nlpyang/BertSum
A research implementation that fine-tunes BERT for extractive document summarization.
Not currently ranked — collecting fresh signals.
star history
This repository implements the paper ‘Fine-tune BERT for Extractive Summarization’ by adding multiple sentence embeddings and interval segments to BERT, then fine-tuning for extractive summarization tasks. The code supports training on CNN/DailyMail datasets and evaluates using ROUGE metrics. It uses PyTorch as the deep learning framework and Stanford CoreNLP for preprocessing.
Frequently asked
- What is nlpyang/BertSum?
- A research implementation that fine-tunes BERT for extractive document summarization.
- Is BertSum open source?
- Yes — nlpyang/BertSum is open source, released under the Apache-2.0 license.
- What language is BertSum written in?
- nlpyang/BertSum is primarily written in Python.
- How popular is BertSum?
- nlpyang/BertSum has 1.5k stars on GitHub.
- Where can I find BertSum?
- nlpyang/BertSum is on GitHub at https://github.com/nlpyang/BertSum.