← Lessons

quiz vs the machine

Gold1480

Machine Learning

The Text Summarization Abstractive

Generating new sentences that compress and rephrase the source.

5 min read · core · beat Gold to climb

What abstractive summarization does

Abstractive summarization generates a summary in fresh wording, compressing and paraphrasing the source rather than copying sentences. It reads more fluently but can invent details.

How it works

  • A sequence to sequence model encodes the document and decodes a short summary token by token.
  • Training pairs long documents with human written summaries and minimizes generation loss.
  • Large pretrained encoder decoders give strong results with limited fine tuning.

The hallucination risk

Because the model writes new text, it can state facts not in the source. This is hallucination, and it is the central danger of abstractive systems.

  • A summary may add a wrong date or attribute a quote to the wrong person.
  • Faithfulness checks compare claims in the summary against the source.

Evaluation

  • ROUGE measures overlap of n grams with reference summaries and correlates loosely with quality.
  • Faithfulness metrics test whether the summary is entailed by the source, since high ROUGE can still hide invented facts.

Key idea

Abstractive summarization generates new fluent text that compresses the source, trading the copy guarantee of extraction for paraphrasing power at the cost of possible hallucination.

Check yourself

Answer to earn rating on the learn ladder.

1. What is the central risk of abstractive summarization?

2. Why is ROUGE alone an insufficient quality metric?

3. What architecture typically powers abstractive summarization?