Classification of Multimodal Hate Speech -- The Winning Solution of Hateful Memes Challenge

Understand

Hateful Memes is a new challenge set for multimodal classification, focusing on detecting hate speech in multimodal memes.

• Difficult examples are added to the dataset to make it hard to rely on unimodal signals, which means only multimodal models can succeed.
• According to Kiela,the state-of-the-art methods perform poorly compared to humans (64.73% vs.
• 84.7% accuracy) on Hateful Memes.