MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection System
This work addresses the need for more reliable sarcasm detection in multi-modal contexts, though it is incremental as it builds upon an existing benchmark.
The authors tackled the problem of unreliable multi-modal sarcasm detection by introducing MMSD2.0, a corrected dataset that removes spurious cues and re-annotates unreasonable samples, and a multi-view CLIP framework that leverages multi-grained cues, resulting in significant performance improvements over previous baselines.
Multi-modal sarcasm detection has attracted much recent attention. Nevertheless, the existing benchmark (MMSD) has some shortcomings that hinder the development of reliable multi-modal sarcasm detection system: (1) There are some spurious cues in MMSD, leading to the model bias learning; (2) The negative samples in MMSD are not always reasonable. To solve the aforementioned issues, we introduce MMSD2.0, a correction dataset that fixes the shortcomings of MMSD, by removing the spurious cues and re-annotating the unreasonable samples. Meanwhile, we present a novel framework called multi-view CLIP that is capable of leveraging multi-grained cues from multiple perspectives (i.e., text, image, and text-image interaction view) for multi-modal sarcasm detection. Extensive experiments show that MMSD2.0 is a valuable benchmark for building reliable multi-modal sarcasm detection systems and multi-view CLIP can significantly outperform the previous best baselines.