Learning to Parse from a Treebank: Combining TBL and ILP

Authors:
Miloslav Nepil
Affiliations:
-
Venue:
ILP '01 Proceedings of the 11th International Conference on Inductive Logic Programming
Year:
2001

Citing 3
Cited 0

Learning Context-Free Grammars with a Simplicity Bias

ECML '00 Proceedings of the 11th European Conference on Machine Learning
Inductive Logic Programming for Natural Language Processing

ILP '96 Selected Papers from the 6th International Workshop on Inductive Logic Programming
Automatic grammar induction and parsing free text: a transformation-based approach

ACL '93 Proceedings of the 31st annual meeting on Association for Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Considering the difficulties inherent in the manual construction of natural language parsers, we have designed and implemented our system Grind 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%.