@inproceedings{suhr-etal-2017-corpus,
    title = "A Corpus of Natural Language for Visual Reasoning",
    author = "Suhr, Alane  and
      Lewis, Mike  and
      Yeh, James  and
      Artzi, Yoav",
    editor = "Barzilay, Regina  and
      Kan, Min-Yen",
    booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = jul,
    year = "2017",
    address = "Vancouver, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/P17-2034/",
    doi = "10.18653/v1/P17-2034",
    pages = "217--223",
    abstract = "We present a new visual reasoning language dataset, containing 92,244 pairs of examples of natural statements grounded in synthetic images with 3,962 unique sentences. We describe a method of crowdsourcing linguistically-diverse data, and present an analysis of our data. The data demonstrates a broad set of linguistic phenomena, requiring visual and set-theoretic reasoning. We experiment with various models, and show the data presents a strong challenge for future research."
}