Dependency-based machine translation and parallel parsing without the projectivity and edge-factoring assumptions

Show simple item record

dc.contributor.author	Buch-Kromann, Matthias	en_US
dc.date.accessioned	2009-02-04T10:25:08Z
dc.date.available	2009-02-04T10:25:08Z
dc.date.issued	2007-12-11T00:00:00Z	en_US
dc.identifier.uri	http://hdl.handle.net/10398/6846
dc.description.abstract	In this white paper, we review the theoretical evidence about the computational efficiency of dependency parsing and machine translation without the widely used, but linguistically questionable assumptions about projectivity and edge-factoring. On the basis of the heuristic local optimality parser proposed by (Buch-Kromann, 2006), we propose a common architecture for monolingual parsing, parallel parsing, and translation that does not make these assumptions. Finally, we describe the elementary repair operations in the model, and argue that the model is potentially interesting as a model of human translation.	en_US
dc.format.extent	14 s.	en_US
dc.language	eng	en_US
dc.relation.ispartofseries	Working paper;2007-1	en_US
dc.title	Dependency-based machine translation and parallel parsing without the projectivity and edge-factoring assumptions	en_US
dc.type	wp	en_US
dc.accessionstatus	modt07dec11 nijemo	en_US
dc.contributor.corporation	Copenhagen Business School. CBS	en_US
dc.contributor.department	Institut for Internationale Sprogstudier og Vidensteknologi
dc.contributor.departmentshort	ISV
dc.contributor.departmentuk	Department of International Language Studies and Computational Linguistics
dc.contributor.departmentukshort	ISV
dc.idnumber	x656555814	en_US
dc.publisher.city	København	en_US
dc.publisher.year	2007	en_US
dc.title.subtitle	A white paper	en_US