@inproceedings{testoni-etal-2019-quantifiers,
    title = "Quantifiers in a Multimodal World: Hallucinating Vision with Language and Sound",
    author = "Testoni, Alberto  and
      Pezzelle, Sandro  and
      Bernardi, Raffaella",
    editor = "Chersoni, Emmanuele  and
      Jacobs, Cassandra  and
      Lenci, Alessandro  and
      Linzen, Tal  and
      Pr{\'e}vot, Laurent  and
      Santus, Enrico",
    booktitle = "Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics",
    month = jun,
    year = "2019",
    address = "Minneapolis, Minnesota",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/W19-2912/",
    doi = "10.18653/v1/W19-2912",
    pages = "105--116",
    abstract = "Inspired by the literature on multisensory integration, we develop a computational model to ground quantifiers in perception. The model learns to pick, out of nine quantifiers ({`}few', `many', `all', etc.), the one that is more likely to describe the percent of animals in a visual-auditory input containing both animals and artifacts. We show that relying on concurrent sensory inputs increases model performance on the quantification task. Moreover, we evaluate the model in a situation in which only the auditory modality is given, while the visual one is `hallucinanted' either from the auditory input itself or from a linguistic caption describing the quantity of entities in the auditory input. This way, the model exploits prior associations between modalities. We show that the model profits from the prior knowledge and outperforms the auditory-only setting."
}