in memes. Our framework combines state-of-the-art techniques from natural language processing and computer vision to extract text and image features and infer relationships between entities in memes. We evaluate the proposed framework on a real-world meme dataset and establish the benchmark for the new multimodal meme semantic understanding task. Our evaluation also includes a low-resource setting, where we assess the applicability of our framework to low-resource settings, which is a common problem due to the high cost and lack of labeled data for relations in memes. Overall, our work contributes to the understanding of the semantics of memes, a crucial form of communication in today's society. 2023-12-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8746 info:doi/10.1109/BigData59044.2023.10386279 https://ink.library.smu.edu.sg/context/sis_research/article/9749/viewcontent/MERMAID_av.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Memes Multimodal Semantic Extraction Databases and Information Systems Graphics and Human Computer Interfaces Mental and Social Health
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Memes
Multimodal
Semantic Extraction
Databases and Information Systems
Graphics and Human Computer Interfaces
Mental and Social Health
spellingShingle Memes
Multimodal
Semantic Extraction
Databases and Information Systems
Graphics and Human Computer Interfaces
Mental and Social Health
TOH, Shaun
KUEK, Adriel
CHONG, Wen Haw
LEE, Roy Ka Wei
MERMAID: A dataset and framework for multimodal meme semantic understanding
description Memes are widely used to convey cultural and societal issues and have a significant impact on public opinion. However, little work has been done on understanding and explaining the semantics expressed in multimodal memes. To fill this research gap, we introduce MERMAID, a dataset consisting of 3,633 memes annotated with their entities and relations, and propose a novel MERF pipeline that extracts entities and their relationships in memes. Our framework combines state-of-the-art techniques from natural language processing and computer vision to extract text and image features and infer relationships between entities in memes. We evaluate the proposed framework on a real-world meme dataset and establish the benchmark for the new multimodal meme semantic understanding task. Our evaluation also includes a low-resource setting, where we assess the applicability of our framework to low-resource settings, which is a common problem due to the high cost and lack of labeled data for relations in memes. Overall, our work contributes to the understanding of the semantics of memes, a crucial form of communication in today's society.
format text
author TOH, Shaun
KUEK, Adriel
CHONG, Wen Haw
LEE, Roy Ka Wei
author_facet TOH, Shaun
KUEK, Adriel
CHONG, Wen Haw
LEE, Roy Ka Wei
author_sort TOH, Shaun
title MERMAID: A dataset and framework for multimodal meme semantic understanding
title_short MERMAID: A dataset and framework for multimodal meme semantic understanding
title_full MERMAID: A dataset and framework for multimodal meme semantic understanding
title_fullStr MERMAID: A dataset and framework for multimodal meme semantic understanding
title_full_unstemmed MERMAID: A dataset and framework for multimodal meme semantic understanding
title_sort mermaid: a dataset and framework for multimodal meme semantic understanding
publisher Institutional Knowledge at Singapore Management University
publishDate 2023
url https://ink.library.smu.edu.sg/sis_research/8746
https://ink.library.smu.edu.sg/context/sis_research/article/9749/viewcontent/MERMAID_av.pdf
_version_ 1814047500327190528