@InProceedings{shutova-wundsam-yannakoudakis:2017:starSEM,
  author    = {Shutova, Ekaterina  and  Wundsam, Andreas  and  Yannakoudakis, Helen},
  title     = {Semantic Frames and Visual Scenes: Learning Semantic Role Inventories from Image and Video Descriptions},
  booktitle = {Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017)},
  month     = {August},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {149--154},
  abstract  = {Frame-semantic parsing and semantic role labelling, that aim to automatically
	assign semantic roles to arguments of verbs in a sentence, have become an
	active strand of research in NLP. However, to date these methods have relied on
	a predefined inventory of semantic roles. In this paper, we present a method to
	automatically learn argument role inventories for verbs from large corpora of
	text, images and videos. We evaluate the method against manually constructed
	role inventories in FrameNet and show that the visual model outperforms the
	language-only model and operates with a high precision.},
  url       = {http://www.aclweb.org/anthology/S17-1018}
}