An Editorial Network for Enhanced Document Summarization
This work addresses the problem of generating high-quality summaries for natural language processing applications, presenting an incremental hybrid method.
The authors tackled document summarization by proposing an Editorial Network that mimics human editing decisions to keep, rephrase, or reject extracted sentences, achieving improved performance over extractive-only and abstractive-only baselines on the CNN/DailyMail dataset.
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.