@inproceedings{huang-etal-2019-multi-modal,
    title = "Multi-modal Discriminative Model for Vision-and-Language Navigation",
    author = "Huang, Haoshuo  and
      Jain, Vihan  and
      Mehta, Harsh  and
      Baldridge, Jason  and
      Ie, Eugene",
    editor = "Bhatia, Archna  and
      Bisk, Yonatan  and
      Kordjamshidi, Parisa  and
      Thomason, Jesse",
    booktitle = "Proceedings of the Combined Workshop on Spatial Language Understanding ({S}p{LU}) and Grounded Communication for Robotics ({R}obo{NLP})",
    month = jun,
    year = "2019",
    address = "Minneapolis, Minnesota",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/W19-1605/",
    doi = "10.18653/v1/W19-1605",
    pages = "40--49"
}