PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization

TL;DR

PEGASUS introduces a novel pre-training method for Transformer models using gap-sentence generation, significantly improving abstractive summarization across diverse domains and low-resource settings.

Contribution

The paper proposes a new self-supervised pre-training objective for Transformer models, tailored specifically for abstractive summarization, and demonstrates its effectiveness across multiple datasets.

Findings

Achieves state-of-the-art ROUGE scores on 12 summarization datasets.

Surpasses previous models in low-resource scenarios with only 1000 examples.

Human evaluation confirms the quality of generated summaries.

Abstract

Recent work pre-training Transformers with self-supervised objectives on large text corpora has shown great success when fine-tuned on downstream NLP tasks including text summarization. However, pre-training objectives tailored for abstractive text summarization have not been explored. Furthermore there is a lack of systematic evaluation across diverse domains. In this work, we propose pre-training large Transformer-based encoder-decoder models on massive text corpora with a new self-supervised objective. In PEGASUS, important sentences are removed/masked from an input document and are generated together as one output sequence from the remaining sentences, similar to an extractive summary. We evaluated our best PEGASUS model on 12 downstream summarization tasks spanning news, science, stories, instructions, emails, patents, and legislative bills. Experiments demonstrate it achieves state-of-the-art performance on all 12 downstream datasets measured by ROUGE scores. Our model also shows surprising performance on low-resource summarization, surpassing previous state-of-the-art results on 6 datasets with only 1000 examples. Finally we validated our results using human evaluation and show that our model summaries achieve human performance on multiple datasets.