Abstract
Considering the difficulties inherent in the manual construction of natural language parsers, we have designed and implemented our system Gcrind which is capable of learning a sequence of context-dependent parsing actions from an arbitrary corpus containing labelled parse trees. To achieve this, Grind combines two established methods of machine learning: transformation-based learning (TBL) and inductive logic programming (ILP). Being trained and tested on corpus SUSANNE, Grind reaches the accuracy of 96 % and the recall of 68%.
This research has been partially supported by the Czech Ministry of Education under the grant JD MSM 143300003.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Blockeel, H. and de Raedt, L.: Top-down induction of logical decision trees. KU Leuven, Department of Computer Science. Technical report CW 247 (1997)
Brill, E.: Automatic grammar induction and parsing free text: A transformation-based approach. In Proceedings of 31 st Annual Meeting of the Association for Computational Linguistics, Somerset, NJ (1993) 259–265
Brill, E.: Transformation-based error-driven parsing. In Bunt, H. and Tomita, M. (eds.), Recent Advances in Parsing Technology. Kluwer Academic Publishers (1996)
Harrison P., Abney S., Black E., Flickinger D., Gdaniec C., Grishman R., Hindle D., Ingria R., Marcus M., Santorini B. and Strzalkowski T.: Evaluating Syntax Performance of Parser/Grammars of English. Language Processing Systems Evaluation Workshop, Technical Report RL-TR-91-36, Rome Laboratory, Air Force Systems, Command, Griffis Air Force Base, NY 13441–5700 (1991)
Langley, P.: Learning context-free grammars with a simplicity bias. In de Mantaras, R. L. and Plaza, E. (eds.), Proceedings of the 11 th European Conference on Machine Learning, LNAI 1810, Berlin, Springer Verlag (2000) 220–228
Mooney, R. J.: Inductive logic programming for natural language processing. In Muggleton, S. (ed.), Inductive Logic Programming: Selected Papers from the 6 th International Workshop, Berlin, Springer Verlag (1997) 3–22
Muggleton, S.: Inverse entailment and Progol. In New Generation Computing, special issue on inductive logic programming 13 (1995) 245–286
Sampson, G.: English for the Computer. Clarendon Press, Oxford, 1st edition (1995)
Zelle, J. M. and Mooney, R. J.: An inductive logic programming method for corpus-based parser construction. University of Texas, Austin. Unpublished technical note (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nepil, M. (2001). Learning to Parse from a Treebank: Combining TBL and ILP. In: Rouveirol, C., Sebag, M. (eds) Inductive Logic Programming. ILP 2001. Lecture Notes in Computer Science(), vol 2157. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44797-0_15
Download citation
DOI: https://doi.org/10.1007/3-540-44797-0_15
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42538-0
Online ISBN: 978-3-540-44797-9
eBook Packages: Springer Book Archive