Basic meanings of spatial relations: computation and evaluation in 3D space
AAAI'94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 2)
From imagery to salience: locative expressions in context
From imagery to salience: locative expressions in context
A three-dimensional spatial model for the interpretation of image data
Representation and processing of spatial expressions
A New Way to Represent the Relative Position between Areal Objects
IEEE Transactions on Pattern Analysis and Machine Intelligence
Qualitative Representation of Spatial Knowledge
Qualitative Representation of Spatial Knowledge
Qualitative representation of spatial knowledge in two-dimensional space
The VLDB Journal — The International Journal on Very Large Data Bases - Spatial Database Systems
The House Is North of the River: Relative Localization of Extended Objects
COSIT 2001 Proceedings of the International Conference on Spatial Information Theory: Foundations of Geographic Information Science
An Empirically Validated Model for Computing Spatial Relations
KI '95 Proceedings of the 19th Annual German Conference on Artificial Intelligence: Advances in Artificial Intelligence
Generating spatial descriptions for cross-modal references
ANLC '92 Proceedings of the third conference on Applied natural language processing
Prepositions in applications: A survey and introduction to the special issue
Computational Linguistics
| Hi-index | 0.00 |
This paper presents a corpus-based method for automatic evaluation of geometric constraints on projective prepositions. The method is used to find an appropriate model of geometric constraints for a two-dimensional domain. Two simple models are evaluated against the uses of projective prepositions in a corpus of natural language dialogues to find the best parameters of these models. Both models cover more than 96% of the data correctly. An extra treatment of negative uses of projective prepositions (e.g. A is not above B) improves both models getting close to full coverage.