Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/78268
DC FieldValue
dc.titleOne class per named entity: Exploiting unlabeled text for named entity recognition
dc.contributor.authorWong, Y.
dc.contributor.authorNg, H.T.
dc.date.accessioned2014-07-04T03:14:20Z
dc.date.available2014-07-04T03:14:20Z
dc.date.issued2007
dc.identifier.citationWong, Y.,Ng, H.T. (2007). One class per named entity: Exploiting unlabeled text for named entity recognition. IJCAI International Joint Conference on Artificial Intelligence : 1763-1768. ScholarBank@NUS Repository.
dc.identifier.issn10450823
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/78268
dc.description.abstractIn this paper, we present a simple yet novel method of exploiting unlabeled text to further improve the accuracy of a high-performance state-of-the-art named entity recognition (NER) system. The method utilizes the empirical property that many named entities occur in one name class only. Using only unlabeled text as the additional resource, our improved NER system achieves an F1 score of 87.13%, an improvement of 1.17% in F1 score and a 8.3% error reduction on the CoNLL 2003 English NER official test set. This accuracy places our NER system among the top 3 systems in the CoNLL 2003 English shared task.
dc.sourceScopus
dc.typeConference Paper
dc.contributor.departmentCOMPUTER SCIENCE
dc.description.sourcetitleIJCAI International Joint Conference on Artificial Intelligence
dc.description.page1763-1768
dc.identifier.isiutNOT_IN_WOS
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

Page view(s)

37
checked on Oct 27, 2019

Google ScholarTM

Check


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