Skip navigation
Please use this identifier to cite or link to this item: http://arks.princeton.edu/ark:/88435/dsp012z10wt41r
Full metadata record
DC FieldValueLanguage
dc.contributor.advisorFellbaum, Christiane-
dc.contributor.authorMasood, Zaynab-
dc.date.accessioned2022-08-08T16:54:46Z-
dc.date.available2022-08-08T16:54:46Z-
dc.date.created2022-05-
dc.date.issued2022-08-08-
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/dsp012z10wt41r-
dc.description.abstractAs a response to the lack of resources for the Urdu language in natural language processing, this thesis seeks to create a WordNet for Urdu. A newly-developed word-embeddings technique, developed by Mikhail Khodak et al., is used on an Urdu newspaper corpus with a set of nouns to construct the WordNet for the Nastaliq script of Urdu.en_US
dc.format.mimetypeapplication/pdf
dc.language.isoenen_US
dc.titleUrdu WordNeten_US
dc.typePrinceton University Senior Theses
pu.date.classyear2022en_US
pu.departmentComputer Scienceen_US
pu.pdf.coverpageSeniorThesisCoverPage
pu.contributor.authorid920209573
pu.mudd.walkinNoen_US
Appears in Collections:Computer Science, 1987-2023

Files in This Item:
File SizeFormat 
MASOOD-ZAYNAB-THESIS.pdf1.39 MBAdobe PDF    Request a copy


Items in Dataspace are protected by copyright, with all rights reserved, unless otherwise indicated.