@inproceedings{lee-etal-2021-constructing, title = "Constructing Multi-Modal Dialogue Dataset by Replacing Text with Semantically Relevant Images", author = "Lee, Nyoungwoo and Shin, Suwon and Choo, Jaegul and Choi, Ho-Jin and Myaeng, Sung-Hyon", editor = "Zong, Chengqing and Xia, Fei and Li, Wenjie and Navigli, Roberto", booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)", month = aug, year = "2021", address = "Online", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2021.acl-short.113/", doi = "10.18653/v1/2021.acl-short.113", pages = "897--906" }