@inproceedings{mazuecos-etal-2021-impact,
    title = "The Impact of Answers in Referential Visual Dialog",
    author = "Mazuecos, Mauricio  and
      Blackburn, Patrick  and
      Benotti, Luciana",
    editor = "Howes, Christine  and
      Dobnik, Simon  and
      Breitholtz, Ellen  and
      Chatzikyriakidis, Stergios",
    booktitle = "Proceedings of the Reasoning and Interaction Conference (ReInAct 2021)",
    month = oct,
    year = "2021",
    address = "Gothenburg, Sweden",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.reinact-1.2",
    pages = "8--13",
    abstract = "In the visual dialog task GuessWhat?! two players maintain a dialog in order to identify a secret object in an image. Computationally, this is modeled using a question generation module and a guesser module for the questioner role and an answering model, the Oracle, to answer the generated questions. This raises a question: what{'}s the risk of having an imperfect oracle model?. Here we present work in progress in the study of the impact of different answering models in human generated questions in GuessWhat?!. We show that having access to better quality answers has a direct impact on the guessing task for human dialog and argue that better answers could help train better question generation models.",
}