The official code for PRIMER: Pyramid-based Masked Sentence Pre-training for Multi-document Summarization.

PRIMER is a pre-trained model for multi-document representation with focus on summarization that reduces the need for dataset-specific architectures and large amounts of fine-tuning labeled data. With extensive experiments on 6 multi-document summarization datasets from 3 different domains on the zero-shot, few-shot and full-supervised settings, PRIMER outperforms current state-of-the-art models on most of these settings with large margins.

Set up

  1. Create new virtual environment by

conda create --name primer python=3.7
conda activate primer
conda install cudatoolkit=10.0
  1. Install Longformer by

pip install git+
  1. Install requirements to run the summarization scripts and data generation scripts by

pip install -r requirements.txt

Usage of PRIMER

  1. Download the pre-trained PRIMER model here to ./PRIMER_model
  2. Load the tokenizer and model by

from transformers import AutoTokenizer
from longformer import LongformerEncoderDecoderForConditionalGeneration
from longformer import LongformerEncoderDecoderConfig

tokenizer = AutoTokenizer.from_pretrained('./PRIMER_model/')
config = LongformerEncoderDecoderConfig.from_pretrained('./PRIMER_model/')
model = LongformerEncoderDecoderForConditionalGeneration.from_pretrained(
            './PRIMER_model/', config=config)

Make sure the documents separated with <doc-sep> in the input.

Summarization Scripts

You can use script/ for pre-train/train/test PRIMER, and script/ for train/test BART/PEGASUS/LED.

Pre-training Data Generation

Newshead: we crawled the newshead dataset using the original code, and cleaned up the crawled data, the final newshead dataset can be found here.

You can use utils/ to generate pre-training data.

  1. Generate data with scores and entities with --mode compute_all_scores
  2. Generate pre-training data with --mode pretraining_data_with_score:
    • Pegasus: --strategy greedy --metric pegasus_score
    • Entity_Pyramid: --strategy greedy_entity_pyramid --metric pyramid_rouge


  • For Multi-News and Multi-XScience, it will automatically download from Huggingface.
  • WCEP-10: the preprocessed version can be found here
  • Wikisum: we only use a small subset for few-shot training(10/100) and testing(3200). The subset we used can be found here. Note we have significantly more examples than we used in and, as we sample 10/100 examples multiple times in the few-shot setting, and we need to make sure it has a large pool to sample from.
  • DUC2003/2004: You need to apply for access based on the
  • arXiv: you can find the data we used in this repo


View Github