Augmenters at SemEval-2023 Task 1: Enhancing CLIP in Handling Compositionality and Ambiguity for Zero-Shot Visual WSD through Prompt Augmentation and Text-To-Image Diffusion

24964

Knowledge Triples

Source Entity	Relationship	Target Entity
Augment CLIP Method	enhances	CLIP Method
Augment CLIP Method	uses	Large Language Models Method
CLIP Method	appliesTo	Visual Word Sense Disambiguation Task
Stable Diffusion Sampling Method	uses	CLIP Method