Gale–Church alignment algorithm: Difference between revisions

Content deleted Content added

Inline

Revision as of 07:36, 29 March 2014

In computational linguistics, the Gale–Church algorithm is a method for aligning corresponding sentences in a parallel corpus. It works on the principle that equivalent sentences should roughly correspond in length—that is, longer sentences in one language should correspond to longer sentences in the other language. The algorithm was described in a 1993 paper by William A. Gale and Kenneth W. Church of AT&T Bell Laboratories.

References

Gale, William A.; Church, Kenneth W. (1993), "A Program for Aligning Sentences in Bilingual Corpora" (PDF), Computational Linguistics, 19 (1): 75–102

This algorithms or data structures-related article is a stub. You can help Wikipedia by expanding it.

This linguistics article is a stub. You can help Wikipedia by expanding it.

Revision as of 18:41, 20 April 2013 edit Yobot (talk \| contribs) Bots 4,733,870 edits m →References: WP:CHECKWIKI error fixes - Replaced endash with hyphen in sortkey per WP:MCSTJR using AWB (9100) ← Previous edit		Revision as of 07:36, 29 March 2014 edit undo Yobot (talk \| contribs) Bots 4,733,870 edits m WP:CHECKWIKI error fixes + other fixes, removed orphan tag using AWB (10065) Next edit →
Line 1:		Line 1:
	{{Orphan\|date=February 2009}}
	In [[computational linguistics]], the '''Gale–Church algorithm''' is a method for aligning corresponding sentences in a [[parallel corpus]]. It works on the principle that equivalent sentences should roughly correspond in length—that is, longer sentences in one language should correspond to longer sentences in the other language. The algorithm was described in a [http://acl.ldc.upenn.edu/J/J93/J93-1004.pdf 1993 paper] by William A. Gale and Kenneth W. Church of [[Bell Labs\|AT&T Bell Laboratories]].		In [[computational linguistics]], the '''Gale–Church algorithm''' is a method for aligning corresponding sentences in a [[parallel corpus]]. It works on the principle that equivalent sentences should roughly correspond in length—that is, longer sentences in one language should correspond to longer sentences in the other language. The algorithm was described in a [http://acl.ldc.upenn.edu/J/J93/J93-1004.pdf 1993 paper] by William A. Gale and Kenneth W. Church of [[Bell Labs\|AT&T Bell Laboratories]].