MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection System

Libo Qin, Shijue Huang, Qiguang Chen, Chenran Cai, Yudi Zhang +3 more
7/14/2023
cs.CL

No official code found. Best implementation: JoeYing1019/MMSD2.0 (62 stars, last commit 2024-01-02).

Abstract

Multi-modal sarcasm detection has attracted much recent attention. Nevertheless, the existing benchmark (MMSD) has some shortcomings that hinder the development of reliable multi-modal sarcasm detection system: (1) There are some spurious cues in MMSD, leading to the model bias learning; (2) The negative samples in MMSD are not always reasonable. To solve the aforementioned issues, we introduce MMSD2.0, a correction dataset that fixes the shortcomings of MMSD, by removing the spurious cues and re-annotating the unreasonable samples. Meanwhile, we present a novel framework called multi-view CLIP that is capable of leveraging multi-grained cues from multiple perspectives (i.e., text, image, and text-image interaction view) for multi-modal sarcasm detection. Extensive experiments show that MMSD2.0 is a valuable benchmark for building reliable multi-modal sarcasm detection systems and multi-view CLIP can significantly outperform the previous best baselines.

View on arXivView PDF

Code Implementations(1)

JoeYing1019/MMSD2.0Community100%

[ACL2023] Code and dataset for paper "MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection System"

6211Shell, PythonMay 12, 20232 years ago

Similar Papers

Dual Modality-Aware Gated Prompt Tuning for Few-Shot Multimodal Sarcasm Detection

91% match2025

A Survey of Multimodal Sarcasm Detection

88% match2024

InterCLIP-MEP: Interactive CLIP and Memory-Enhanced Predictor for Multi-modal Sarcasm Detection

88% match1 repo162024

DIP: Dual Incongruity Perceiving Network for Sarcasm Detection

88% match1 repo362023

Multi-View Incongruity Learning for Multimodal Sarcasm Detection

88% match2024

CofiPara: A Coarse-to-fine Paradigm for Multimodal Sarcasm Target Identification with Large Multimodal Models

88% match1 repo132024

Cite this paper

@article{qin2023mmsd,
  title  = {MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection System},
  author = {Libo Qin and Shijue Huang and Qiguang Chen and Chenran Cai and Yudi Zhang and Bin Liang and Wanxiang Che and Ruifeng Xu},
  year   = {2023},
  eprint = {2307.07135},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.07135v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.07135.svg)](https://codeofpaper.com/paper/2307.07135)

Discussion