Disambiguation of Super Parts of Speech (or Supertags): Almost Parsing

Simple item page
dc.contributor.authorJoshi, Aravind K.
dc.contributor.authorJoshi, Aravind K.
dc.contributor.authorSrinivas, B.
dc.date2023-05-16T23:49:48.000
dc.date.accessioned2023-05-22T19:57:33Z
dc.date.available2023-05-22T19:57:33Z
dc.date.issued1995-04-01
dc.date.submitted2006-09-07T09:14:05-07:00
dc.description.abstractIn a lexicalized grammar formalism such as Lexicalized Tree-Adjoining Grammar (LTAG), each lexical item is associated with at least one elementary structure (supertag) that localizes syntactic and semantic dependencies. Thus a parser for a lexicalized grammar must search a large set of supertags to choose the right ones to combine for the parse of the sentence. We present techniques for disambiguating supertags using local information such as lexical preference and local lexical dependencies. The similarity between LTAG and Dependency grammars is exploited in the dependency model of supertag disambiguation. The performance results for various models of supertag disambiguation such as unigram, trigram and dependency-based models are presented.
dc.description.commentsUniversity of Pennsylvania Institute for Research in Cognitive Science Technical Report No. IRCS-95-10.
dc.identifier.urihttps://repository.upenn.edu/handle/20.500.14332/37537
dc.legacy.articleid1127
dc.legacy.fulltexturlhttps://repository.upenn.edu/cgi/viewcontent.cgi?article=1127&context=ircs_reports&unstamped=1
dc.source.issue124
dc.source.journalIRCS Technical Reports Series
dc.source.statuspublished
dc.titleDisambiguation of Super Parts of Speech (or Supertags): Almost Parsing
dc.typeReport
digcom.contributor.authorisAuthorOfPublication|email:joshi@linc.cis.upenn.edu|institution:University of Pennsylvania|Joshi, Aravind K.
digcom.contributor.authorSrinivas, B.
digcom.identifierircs_reports/124
digcom.identifier.contextkey202938
digcom.identifier.submissionpathircs_reports/124
digcom.typereport
dspace.entity.typePublication
relation.isAuthorOfPublicationd8e4eeb5-ec36-4192-835f-c4d4edd1a709
relation.isAuthorOfPublication.latestForDiscoveryd8e4eeb5-ec36-4192-835f-c4d4edd1a709
upenn.schoolDepartmentCenterIRCS Technical Reports Series
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
95_10.pdf
Size:
193.48 KB
Format:
Adobe Portable Document Format
Download
Collection
Reports