Online large-margin training of dependency parsers

Online large-margin training of dependency parsers (2005)

by Ryan Mcdonald , Koby Crammer , Fernando Pereira

Venue:	In Proc. ACL
Citations:	156 - 16 self

Datum	Value	Source
TITLE	Online large-margin training of dependency parsers	INFERENCE
AUTHOR NAME	Ryan Mcdonald	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Computer and Information Science; University of Pennsylvania	SVM HeaderParse 0.2
AUTHOR ADDR	Philadelphia, PA	SVM HeaderParse 0.2
AUTHOR NAME	Koby Crammer	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Computer and Information Science; University of Pennsylvania	SVM HeaderParse 0.2
AUTHOR ADDR	Philadelphia, PA	SVM HeaderParse 0.2
AUTHOR NAME	Fernando Pereira	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Computer and Information Science; University of Pennsylvania	SVM HeaderParse 0.2
AUTHOR ADDR	Philadelphia, PA	SVM HeaderParse 0.2
ABSTRACT	We present an effective training algorithm for linearly-scored dependency parsers that implements online largemargin multi-class training (Crammer and Singer, 2003; Crammer et al., 2003) on top of efficient parsing techniques for dependency trees (Eisner, 1996). The trained parsers achieve a competitive dependency accuracy for both English and Czech with no language specific enhancements. 1	SVM HeaderParse 0.2
YEAR	2005	INFERENCE
VENUE	In Proc. ACL	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	91--98	INFERENCE
CITATIONS	29 found	ParsCit 1.0