Show simple item record

dc.contributor.authorAngrosh, M. A.
dc.contributor.authorCranefield, Stephen
dc.contributor.authorStanger, Nigel
dc.contributor.editorHunter, Jane
dc.contributor.editorLagoze, Carl
dc.contributor.editorGiles, Lee
dc.contributor.editorLi, Yuan-Fang
dc.date.available2017-02-22T20:33:22Z
dc.date.copyright2010
dc.identifier.citationAngrosh, M. A., Cranefield, S., & Stanger, N. (2010). Context identification of sentences in related work sections using a conditional random field: towards intelligent digital libraries. In J. Hunter, C. Lagoze, L. Giles, & Y.-F. Li (Eds.), JCDL ’10 Proceedings of the 10th Annual Joint Conference on Digital Libraries (pp. 293–302). Joint conference on digital libraries presented at the 10th annual joint conference on digital libraries, ACM. doi:10.1145/1816123.1816168en
dc.identifier.urihttp://hdl.handle.net/10523/7134
dc.description.abstractIdentification of contexts associated with sentences is becoming increasingly necessary for developing intelligent information retrieval systems. This article describes a supervised learning mechanism employing a conditional random field (CRF) for context identification and sentence classification. Specifically, we focus on sentences in related work sections in research articles. Based on a generic rhetorical pattern, a framework for modelling the sequential flow in these sections is proposed. Adopting a generalization strategy, each of these sentences is transformed into a set of features, which forms our dataset. We distinguish between two kinds of features for each of these sentences viz., citation features and sentence features. While an overall accuracy of 96.51% is achieved by using a combination of both citation and sentence features, the use of sentence features alone yields an accuracy of 93.22%. The results also show F-Scores ranging from 0.99 to 0.90 for various classes indicating the robustness of our application.en_NZ
dc.format.mimetypeapplication/pdf
dc.language.isoenen_NZ
dc.publisherACMen_NZ
dc.relation.ispartofJCDL '10 Proceedings of the 10th annual joint conference on digital librariesen_NZ
dc.relation.ispartofseriesJoint conference on digital librariesen_NZ
dc.subjectSentence Classificationen_NZ
dc.subjectCitation Classificationen_NZ
dc.subjectConditional Random Fieldsen_NZ
dc.titleContext identification of sentences in related work sections using a conditional random field: towards intelligent digital librariesen_NZ
dc.typeConference or Workshop Item (Paper published in proceedings)en_NZ
dc.date.updated2017-02-21T23:16:02Z
otago.schoolInformation Scienceen_NZ
dc.identifier.doi10.1145/1816123.1816168en_NZ
otago.bitstream.endpage302en_NZ
otago.bitstream.startpage293en_NZ
otago.openaccessOpenen_NZ
dc.rights.statementACM New York, NY, USA ©2010en_NZ
dc.description.refereedPeer Revieweden_NZ
otago.event.placeGold Coast, Queensland, Australiaen_NZ
otago.event.title10th annual joint conference on digital librariesen_NZ
otago.relation.number10en_NZ
 Find in your library

Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record