Creation and evaluation of large keyphrase extraction collections with multiple opinions.

While several automatic keyphrase extraction (AKE) techniques have been developed and analyzed, there is little consensus on the definition of the task and a lack of overview of the effectiveness of different techniques. Proper evaluation of keyphrase extraction requires large test collections with...

Descripción completa

Detalles Bibliográficos
Publicado en:Language Resources & Evaluation Vol. 52; no. 2; pp. 503 - 533
Autores principales: Sterckx, Lucas, Demeester, Thomas, Deleu, Johannes, Develder, Chris
Formato: Artículo
Publicado: Springer Nature Jun2018
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=129593481&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 129593481
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        1574020X
        179V
      jtl: Language Resources & Evaluation
      issn: 1574020X
      maglogo: N
    pubinfo:
      dt: Jun2018
      vid: 52
      iid: 2
      pid: 237
      pub: Springer Nature
    artinfo:
      ui:
        129593481
        10.1007/s10579-017-9395-6
      ppf: 503
      ppct: 30
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
              size: 2.4MB
      tig:
        atl: Creation and evaluation of large keyphrase extraction collections with multiple opinions.
      aug:
        au:
          Sterckx, Lucas
          Demeester, Thomas
          Deleu, Johannes
          Develder, Chris
        affil: Department of Information Technology, Ghent University - imec, Technologiepark Zwijnaarde 15, 9052, Ghent, Belgium
      su:
        Machine learning
        Information resources management
        Data mining
        Support vector machines
        Data management
      sug:
        subj:
          Machine learning
          Information resources management
          Data mining
          Support vector machines
          Data management
      keyword:
        Annotator disagreement
        Automatic keyphrase extraction
        Test collections
      ab: While several automatic keyphrase extraction (AKE) techniques have been developed and analyzed, there is little consensus on the definition of the task and a lack of overview of the effectiveness of different techniques. Proper evaluation of keyphrase extraction requires large test collections with multiple opinions, currently not available for research. In this paper, we (i) present a set of test collections derived from various sources with multiple annotations (which we also refer to as <italic>opinions</italic> in the remained of the paper) for each document, (ii) systematically evaluate keyphrase extraction using several supervised and unsupervised AKE techniques, (iii) and experimentally analyze the effects of disagreement on AKE evaluation. Our newly created set of test collections spans different types of topical content from general news and magazines, and is annotated with multiple annotations per article by a large annotator panel. Our annotator study shows that for a given document there seems to be a large disagreement on the preferred keyphrases, suggesting the need for multiple opinions per document. A first systematic evaluation of ranking and classification of keyphrases using both unsupervised and supervised AKE techniques on the test collections shows a superior effectiveness of supervised models, even for a low annotation effort and with basic positional and frequency features, and highlights the importance of a suitable keyphrase candidate generation approach. We also study the influence of multiple opinions, training data and document length on evaluation of keyphrase extraction. Our new test collection for keyphrase extraction is one of the largest of its kind and will be made available to stimulate future work to improve reliable evaluation of new keyphrase extractors.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      custom: Language Resources & Evaluation is a copyright of Springer, 2018. All Rights Reserved.
      item: Language Resources & Evaluation
      holder: Springer Nature
      dt:
        @attributes:
          year: 2018
    holdings:
      @attributes:
        islocal: N