@inproceedings{le-etal-2021-dvd,
    title = "{DVD}: A Diagnostic Dataset for Multi-step Reasoning in Video Grounded Dialogue",
    author = "Le, Hung  and
      Sankar, Chinnadhurai  and
      Moon, Seungwhan  and
      Beirami, Ahmad  and
      Geramifard, Alborz  and
      Kottur, Satwik",
    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 1: Long Papers)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2021.acl-long.439/",
    doi = "10.18653/v1/2021.acl-long.439",
    pages = "5651--5665"
}