Extracting synchronous grammar rules from word-level alignments in linear time

Extracting synchronous grammar rules from word-level alignments in linear time (2008)

by Hao Zhang , Daniel Gildea , David Chiang

Venue:	In Proceedings of the 22nd International Conference on Computational Linguistics (COLING-08
Citations:	6 - 1 self

Datum	Value	Source
TITLE	Extracting synchronous grammar rules from word-level alignments in linear time	INFERENCE
AUTHOR NAME	Hao Zhang	SVM HeaderParse 0.2
AUTHOR AFFIL	Computer Science Department; University of Rochester	SVM HeaderParse 0.2
AUTHOR ADDR	Rochester, NY 14627, USA	SVM HeaderParse 0.2
AUTHOR NAME	Daniel Gildea	SVM HeaderParse 0.2
AUTHOR AFFIL	Computer Science Department; University of Rochester	SVM HeaderParse 0.2
AUTHOR ADDR	Rochester, NY 14627, USA	SVM HeaderParse 0.2
AUTHOR NAME	David Chiang	SVM HeaderParse 0.2
AUTHOR AFFIL	Information Sciences Institute; University of Southern California	SVM HeaderParse 0.2
AUTHOR ADDR	Marina del Rey, CA 90292, USA	SVM HeaderParse 0.2
ABSTRACT	We generalize Uno and Yagiura’s algorithm for finding all common intervals of two permutations to the setting of two sequences with many-to-many alignment links across the two sides. We show how to maximally decompose a word-aligned sentence pair in linear time, which can be used to generate all possible phrase pairs or a Synchronous Context-Free Grammar (SCFG) with the simplest rules possible. We also use the algorithm to precisely analyze the maximum SCFG rule length needed to cover hand-aligned data from various language pairs. 1	SVM HeaderParse 0.2
YEAR	2008	INFERENCE
VENUE	In Proceedings of the 22nd International Conference on Computational Linguistics (COLING-08	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
CITATIONS	10 found	ParsCit 1.0