Effective self-training for parsing

Effective self-training for parsing (2006)

by David Mcclosky , Eugene Charniak , Mark Johnson

Venue:	In Proc. N. American ACL (NAACL
Citations:	57 - 5 self

Datum	Value	Source
TITLE	Effective self-training for parsing	INFERENCE
AUTHOR NAME	David Mcclosky	SVM HeaderParse 0.2
AUTHOR AFFIL	Brown Laboratory for Linguistic Information Processing (BLLIP); Brown University	SVM HeaderParse 0.2
AUTHOR ADDR	Providence, RI 02912	SVM HeaderParse 0.2
AUTHOR NAME	Eugene Charniak	SVM HeaderParse 0.2
AUTHOR AFFIL	Brown Laboratory for Linguistic Information Processing (BLLIP); Brown University	SVM HeaderParse 0.2
AUTHOR ADDR	Providence, RI 02912	SVM HeaderParse 0.2
AUTHOR NAME	Mark Johnson	SVM HeaderParse 0.2
AUTHOR AFFIL	Brown Laboratory for Linguistic Information Processing (BLLIP); Brown University	SVM HeaderParse 0.2
AUTHOR ADDR	Providence, RI 02912	SVM HeaderParse 0.2
ABSTRACT	We present a simple, but surprisingly effective, method of self-training a twophase parser-reranker system using readily available unlabeled data. We show that this type of bootstrapping is possible for parsing when the bootstrapped parses are processed by a discriminative reranker. Our improved model achieves an f-score of 92.1%, an absolute 1.1 % improvement (12 % error reduction) over the previous best result for Wall Street Journal parsing. Finally, we provide some analysis to better understand the phenomenon. 1	SVM HeaderParse 0.2
YEAR	2006	INFERENCE
VENUE	In Proc. N. American ACL (NAACL	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	152--159	INFERENCE
CITATIONS	19 found	ParsCit 1.0