Estimating the average need of semantic knowledge from distributional semantic models.

Continuous bag of words (CBOW) and skip-gram are two recently developed models of lexical semantics (Mikolov, Chen, Corrado, & Dean, Advances in Neural Information Processing Systems, 26, 3111-3119, 2013). Each has been demonstrated to perform markedly better at capturing human judgments about seman...

Descripción completa

Detalles Bibliográficos
Publicado en:Memory & Cognition Vol. 45; no. 8; pp. 1350 - 1371
Autor principal: Hollis, Geoff
Formato: Artículo
Publicado: Springer Nature Nov2017
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=126091107&site=ehost-live
header:
  @attributes:
    shortDbName: ssf
    uiTerm: 126091107
    longDbName: Social Sciences Full Text (H.W. Wilson)
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        0090502X
        MEG
      jtl: Memory & Cognition
      issn: 0090502X
      maglogo: N
    pubinfo:
      dt: Nov2017
      vid: 45
      iid: 8
      pid: 237
      pub: Springer Nature
    artinfo:
      ui:
        126091107
        10.3758/s13421-017-0732-1
      ppf: 1350
      ppct: 21
      formats:
        fmt:
          @attributes:
            type: P
            size: 827KB
      tig:
        atl: Estimating the average need of semantic knowledge from distributional semantic models.
      aug:
        au: Hollis, Geoff
        affil: Department of Psychology , University of Alberta , P217 Biological Sciences Building Edmonton T6G 2E9 Canada
      su:
        Cognition
        Intellect
        Learning
        Psychology
        Semantics
        Algorithms
        Mathematical models
        Theory
        Phonological awareness
        Latent semantic analysis
      sug:
        subj:
          Cognition
          Intellect
          Learning
          Psychology
          Semantics
          Algorithms
          Mathematical models
          Theory
          Phonological awareness
          Latent semantic analysis
      keyword:
        average need
        CBOW
        Contextual diversity
        Likely need
        Needs probability
        Rational analysis
        Skip-gram
        Word frequency
        average need
        CBOW
        Contextual diversity
        Likely need
        Needs probability
        Rational analysis
        Skip-gram
        Word frequency
      ab: Continuous bag of words (CBOW) and skip-gram are two recently developed models of lexical semantics (Mikolov, Chen, Corrado, & Dean, Advances in Neural Information Processing Systems, 26, 3111-3119, 2013). Each has been demonstrated to perform markedly better at capturing human judgments about semantic relatedness than competing models (e.g., latent semantic analysis; Landauer & Dumais, Psychological Review, 104(2), 1997 211; hyperspace analogue to language; Lund & Burgess, Behavior Research Methods, Instruments, & Computers, 28(2), 203-208, 1996). The new models were largely developed to address practical problems of meaning representation in natural language processing. Consequently, very little attention has been paid to the psychological implications of the performance of these models. We describe the relationship between the learning algorithms employed by these models and Anderson's rational theory of memory (J. R. Anderson & Milson, Psychological Review, 96(4), 703, 1989) and argue that CBOW is learning word meanings according to Anderson's concept of needs probability. We also demonstrate that CBOW can account for nearly all of the variation in lexical access measures typically attributable to word frequency and contextual diversity-two measures that are conceptually related to needs probability. These results suggest two conclusions: One, CBOW is a psychologically plausible model of lexical semantics. Two, word frequency and contextual diversity do not capture learning effects but rather memory retrieval effects.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: N
    holdings:
      @attributes:
        islocal: N