MemeMQA: Multimodal Question Answering for Memes via Rationale-Based Inferencing

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Agarwal, Siddhant, Sharma, Shivam, Nakov, Preslav, Chakraborty, Tanmoy
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916251345879040
author Agarwal, Siddhant
Sharma, Shivam
Nakov, Preslav
Chakraborty, Tanmoy
author_facet Agarwal, Siddhant
Sharma, Shivam
Nakov, Preslav
Chakraborty, Tanmoy
contents Memes have evolved as a prevalent medium for diverse communication, ranging from humour to propaganda. With the rising popularity of image-focused content, there is a growing need to explore its potential harm from different aspects. Previous studies have analyzed memes in closed settings - detecting harm, applying semantic labels, and offering natural language explanations. To extend this research, we introduce MemeMQA, a multimodal question-answering framework aiming to solicit accurate responses to structured questions while providing coherent explanations. We curate MemeMQACorpus, a new dataset featuring 1,880 questions related to 1,122 memes with corresponding answer-explanation pairs. We further propose ARSENAL, a novel two-stage multimodal framework that leverages the reasoning capabilities of LLMs to address MemeMQA. We benchmark MemeMQA using competitive baselines and demonstrate its superiority - ~18% enhanced answer prediction accuracy and distinct text generation lead across various metrics measuring lexical and semantic alignment over the best baseline. We analyze ARSENAL's robustness through diversification of question-set, confounder-based evaluation regarding MemeMQA's generalizability, and modality-specific assessment, enhancing our understanding of meme interpretation in the multimodal communication landscape.
format Preprint
id arxiv_https___arxiv_org_abs_2405_11215
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MemeMQA: Multimodal Question Answering for Memes via Rationale-Based Inferencing
Agarwal, Siddhant
Sharma, Shivam
Nakov, Preslav
Chakraborty, Tanmoy
Computation and Language
Computers and Society
Memes have evolved as a prevalent medium for diverse communication, ranging from humour to propaganda. With the rising popularity of image-focused content, there is a growing need to explore its potential harm from different aspects. Previous studies have analyzed memes in closed settings - detecting harm, applying semantic labels, and offering natural language explanations. To extend this research, we introduce MemeMQA, a multimodal question-answering framework aiming to solicit accurate responses to structured questions while providing coherent explanations. We curate MemeMQACorpus, a new dataset featuring 1,880 questions related to 1,122 memes with corresponding answer-explanation pairs. We further propose ARSENAL, a novel two-stage multimodal framework that leverages the reasoning capabilities of LLMs to address MemeMQA. We benchmark MemeMQA using competitive baselines and demonstrate its superiority - ~18% enhanced answer prediction accuracy and distinct text generation lead across various metrics measuring lexical and semantic alignment over the best baseline. We analyze ARSENAL's robustness through diversification of question-set, confounder-based evaluation regarding MemeMQA's generalizability, and modality-specific assessment, enhancing our understanding of meme interpretation in the multimodal communication landscape.
title MemeMQA: Multimodal Question Answering for Memes via Rationale-Based Inferencing
topic Computation and Language
Computers and Society
url https://arxiv.org/abs/2405.11215