A comparative evaluation of off-the-shelf distributed semantic representations for modelling behavioural data.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
  • Additional Information
    • Source:
      Publisher: Routledge Country of Publication: England NLM ID: 8411889 Publication Model: Print Cited Medium: Internet ISSN: 1464-0627 (Electronic) Linking ISSN: 02643294 NLM ISO Abbreviation: Cogn Neuropsychol Subsets: MEDLINE
    • Publication Information:
      Publication: 2013- : London : Routledge
      Original Publication: London ; Hillsdale, N.J. : Lawrence Erlbaum Associates, c1984-
    • Subject Terms:
    • Abstract:
      In this paper we carry out an extensive comparison of many off-the-shelf distributed semantic vectors representations of words, for the purpose of making predictions about behavioural results or human annotations of data. In doing this comparison we also provide a guide for how vector similarity computations can be used to make such predictions, and introduce many resources available both in terms of datasets and of vector representations. Finally, we discuss the shortcomings of this approach and future research directions that might address them.
    • Contributed Indexing:
      Keywords: Distributed semantic representation; evaluation; semantic space; semantic vector
    • Publication Date:
      Date Created: 20161001 Date Completed: 20170404 Latest Revision: 20181202
    • Publication Date:
      20240104
    • Accession Number:
      10.1080/02643294.2016.1176907
    • Accession Number:
      27686110