@inproceedings{lee-etal-2020-vilbertscore,
    title = "{V}i{LBERTS}core: Evaluating Image Caption Using Vision-and-Language {BERT}",
    author = "Lee, Hwanhee  and
      Yoon, Seunghyun  and
      Dernoncourt, Franck  and
      Kim, Doo Soon  and
      Bui, Trung  and
      Jung, Kyomin",
    editor = "Eger, Steffen  and
      Gao, Yang  and
      Peyrard, Maxime  and
      Zhao, Wei  and
      Hovy, Eduard",
    booktitle = "Proceedings of the First Workshop on Evaluation and Comparison of NLP Systems",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.eval4nlp-1.4/",
    doi = "10.18653/v1/2020.eval4nlp-1.4",
    pages = "34--39"
}