@inproceedings{robbins-etal-2021-towards, title = "Towards Multimodal Vision-Language Models Generating Non-Generic Text", author = "Robbins, Wes and Zohourianshahzadi, Zanyar and Kalita, Jugal", editor = "Bandyopadhyay, Sivaji and Devi, Sobha Lalitha and Bhattacharyya, Pushpak", booktitle = "Proceedings of the 18th International Conference on Natural Language Processing (ICON)", month = dec, year = "2021", address = "National Institute of Technology Silchar, Silchar, India", publisher = "NLP Association of India (NLPAI)", url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2021.icon-main.27/", pages = "220--230" }