[go: up one dir, main page]
Search
 
loader loading subjects...
cover
Multi-Modal Sarcasm Detection via Cross-Modal Attention Mechanism
Yueying Li, Hui Cao, Xiaotian Xia, Quan Song
548 - 554
10.3233/FAIA230853
Research Article
Frontiers in Artificial Intelligence and Applications
Volume 373: Advances in Artificial Intelligence, Big Data and Algorithms
Abstract

With the popularity of social media, the sarcasm figure of speech has become a common phenomenon on social media platforms, and many studies have utilized text and visual information for multimodal sarcasm detection. This paper use a method based on cross modal attention mechanism. Specifically, the paper extract multimodal features firstly, use attention mechanism to focus on the inconsistent information between modalities, and then use the inconsistent information for prediction. The experimental results show that the performance of this paper is improved on the Twitters sarcasm dataset.

Download
Creative Commons License