Please use this identifier to cite or link to this item: http://hdl.handle.net/1893/16451
Full metadata record
DC FieldValueLanguage
dc.contributor.authorWang, Qiu-Feng-
dc.contributor.authorCambria, Erik-
dc.contributor.authorLiu, Cheng-Lin-
dc.contributor.authorHussain, Amir-
dc.date.accessioned2013-08-12T23:10:33Z-
dc.date.issued2013-06-
dc.identifier.urihttp://hdl.handle.net/1893/16451-
dc.description.abstractCompared to human intelligence, computers are far short of common sense knowledge which people normally acquire during the formative years of their lives. This paper investigates the effects of employing common sense knowledge as a new linguistic context in handwritten Chinese text recognition. Three methods are introduced to supplement the standard n-gram language model: embedding model, direct model, and an ensemble of these two. The embedding model uses semantic similarities from common sense knowledge to make the n-gram probabilities estimation more reliable, especially for the unseen n-grams in the training text corpus. The direct model, in turn, considers the linguistic context of the whole document to make up for the short context limit of the n-gram model. The three models are evaluated on a large unconstrained handwriting database, CASIA-HWDB, and the results show that the adoption of common sense knowledge yields improvements in recognition performance, despite the reduced concept list hereby employed.en_UK
dc.language.isoen-
dc.publisherSpringer-
dc.relationWang Q, Cambria E, Liu C & Hussain A (2013) Common Sense Knowledge for Handwritten Chinese Text Recognition, Cognitive Computation, 5 (2), pp. 234-242.-
dc.rightsThe publisher does not allow this work to be made publicly available in this Repository. Please use the Request a Copy feature at the foot of the Repository record to request a copy directly from the author. You can only request a copy if you wish to use this work for your own research or private study.-
dc.subjectCommon sense knowledgeen_UK
dc.subjectNatural language processingen_UK
dc.subjectLinguistic contexten_UK
dc.subjectn-gramen_UK
dc.subjectHandwritten Chinese text recognitionen_UK
dc.titleCommon Sense Knowledge for Handwritten Chinese Text Recognitionen_UK
dc.typeJournal Articleen_UK
dc.rights.embargodate2999-12-31T00:00:00Z-
dc.rights.embargoreasonThe publisher does not allow this work to be made publicly available in this Repository therefore there is an embargo on the full text of the work.-
dc.identifier.doihttp://dx.doi.org/10.1007/s12559-012-9183-y-
dc.citation.jtitleCognitive Computation-
dc.citation.issn1866-9956-
dc.citation.volume5-
dc.citation.issue2-
dc.citation.spage234-
dc.citation.epage242-
dc.citation.publicationstatusPublished-
dc.citation.peerreviewedRefereed-
dc.type.statusPublisher version (final published refereed version)-
dc.author.emailamir.hussain@stir.ac.uk-
dc.contributor.affiliationChinese Academy of Sciences-
dc.contributor.affiliationNational University of Singapore-
dc.contributor.affiliationChinese Academy of Sciences-
dc.contributor.affiliationComputing Science - CSM Dept-
dc.rights.embargoterms2999-12-31-
dc.rights.embargoliftdate2999-12-31-
dc.identifier.isi000318648900009-
Appears in Collections:Computing Science and Mathematics Journal Articles

Files in This Item:
File Description SizeFormat 
Common Sense Knowledge for Handwritten Chinese Text Recognition.pdf555.34 kBAdobe PDFUnder Permanent Embargo    Request a copy


This item is protected by original copyright



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

If you believe that any material held in STORRE infringes copyright, please contact library@stir.ac.uk providing details and we will remove the Work from public display in STORRE and investigate your claim.