Classification of Multimodal Hate Speech – The Winning Solution of Hateful Memes Challenge
share
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 I propose a new model that combined multimodal with rules, which achieve the first ranking of accuracy and AUROC of 86.8 rules are extracted from training set, and focus on improving the classification accuracy of difficult samples.
READ FULL TEXT