Semantic Composition with Quotient Algebras

dc.contributor.author	Clarke, D.
dc.contributor.author	Lutz, R.
dc.contributor.author	Weir, D.
dc.date.accessioned	2012-01-12T13:01:04Z
dc.date.available	2012-01-12T13:01:04Z
dc.date.issued	2010
dc.identifier.citation	Clarke , D , Lutz , R & Weir , D 2010 , Semantic Composition with Quotient Algebras . in Procs of Geometric Models of Natural Language Semantics : GEMS-2010 . pp. 38-44 .
dc.identifier.other	PURE: 515332
dc.identifier.other	PURE UUID: 8abd3a25-2df3-4cbc-b0a4-baf248deee4f
dc.identifier.other	dspace: 2299/4684
dc.identifier.uri	http://hdl.handle.net/2299/7633
dc.description.abstract	We describe an algebraic approach for computing with vector based semantics. The tensor product has been proposed as a method of composition, but has the undesirable property that strings of different length are incomparable. We consider how a quotient algebra of the tensor algebra can allow such comparisons to be made, offering the possibility of data-driven models of semantic composition.	en
dc.language.iso	eng
dc.relation.ispartof	Procs of Geometric Models of Natural Language Semantics
dc.subject	linguistics
dc.subject	vector-based semantics
dc.subject	tensor algebra
dc.title	Semantic Composition with Quotient Algebras	en
dc.contributor.institution	School of Computer Science
rioxxterms.version	AM
rioxxterms.type	Other
herts.preservation.rarelyaccessed	true