Extractive Summarization of Long Documents by Combining Global and Local Context
This addresses the problem of summarizing long scientific papers for researchers, but it is incremental as it builds on existing neural methods with a focus on context modeling.
The paper tackled extractive summarization of long documents by incorporating global and local context, achieving improved ROUGE-1, ROUGE-2, and METEOR scores on Pubmed and arXiv datasets compared to previous models, with benefits increasing for longer documents.
In this paper, we propose a novel neural single document extractive summarization model for long documents, incorporating both the global context of the whole document and the local context within the current topic. We evaluate the model on two datasets of scientific papers, Pubmed and arXiv, where it outperforms previous work, both extractive and abstractive models, on ROUGE-1, ROUGE-2 and METEOR scores. We also show that, consistently with our goal, the benefits of our method become stronger as we apply it to longer documents. Rather surprisingly, an ablation study indicates that the benefits of our model seem to come exclusively from modeling the local context, even for the longest documents.