Yang Liu
BERT, a pre-trained Transformer model, has achieved ground-breaking performance on multiple NLP tasks. In this paper, we describe BERTSUM, a simple variant of BERT, for extractive summarization. Our system is the state of the art on the CNN/Dailymail dataset, outperforming the previous best-performed system by 1.65 on ROUGE-L. The codes to reproduce our results are available at https://github.com/nlpyang/BertSum
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Text Summarization | CNN / Daily Mail | ROUGE-1 | 43.25 | BERTSUM+Transformer |
| Text Summarization | CNN / Daily Mail | ROUGE-2 | 20.24 | BERTSUM+Transformer |
| Text Summarization | CNN / Daily Mail | ROUGE-L | 39.63 | BERTSUM+Transformer |
| Document Summarization | CNN / Daily Mail | ROUGE-1 | 43.25 | BERTSUM+Transformer |
| Document Summarization | CNN / Daily Mail | ROUGE-2 | 20.24 | BERTSUM+Transformer |
| Document Summarization | CNN / Daily Mail | ROUGE-L | 39.63 | BERTSUM+Transformer |