Instance-Family Abstraction in Memory-Based Language Learning

Instance-Family Abstraction in Memory-Based Language Learning (1999)

Cached

Download Links

[pi0657.kub.nl]

Other Repositories/Bibliography

DBLP

by Antal van den Bosch

Venue:	Machine Learning: Proceedings of the Sixteenth International Conference
Citations:	7 - 3 self

Versions

Version History

Metadata Version 3

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	Instance-Family Abstraction in Memory-Based Language Learning	user correction - Legacy Corrections
AUTHOR NAME	Antal van den Bosch	user correction - Legacy Corrections
AUTHOR AFFIL	ILK / Computational Linguistics; Tilburg University	user correction - Legacy Corrections
AUTHOR ADDR	The Netherlands	user correction - Legacy Corrections
ABSTRACT	ion in Memory-Based Language Learning Antal van den Bosch ILK / Computational Linguistics Tilburg University The Netherlands Antal.vdnBosch@kub.nl Abstract Memory-based learning appears relatively successful when the learning data is highly disjunct, i.e., when classes are scattered over many small families of instances in instance space, as in many language learning tasks. Abstraction over borders of disjuncts tends to harm generalization performance. However, careful abstraction in memory-based learning may be harmless when it preserves the disjunctivity of the learning data. We investigate the effect of careful abstraction in a series of language-learning task studies, and a small benchmark-task study. We find that when combined with feature weighting or value-distance metrics, careful abstraction, as implemented in the new fambl algorithm, can equal the generalization accuracies of pure memory-based learning, while attaining fair levels of memory compression. 1 INTRODUCTION Memo...	user correction - Legacy Corrections
YEAR	1999	INFERENCE
VENUE	Machine Learning: Proceedings of the Sixteenth International Conference	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	39--48	INFERENCE
CITATIONS	31 found	ParsCit 1.0