FigCLIP: A Generative Multimodal Model with Bidirectional Cross-attention for Understanding Figurative Language via Visual Entailment

FigCLIP: A Generative Multimodal Model with Bidirectional Cross-attention for Understanding Figurative Language via Visual Entailment Qihao Yang author Xuelin Wang author 2024-06 text Proceedings of the 4th Workshop on Figurative Language Processing (FigLang 2024) Debanjan Ghosh editor Smaranda Muresan editor Anna Feldman editor Tuhin Chakrabarty editor Emmy Liu editor Association for Computational Linguistics Mexico City, Mexico (Hybrid) conference publication yang-wang-2024-figclip 10.18653/v1/2024.figlang-1.13 https://aclanthology.org/2024.figlang-1.13/ 2024-06 92 98