Discovering Types of Spatial Relations with a Text Mining Approach

Sarah Zenasni (1) , Eric Kergosien (2) , Mathieu Roche , Maguelonne Teisseire (1)

1 UMR TETIS - Territoires, Environnement, Télédétection et Information Spatiale
2 GERIICO - Groupe d'Études et de Recherche Interdisciplinaire en Information et COmmunication - ULR 4073

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.

Mots clés: Spatial relations; Text mining

Domaines: Informatique [cs]

Sarah Zenasni, Eric Kergosien, Mathieu Roche, Maguelonne Teisseire. Discovering Types of Spatial Relations with a Text Mining Approach. 22nd International Symposium on Methodologies for Intelligent Systems, Oct 2015, Lyon, France. pp.442-451, ⟨10.1007/978-3-319-25252-0_47⟩. ⟨hal-01358479⟩