ML Anthology

Complementing Semantic Roles with Temporally Anchored Spatial Knowledge: Crowdsourced Annotations and Experiments

Alakananda Vempala, Eduardo Blanco
AAAI 2016 pp. 2652-2658
doi:10.1609/AAAI.V30I1.10331 /aaai/2016/vempala2016aaai-complementing/

Abstract

This paper presents a framework to infer spatial knowledge from semantic role representations. We infer whether entities are or are not located somewhere, and temporally anchor this spatial information. A large crowdsourcing effort on top of OntoNotes shows that these temporally-anchored spatial inferences are ubiquitous and intuitive to humans. Experimental results show that inferences can be performed automatically and semantic features bring significant improvement.

PDF AAAI Semantic Scholar

Cite

Text

Vempala and Blanco. "Complementing Semantic Roles with Temporally Anchored Spatial Knowledge: Crowdsourced Annotations and Experiments." AAAI Conference on Artificial Intelligence, 2016. doi:10.1609/AAAI.V30I1.10331

Markdown

[Vempala and Blanco. "Complementing Semantic Roles with Temporally Anchored Spatial Knowledge: Crowdsourced Annotations and Experiments." AAAI Conference on Artificial Intelligence, 2016.](https://mlanthology.org/aaai/2016/vempala2016aaai-complementing/) doi:10.1609/AAAI.V30I1.10331

BibTeX

@inproceedings{vempala2016aaai-complementing,
  title     = {{Complementing Semantic Roles with Temporally Anchored Spatial Knowledge: Crowdsourced Annotations and Experiments}},
  author    = {Vempala, Alakananda and Blanco, Eduardo},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2016},
  pages     = {2652-2658},
  doi       = {10.1609/AAAI.V30I1.10331},
  url       = {https://mlanthology.org/aaai/2016/vempala2016aaai-complementing/}
}