Paper Info
Title
Relational learning for spatial relation extraction from natural language
Abstract
Automatically extracting spatial information is a challenging novel task with many applications. We formalize it as an information extraction step required for a mapping from natural language to a formal spatial representation. Sentences may give rise to multiple spatial relations between words representing landmarks, trajectors and spatial indicators. Our contribution is to formulate the extraction task as a relational learning problem, for which we employ the recently introduced kLog framework. We discuss representational and modeling aspects, kLog's flexibility in our task and we present current experimental results.
Year
DOI
Venue
2011
10.1007/978-3-642-31951-8_20
ILP
Keywords
Field
DocType
spatial relation extraction,klog framework,current experimental result,formal spatial representation,spatial information,information extraction step,extraction task,multiple spatial relation,natural language,spatial indicator,challenging novel task
Spatial analysis,Spatial relation,Parse tree,Statistical relational learning,Computer science,Theoretical computer science,Spatial representation,Natural language processing,Artificial intelligence,Inductive logic programming,Information extraction,Natural language,Machine learning
Conference
Citations 
PageRank 
References 
10
0.59
13
Authors
5
Name
Order
Citations
PageRank
Parisa Kordjamshidi114318.52
Paolo Frasconi22984368.70
Martijn Van Otterlo31749.31
Marie-Francine Moens41750139.27
Luc De Raedt55481505.49