nlpyang/PreSumm

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1303 stars · 452 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

PreSumm is the official PyTorch implementation of the EMNLP 2019 paper 'Text Summarization with Pretrained Encoders', providing BERT-based extractive (BertSumExt) and abstractive (BertSumAbs, BertSumExtAbs) summarization models. It includes training, evaluation, and inference code with pretrained checkpoints for CNN/DailyMail and XSum.

Use cases

• summarize long documents with bert
• train an extractive summarization model
• run abstractive text summarization with pretrained encoders
• reproduce emnlp 2019 summarization results on cnn/dailymail
• summarize raw text files from the command line
• evaluate summarization models with rouge

When to choose

• you need BERT-based extractive or abstractive summarization with published ROUGE benchmarks
• you want to reproduce or build on the PreSumm paper's models
• you have GPU resources and are comfortable with older PyTorch versions

When to avoid

• you need a production-ready, actively maintained summarization library
• you require modern PyTorch or transformer library versions
• you want plug-and-play summarization without training or setup effort

Facets

library · maturity maintenance

nlp machine-learning deep-learning machine-learning deep-learning python text-summarization bert abstractive-summarization extractive-summarization research-code pytorch emnlp-2019 rouge natural-language-processing linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="nlpyang/PreSumm")