While the unimodal-text context-aware (transformer) model was the most accurate on the subtask of implicit hate detection, the multimodal model outperformed it overall because of a lower propensity towards false positives. We find that all models perform better on content with full annotator agreement and that multimodal models are best at classifying the content where annotators disagree. https://aclanthology.org/2021.findings-acl.166/ Share this: Click to share on Facebook (Opens in new window) Facebook Click to share on X (Opens in new window) X Like this:Like Loading... Post navigation Deep learning based fusion strategies for hate speech detection to combine the classifiers to improve classification performance (AIP Conference Procedingsw) Free Resources on Countering Extremism and Hate Speech, September 2023 (I/II)