TextMI: Textualize Multimodal Information for Integrating Non-verbal Cues in Pre-trained Language Models

no code implementations • 27 Mar 2023 • Md Kamrul Hasan, Md Saiful Islam, Sangwu Lee, Wasifur Rahman, Iftekhar Naim, Mohammed Ibrahim Khan, Ehsan Hoque

Our approach, TextMI, significantly reduces model complexity, adds interpretability to the model's decision, and can be applied for a diverse set of tasks while achieving superior (multimodal sarcasm detection) or near SOTA (multimodal sentiment analysis and multimodal humor detection) performance.

Humor Detection Multimodal Sentiment Analysis +1