Detecting Hate Speech in Memes Using Multimodal Deep Learning Approaches: Prize-winning solution to Hateful Memes Challenge

Abstract

Memes on the Internet are often harmless and sometimes amusing. However, by using certain types of images, text, or combinations of both, the seemingly harmless meme becomes a multimodal type of hate speech -- a hateful meme. The Hateful Memes Challenge is a first-of-its-kind competition which focuses on detecting hate speech in multimodal memes and it proposes a new data set containing 10,000+ new examples of multimodal content. We utilize VisualBERT -- which meant to be the BERT of vision and language -- that was trained multimodally on images and captions and apply Ensemble Learning. Our approach achieves 0.811 AUROC with an accuracy of 0.765 on the challenge test set and placed third out of 3,173 participants in the Hateful Memes Challenge.

Presented at NeurIPS (2020)

References in corpus (5)

• Microsoft COCO Captions: Data Collection and Evaluation Server
• VisualBERT: A Simple and Performant Baseline for Vision and Language
• Learning the Difference that Makes a Difference with Counterfactually-Augmented Data
• The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes
• Multiresolution and Multimodal Speech Recognition with Transformers

Cited by in corpus (8)

• Disentangling Hate in Online Memes
• SoK: Content Moderation in Social Media, from Guidelines to Enforcement, and Research to Practice
• An Ensemble Model with Attention Based Mechanism for Image Captioning
• Toxic Memes: A Survey of Computational Perspectives on the Detection and Explanation of Meme Toxicities
• HateProof: Are Hateful Meme Detection Systems really Robust?
• Towards A Multi-agent System for Online Hate Speech Detection
• AOMD: An Analogy-aware Approach to Offensive Meme Detection on Social Media
• MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets