Discovering types of spatial relations with a text mining approach
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.
Saved in:
Main Authors: | Zenasni, Sarah, Kergosien, Eric, Roche, Mathieu, Teisseire, Maguelonne |
---|---|
Format: | conference_item biblioteca |
Language: | eng |
Published: |
Springer International Publishing
|
Subjects: | C30 - Documentation et information, U10 - Informatique, mathématiques et statistiques, |
Online Access: | http://agritrop.cirad.fr/579646/ http://agritrop.cirad.fr/579646/1/conf_ISMIS15.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Identification automatique des types de relations spatiales dans les textes
by: Zenasni, Sarah, et al. -
Découverte de nouvelles entités et relations spatiales à partir d'un corpus de SMS
by: Zenasni, Sarah, et al. -
Extracting absolute spatial entities from SMS: Comparing a supervised and an unsupervised approach
by: Lopez, Cédric, et al. -
When textual information becomes spatial information compatible with satellite images
by: Kergosien, Eric, et al. -
ANIMITEX project: image analysis based on textual information
by: Alatrista-Sala, Hugo, et al.