Are Language-and-Vision Transformers Sensitive to Discourse? A Case Study of ViLBERT Ekaterina Voloshina author Nikolai Ilinykh author Simon Dobnik author 2023-09 text Proceedings of the Workshop on Multimodal, Multilingual Natural Language Generation and Multilingual WebNLG Challenge (MM-NLG 2023) Albert Gatt editor Claire Gardent editor Liam Cripwell editor Anya Belz editor Claudia Borg editor Aykut Erdem editor Erkut Erdem editor Association for Computational Linguistics Prague, Czech Republic conference publication voloshina-etal-2023-language https://aclanthology.org/2023.mmnlg-1.4/ 2023-09 28 38