Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/5199
PIRA download icon_1.1View/Download Full Text
DC FieldValueLanguage
dc.contributorDepartment of Computing-
dc.creatorXu, J-
dc.creatorLu, Q-
dc.creatorLiu, Z-
dc.date.accessioned2014-12-11T08:26:11Z-
dc.date.available2014-12-11T08:26:11Z-
dc.identifier.isbn978-1-937284-21-3 (v.1)-
dc.identifier.isbn978-1-937284-22-0 (v.2)-
dc.identifier.urihttp://hdl.handle.net/10397/5199-
dc.language.isoenen_US
dc.publisherAssociation for Computational Linguistics (ACL)en_US
dc.rights©Association for Computational Linguisticsen_US
dc.rightsReproduced with permission of the author.en_US
dc.titlePolyUCOMP : combining semantic vectors with skip bigrams for semantic textual similarityen_US
dc.typeConference Paperen_US
dcterms.abstractThis paper presents the work of the Hong Kong Polytechnic University (PolyUCOMP) team which has participated in the Semantic Textual Similarity task of SemEval-2012. The PolyUCOMP system combines semantic vectors with skip bigrams to determine sentence similarity. The semantic vector is used to compute similarities between sentence pairs using the lexical database WordNet and the Wikipedia corpus. The use of skip bigram is to introduce the order of words in measuring sentence similarity.-
dcterms.accessRightsopen accessen_US
dcterms.bibliographicCitation*SEM 2012: The First Joint Conference on Lexical and Computational Semantics, June 7-8, 2012, Montre´al, Canada, p. 524–528-
dcterms.issued2012-06-07-
dc.identifier.rosgroupidr59847-
dc.description.ros2011-2012 > Academic research: refereed > Refereed conference paper-
dc.description.oaVersion of Recorden_US
dc.identifier.FolderNumberOA_IR/PIRAen_US
dc.description.pubStatusPublisheden_US
Appears in Collections:Conference Paper
Files in This Item:
File Description SizeFormat 
Xu_PolyUCOMP_Semantic_Textual.pdf194.09 kBAdobe PDFView/Open
Open Access Information
Status open access
File Version Version of Record
Access
View full-text via PolyU eLinks SFX Query
Show simple item record

Page views

98
Last Week
0
Last month
Citations as of Apr 14, 2024

Downloads

46
Citations as of Apr 14, 2024

Google ScholarTM

Check


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