Saltar al contenido
Atlas de IA

Resumen de texto

Comprimir un texto largo en uno más corto y fiel

Lenguaje y conocimientoPrincipiante #04
entradaTextoTexto

El texto completo se presenta en inglés; el título y el resumen están traducidos.

QUÉ SIGNIFICA ESTA CAPACIDAD

Takes a long document and returns a shorter version that keeps the key information. It splits into extractive (selecting sentences) and abstractive (rewriting in new words) styles, the latter now dominant. Unlike free generation it has an explicit compression target, and unlike question answering it is not aimed at one query but should cover the whole thread.

Cómo se consigue técnicamente

The classic approach is a sequence-to-sequence attention model producing abstractive summaries, with rewriting ability coming from large-scale pre-training. Long documents are usually handled hierarchically or by a map-reduce scheme that summarises chunks and then combines them. Controlled summarisation passes length, angle or audience constraints through the prompt or light fine-tuning to steer style.

Productos representativos

8

Organizaciones relacionadas

Usos típicos

  • Quick reads of news and reports
  • Meeting and call minutes
  • Literature triage and paper skims
  • Rolling summaries of tickets and email

Cómo se evalúa

ROUGE
N-gram overlap with reference summaries
BERTScore
Semantic-embedding similarity, more tolerant than literal overlap
Factual consistency
Share of statements conflicting with the source, as in FactCC-style evaluation

Límites y dificultades

  • Middle sections of long documents are often dropped; models favour the start and end
  • Abstractive models splice facts from different sentences into claims the source never made
  • On ambiguous or multi-sided texts, minority views are often reported as the majority

Conceptos detrás