Discovering types of spatial relations with a text mining approach
Zenasni S., Kergosien E., Roche M., Teisseire M.. 2015. In : Esposito Floriana (ed.), Pivert Olivier (ed.), Hacid Mohand-Said (ed.), Rás Zbigniew W. (ed.), Ferilli Stefano (ed.). Foundations of intelligent systems. Cham : Springer International Publishing, p. 442-451. (Lecture Notes in Computer Science, 9384). International Symposium on Methodologies for Intelligent Systems. 22, 2015-10-21/2015-10-23, Lyon (France).
Knowledge discovery from texts, particularly the identification of spatial information is a difficult task due to the complexity of texts written in natural language. Here we propose a method combining two statistical approaches (lexical and contextual analysis) and a text mining approach to automatically identify types of spatial relations. Experiments conducted on an English corpus are presented.
Documents associés
Communication de congrès
Agents Cirad, auteurs de cette publication :
- Roche Mathieu — Es / UMR TETIS