File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Improved world-based language model

TitleImproved world-based language model
Authors
KeywordsComputational Language
Language Model
Pattern Recognition
Issue Date2004
Citation
Journal Of Harbin Institute Of Technology (New Series), 2004, v. 11 n. 1, p. 114-120 How to Cite?
AbstractIn order to construct a good language model used in the postprocessing phase of a recognition system, a smoothing technique must be used to solve the data sparseness problem. In the past, many smoothing techniques have been proposed. Among them, Katz's smoothing technique is well known. However, we found a weakness with the Katz's smoothing technique. We improved this approach by incorporating one kind of special Chinese language information and Chinese word class information into the language model. We tested the new smoothing technique with a Chinese character recognition system. The experimental result showed that a better performance could be achieved.
Persistent Identifierhttp://hdl.handle.net/10722/152329
ISSN
2015 SCImago Journal Rankings: 0.141
References

 

DC FieldValueLanguage
dc.contributor.authorChen, Yen_US
dc.contributor.authorChan, KPen_US
dc.date.accessioned2012-06-26T06:37:14Z-
dc.date.available2012-06-26T06:37:14Z-
dc.date.issued2004en_US
dc.identifier.citationJournal Of Harbin Institute Of Technology (New Series), 2004, v. 11 n. 1, p. 114-120en_US
dc.identifier.issn1005-9113en_US
dc.identifier.urihttp://hdl.handle.net/10722/152329-
dc.description.abstractIn order to construct a good language model used in the postprocessing phase of a recognition system, a smoothing technique must be used to solve the data sparseness problem. In the past, many smoothing techniques have been proposed. Among them, Katz's smoothing technique is well known. However, we found a weakness with the Katz's smoothing technique. We improved this approach by incorporating one kind of special Chinese language information and Chinese word class information into the language model. We tested the new smoothing technique with a Chinese character recognition system. The experimental result showed that a better performance could be achieved.en_US
dc.languageengen_US
dc.relation.ispartofJournal of Harbin Institute of Technology (New Series)en_US
dc.subjectComputational Languageen_US
dc.subjectLanguage Modelen_US
dc.subjectPattern Recognitionen_US
dc.titleImproved world-based language modelen_US
dc.typeArticleen_US
dc.identifier.emailChan, KP:kpchan@cs.hku.hken_US
dc.identifier.authorityChan, KP=rp00092en_US
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.scopuseid_2-s2.0-2942543080en_US
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-2942543080&selection=ref&src=s&origin=recordpageen_US
dc.identifier.volume11en_US
dc.identifier.issue1en_US
dc.identifier.spage114en_US
dc.identifier.epage120en_US
dc.identifier.scopusauthoridChen, Y=7601437873en_US
dc.identifier.scopusauthoridChan, KP=7406032820en_US

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats