Ming Zhong, PengFei Liu, Danqing Wang, Xipeng Qiu, Xuanjing Huang
The recent years have seen remarkable success in the use of deep neural networks on text summarization. However, there is no clear understanding of \textit{why} they perform so well, or \textit{how} they might be improved. In this paper, we seek to better understand how neural extractive summarization systems could benefit from different types of model architectures, transferable knowledge and learning schemas. Additionally, we find an effective way to improve current frameworks and achieve the state-of-the-art result on CNN/DailyMail by a large margin based on our observations and analyses. Hopefully, our work could provide more clues for future research on extractive summarization.
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Text Summarization | CNN / Daily Mail | ROUGE-1 | 42.69 | PNBERT |
| Text Summarization | CNN / Daily Mail | ROUGE-2 | 19.6 | PNBERT |
| Text Summarization | CNN / Daily Mail | ROUGE-L | 38.85 | PNBERT |
| Extractive Text Summarization | CNN / Daily Mail | ROUGE-1 | 42.69 | PNBERT |
| Extractive Text Summarization | CNN / Daily Mail | ROUGE-2 | 19.6 | PNBERT |
| Extractive Text Summarization | CNN / Daily Mail | ROUGE-L | 38.85 | PNBERT |