Relational learning for spatial relation extraction from natural language

Authors:
Parisa Kordjamshidi;Paolo Frasconi;Martijn Van Otterlo;Marie-Francine Moens;Luc De Raedt
Affiliations:
Department of Computer Science, Katholieke Universiteit Leuven, Belgium;Università degli Studi di Firenze, Italy;Radboud University Nijmegen, The Netherlands;Department of Computer Science, Katholieke Universiteit Leuven, Belgium;Department of Computer Science, Katholieke Universiteit Leuven, Belgium
Venue:
ILP'11 Proceedings of the 21st international conference on Inductive Logic Programming
Year:
2011

Citing 9
Cited 0

Issues in Learning Language in Logic

Computational Logic: Logic Programming and Beyond, Essays in Honour of Robert A. Kowalski, Part II
Knowledge-based spatial reasoning for automated scene generation from text descriptions

Knowledge-based spatial reasoning for automated scene generation from text descriptions
Large Margin Methods for Structured and Interdependent Output Variables

The Journal of Machine Learning Research
Coarse-to-fine n-best parsing and MaxEnt discriminative reranking

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Learning from interpretations: a rooted kernel for ordered hypergraphs

Proceedings of the 24th international conference on Machine learning
Database Systems: The Complete Book

Database Systems: The Complete Book
Combination strategies for semantic role labeling

Journal of Artificial Intelligence Research
Probabilistic inductive logic programming

Probabilistic inductive logic programming
Spatial role labeling: Towards extraction of spatial relations from natural language

ACM Transactions on Speech and Language Processing (TSLP)

Quantified Score

Hi-index	0.00

Visualization

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.