Nasty.Language.Spanish.Summarizer (Nasty v0.3.0)

View Source

Generates summaries of Spanish documents.

Delegates to generic extractive summarization with Spanish-specific configuration.

Extractive Summarization

Ranks sentences by importance using:

  • TF-IDF term frequency
  • Position in document
  • Named entity density
  • Sentence length
  • Spanish discourse markers

Spanish-Specific Features

  • Stop words (el, la, de, en, y, etc.)
  • Sentence boundaries (., !, ?, ;, ¿, ¡)
  • Discourse markers (además, sin embargo, por lo tanto, en conclusión)

Example

iex> doc = parse("El gato es un animal. Los gatos son carnívoros. Les gusta dormir.")
iex> summary = Summarizer.summarize(doc, ratio: 0.5)
{:ok, %Document{...}}

Summary

Functions

summarize(doc, opts \\ [])

Generates an extractive summary of a Spanish document.

Functions

summarize(doc, opts \\ [])

@spec summarize(
  Nasty.AST.Document.t(),
  keyword()
) :: {:ok, Nasty.AST.Document.t()} | {:error, term()}

Generates an extractive summary of a Spanish document.

Delegates to the Spanish adapter which uses generic extractive summarization with Spanish-specific configuration (stop words, discourse markers, punctuation).

Options

  • :ratio - Fraction of sentences to include (default: 0.3)
  • :max_sentences - Maximum number of sentences (default: unlimited)
  • :min_sentences - Minimum number of sentences (default: 1)
  • :method - Selection method: :greedy (default) or :mmr
  • :mmr_lambda - MMR lambda parameter (0.0-1.0), default 0.7

Examples

iex> {:ok, summary} = Summarizer.summarize(doc, ratio: 0.3)
iex> {:ok, summary} = Summarizer.summarize(doc, max_sentences: 3, method: :mmr)