# An Editorial Network for Enhanced Document Summarization

arXiv: https://arxiv.org/abs/1902.10360 · HTML: https://mlsanity.com/paper/1902.10360/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Feb 2019.

## Built on by (most cited first, 5 of 5)

- [Subjective Bias in Abstractive Summarization](https://mlsanity.com/paper/2106.10084/) (2021)
- [Universal Evasion Attacks on Summarization Scoring](https://mlsanity.com/paper/2210.14260/) (2022)
- [Reinforced Abstractive Summarization with Adaptive Length Controlling](https://mlsanity.com/paper/2112.07534/) (2021)
- [Reinforcing Semantic-Symmetry for Document Summarization](https://mlsanity.com/paper/2112.07583/) (2021)
- [Topic-Aware Encoding for Extractive Summarization](https://mlsanity.com/paper/2112.09572/) (2021)

## Abstract (arXiv)

We suggest a new idea of Editorial Network - a mixed extractive-abstractive summarization approach, which is applied as a post-processing step over a given sequence of extracted sentences. Our network tries to imitate the decision process of a human editor during summarization. Within such a process, each extracted sentence may be either kept untouched, rephrased or completely rejected. We further suggest an effective way for training the "editor" based on a novel soft-labeling approach. Using the CNN/DailyMail dataset we demonstrate the effectiveness of our approach compared to state-of-the-art extractive-only or abstractive-only baseline methods.