Reference Information Extraction and Processing Using Conditional Random Fields.
Fostering both the creation and the linking of data with the scope of supporting the growth of the Linked Data Web requires us to improve the acquisition and extraction mechanisms of the underlying semantic metadata. This is particularly important for the scientific publishing domain, where currentl...
| Publicado en: | Information Technology & Libraries Vol. 31; no. 2; pp. 6 - 21 |
|---|---|
| Autores principales: | , , |
| Formato: | equations & formulas pictorial research Journal Article |
| Publicado: |
American Library Association
Jun2012
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=83582598&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 83582598 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 07309295 ITL jtl: Information Technology & Libraries issn: 07309295 maglogo: N pubinfo: dt: Jun2012 vid: 31 iid: 2 pid: 55 pub: American Library Association place: Chicago, Illinois artinfo: ui: 83582598 104442257 104442257 10.6017/ital.v31i2.2163 83582598 ppf: 6 ppct: 15 formats: fmt: @attributes: type: P tig: atl: Reference Information Extraction and Processing Using Conditional Random Fields. aug: au: Groza, Tudor Aastrand Grimnes, Gunnar Handschuh, Siegfried affil: Postdoctoral Research Fellow, School of Information Technology and Electrical Engineering, University of Queensland sug: subj: Internet Information Retrieval Library Reference Services Semantics Science Human Experimental Studies Metadata Computers and Computerization Funding Source ab: Fostering both the creation and the linking of data with the scope of supporting the growth of the Linked Data Web requires us to improve the acquisition and extraction mechanisms of the underlying semantic metadata. This is particularly important for the scientific publishing domain, where currently most of the datasets are being created in an author-driven, manual manner. In addition, such datasets capture only fragments of the complete metadata, omitting usually, important elements such as the references, although they represent valuable information. In this paper we present an approach that aims at dealing with this aspect of extraction and processing of reference information. The experimental evaluation shows that, currently, our solution handles very well diverse types of reference format, thus making it usable for, or adaptable to, any area of scientific publishing. pubtype: Academic Journal doctype: equations & formulas pictorial research Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|