Pegasus Arxiv

🚀 Pegasus Models

PEGASUS models are designed for the task of summarization, offering effective solutions in text summarization.

📚 Documentation

• See Docs: here
• Original TF 1 code here

👥 Authors and Maintainer

• Authors: Jingqing Zhang, Yao Zhao, Mohammad Saleh and Peter J. Liu on Dec 18, 2019
• Maintained by: @sshleifer

🎯 Task

Task: Summarization

📊 Mixed & Stochastic Checkpoints

We train a pegasus model with sampled gap sentence ratios on both C4 and HugeNews, and stochastically sample important sentences. The updated results are reported in the following table:

⚠️ Important Note

(*) the numbers of wikihow and big_patent datasets are not comparable because of change in tokenization and data:

• wikihow dataset contains newline characters which is useful for paragraph segmentation, the C4 and HugeNews model's sentencepiece tokenizer doesn't encode newline and loose this information.
• we update the BigPatent dataset to preserve casing, some format cleanings are also changed, please refer to change in TFDS.

🔍 Changes in the "Mixed & Stochastic" Model

The "Mixed & Stochastic" model has the following changes (from pegasus-large in the paper):

• Trained on both C4 and HugeNews (dataset mixture is weighted by their number of examples).
• Trained for 1.5M instead of 500k (we observe slower convergence on pretraining perplexity).
• The model uniformly samples a gap sentence ratio between 15% and 45%.
• Importance sentences are sampled using a 20% uniform noise to importance scores.
• The sentencepiece tokenizer is updated to be able to encode newline character.

📖 Citation

@misc{zhang2019pegasus,
    title={PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization},
    author={Jingqing Zhang and Yao Zhao and Mohammad Saleh and Peter J. Liu},
    year={2019},
    eprint={1912.08777},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}