Explaining Contextualized Word Embeddings in Biomedical Research – A Qualitative Investigation...International Conference on Informatics, Management, and Technology in Healthcare (ICIMTH), 1-3 July, 2022, Athens, Greece.

Contextualized word embeddings proved to be highly successful quantitative representations of words that allow to efficiently solve various tasks such as clinical entity normalization in unstructured texts. In this paper, we investigate how the Saussurean sign theory can be used as a qualitative exp...

Descripción completa

Detalles Bibliográficos
Publicado en:Studies in Health Technology & Informatics Vol. 295; pp. 289 - 293
Autores principales: MILETIC, Marko, SARIYAR, Murat
Formato: proceedings research tables/charts Journal Article
Publicado: Sage Publications Inc. 2022
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=157849127&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 157849127
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        09269630
        U1V
      jtl: Studies in Health Technology & Informatics
      issn: 09269630
      maglogo: N
    pubinfo:
      dt: 2022
      vid: 295
      pid: 344
      pub: Sage Publications Inc.
      place: Thousand Oaks, California
    artinfo:
      ui:
        157849127
        157849127
        157849127
        10.3233/SHTI220719
        157849127
      ppf: 289
      ppct: 4
      formats:
      tig:
        atl: Explaining Contextualized Word Embeddings in Biomedical Research – A Qualitative Investigation...International Conference on Informatics, Management, and Technology in Healthcare (ICIMTH), 1-3 July, 2022, Athens, Greece.
      aug:
        au:
          MILETIC, Marko
          SARIYAR, Murat
        affil: Bern University of Applied Sciences, Switzerland.
      sug:
        subj:
          Language
          Artificial Intelligence Utilization
          Task Performance and Analysis
          Biomedical Engineering
          Human
          Qualitative Studies
          Goals and Objectives
          Confidence
          Trust
          Natural Language Processing
          Models, Theoretical
      ab: Contextualized word embeddings proved to be highly successful quantitative representations of words that allow to efficiently solve various tasks such as clinical entity normalization in unstructured texts. In this paper, we investigate how the Saussurean sign theory can be used as a qualitative explainable AI method for word embeddings. Our assumption is that the main goal of XAI is to produce confidence and/or trust, which can be gained through quantitative as well as quantitative approaches. One important result is related to the fact that the differential structure of language as explained by Saussure corresponds to the possibility of adding and subtracting word embeddings. On the other hand, these mathematical structures provide insights into the inner workings of natural language.
      pubtype: Academic Journal
      doctype:
        proceedings
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N