Item request has been placed! ×
Item request cannot be made. ×
loading  Processing Request

Concreteness and imageability lexicon MEGA.HR-Crossling

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read More Add to Saved list
  • Additional Information
    • Publication Information:
      Jožef Stefan Institute
      Faculty of Humanities and Social Sciences, University of Zagreb
    • Publication Date:
      2018
    • Collection:
      OLAC: Open Language Archives Community
    • Abstract:
      The lexicon contains concreteness and imageability predictions of words in 77 languages. The resource is built via supervised machine learning, using average human responses obtained for Croatian lexemes inside the MEGAHR project (http://megahr.ffzg.unizg.hr) as the response variable, and the Facebook cross-lingual word embeddings (https://github.com/Babylonpartners/fastText_multilingual) as explanatory variables. The Spearman correlation of human responses and automatic annotations on the Croatian-English language pair is ~0.8 for concreteness and ~0.7 for imageability.
    • Relation:
      http://hdl.handle.net/11356/1187
    • Online Access:
      http://hdl.handle.net/11356/1187
    • Rights:
      Creative Commons - Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ; https://creativecommons.org/licenses/by-sa/4.0/
    • Accession Number:
      edsbas.E6373657