@inproceedings{kitaev-klein-2017-misty,
    title = "Where is Misty? Interpreting Spatial Descriptors by Modeling Regions in Space",
    author = "Kitaev, Nikita  and
      Klein, Dan",
    editor = "Palmer, Martha  and
      Hwa, Rebecca  and
      Riedel, Sebastian",
    booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",
    month = sep,
    year = "2017",
    address = "Copenhagen, Denmark",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest_wac_2008/D17-1015/",
    doi = "10.18653/v1/D17-1015",
    pages = "157--166",
    abstract = "We present a model for locating regions in space based on natural language descriptions. Starting with a 3D scene and a sentence, our model is able to associate words in the sentence with regions in the scene, interpret relations such as {\textquoteleft}on top of' or {\textquoteleft}next to,' and finally locate the region described in the sentence. All components form a single neural network that is trained end-to-end without prior knowledge of object segmentation. To evaluate our model, we construct and release a new dataset consisting of Minecraft scenes with crowdsourced natural language descriptions. We achieve a 32{\%} relative error reduction compared to a strong neural baseline."
}