Probability Statements Extraction with Constrained Conditional Random Fields.
This paper investigates how to extract probability statements from academic medical papers. In previous work we have explored traditional classification methods which led to numerous false negatives. This current work focuses on constraining classification output obtained from a Conditional Random F...
| Publicado en: | Studies in Health Technology & Informatics Vol. 228; pp. 527 - 532 |
|---|---|
| Autores principales: | , |
| Formato: | research tables/charts Journal Article |
| Publicado: |
Sage Publications Inc.
2016
|
| 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=117766228&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 117766228 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 09269630 U1V jtl: Studies in Health Technology & Informatics issn: 09269630 maglogo: N pubinfo: dt: 2016 vid: 228 pid: 344 pub: Sage Publications Inc. place: Thousand Oaks, California artinfo: ui: 117766228 117766228 117766228 10.3233/978-1-61499-678-1-527 117766228 ppf: 527 ppct: 5 formats: tig: atl: Probability Statements Extraction with Constrained Conditional Random Fields. aug: au: DELERIS, Léa A. JOCHIM, Charles affil: IBM Research - Ireland sug: subj: Information Retrieval Methods Probability Medical Literature Data Mining Informatics Models, Statistical ab: This paper investigates how to extract probability statements from academic medical papers. In previous work we have explored traditional classification methods which led to numerous false negatives. This current work focuses on constraining classification output obtained from a Conditional Random Field (CRF) model to allow for domain knowledge constraints. Our experimental results indicate constraining leads to a significant improvement in performance. pubtype: Academic Journal doctype: research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|