Automatic Depiction of Spatial Descriptions

Abstract

A novel combination of ideas from cognitive linguis-tics and spatial occupancy models in robotics has led to the WIP (Words Into Pictures) system. WIP au-tomatically generates depictions of natural language descriptions of indoor scenes. A qualitative layer in the conceptual representation of objects underlies a mechanism by which alternative depictions arise for qualitatively distinct interpretations, as often occurs as a result of deictic/intrinsic reference frame ambigu-ity. At the same time, a quantitative layer, in conjunc-tion with a potential field model of the semantics of projective prepositions, is used in the process of cap-turing the inherently fuzzy character of the meaning of natural language spatial predications.

Cite

Text

Olivier et al. "Automatic Depiction of Spatial Descriptions." AAAI Conference on Artificial Intelligence, 1994.

Markdown

[Olivier et al. "Automatic Depiction of Spatial Descriptions." AAAI Conference on Artificial Intelligence, 1994.](https://mlanthology.org/aaai/1994/olivier1994aaai-automatic/)

BibTeX

@inproceedings{olivier1994aaai-automatic,
  title     = {{Automatic Depiction of Spatial Descriptions}},
  author    = {Olivier, Patrick and Maeda, Toshiyuki and Tsujii, Jun'ichi},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {1994},
  pages     = {1405-1410},
  url       = {https://mlanthology.org/aaai/1994/olivier1994aaai-automatic/}
}