@inproceedings{f10e3c49b87b45878a6f920e4708b6b8,
title = "Visually guided spatial relation extraction from text",
abstract = "Extraction of spatial relations from sentences with complex/nesting relationships is very challenging as often needs resolving inherent semantic ambiguities. We seek help from visual modality to fill the information gap in the text modality and resolve spatial semantic ambiguities. We use various recent vision and language datasets and techniques to train inter-modality alignment models, visual relationship classifiers and propose a novel global inference model to integrate these components into our structured output prediction model for spatial role and relation extraction. Our global inference model enables us to utilize the visual and geometric relationships between objects and improves the state-of-art results of spatial information extraction from text.",
author = "Taher Rahgooy and Umar Manzoor and Parisa Kordjamshidi",
year = "2018",
month = jun,
doi = "10.18653/v1/N18-2",
language = "English",
series = "NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",
pages = "788--794",
booktitle = "Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2, Short Papers",
address = "United States",
note = "2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018 ; Conference date: 01-06-2018 Through 06-06-2018",
}