Nasty.Language.Catalan.EntityRecognizer (Nasty v0.3.0)

View Source

Recognizes named entities in Catalan text.

Uses rule-based patterns to identify:

  • PERSON: names (Joan Garcia, Maria López)
  • LOCATION: cities, regions (Barcelona, Catalunya, València)
  • ORGANIZATION: companies, institutions (Banc de Catalunya, FC Barcelona)
  • DATE: temporal expressions (dilluns, 15 de gener, 2024)
  • MONEY: currency amounts (100 euros, 25€)
  • PERCENT: percentages (25%, 3,5 per cent)

Catalan-Specific Features

  • Catalan name and place lexicons
  • Catalan titles (Sr., Sra., Dr., Dra., Don, Donya)
  • Catalan date formats (15 de gener de 2024)
  • Euro currency symbols (€)
  • Catalan organizational patterns (S.A., S.L.)

Summary

Functions

recognize(tokens, opts \\ [])

@spec recognize(
  [Nasty.AST.Token.t()],
  keyword()
) :: {:ok, [Nasty.AST.Semantic.Entity.t()]} | {:error, term()}