Nasty.Language.Spanish.Adapters.EntityRecognizerAdapter (Nasty v0.3.0)

View Source

Adapter that bridges Spanish.EntityRecognizer to generic Semantic.EntityRecognition.RuleBased.

This adapter provides Spanish-specific configuration while delegating the core entity recognition algorithm to the language-agnostic implementation.

Configuration

Spanish-specific settings:

  • Name lexicons (common Spanish names from priv/languages/spanish/)
  • Place lexicons (Spanish cities, regions, countries)
  • Organization patterns (S.A., S.L., Ltda.)
  • Title patterns (Dr., Dra., Sr., Sra., Don, Doña)

Summary

Functions

recognize(tokens, opts \\ [])

Recognizes named entities in Spanish text using rule-based extraction.

Functions

recognize(tokens, opts \\ [])

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

Recognizes named entities in Spanish text using rule-based extraction.

Delegates to Semantic.EntityRecognition.RuleBased with Spanish configuration.

Options

  • :types - List of entity types to extract (default: all)
  • :min_confidence - Minimum confidence threshold (default: 0.5)
  • :use_context - Use context for disambiguation (default: true)

Examples

iex> {:ok, entities} = EntityRecognizerAdapter.recognize(spanish_tokens)
{:ok, [%Entity{type: :PERSON, text: "María García"}, ...]}

iex> {:ok, entities} = EntityRecognizerAdapter.recognize(tokens, types: [:PERSON, :ORG])
{:ok, [%Entity{...}]}