Skip to content

Latest commit

 

History

History
25 lines (16 loc) · 653 Bytes

README.md

File metadata and controls

25 lines (16 loc) · 653 Bytes

UNER-OEKG-Hackathon

Universal Named Entity Recognition (UNER) is a framework hierarchy composed of 5 levels:

alt text

3-step Data-set creation:

    1. Extraction of texts and metadata from Wikipedia (EN and HR)
    1. Identication of the DBpedia classes via the hyperlinks associated with certain tokens (entities)
    1. Translation to UNER types and sub-types

Number of Entities:

  • English: 630,519
  • Croatian: 157,418

Statistics

Sample queries

UNER Hierachy

alt text