How Vision Affects Language: Comparing Masked Self-Attention in Uni-Modal and Multi-Modal Transformer

How Vision Affects Language: Comparing Masked Self-Attention in Uni-Modal and Multi-Modal Transformer Nikolai Ilinykh author Simon Dobnik author 2021-06 text Proceedings of the 1st Workshop on Multimodal Semantic Representations (MMSR) Lucia Donatelli editor Nikhil Krishnaswamy editor Kenneth Lai editor James Pustejovsky editor Association for Computational Linguistics Groningen, Netherlands (Online) conference publication ilinykh-dobnik-2021-vision https://aclanthology.org/2021.mmsr-1.5/ 2021-06 45 55