# Jointly Extracting and Compressing Documents with Summary State Representations

arXiv: https://arxiv.org/abs/1904.02020 · HTML: https://mlsanity.com/paper/1904.02020/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2019.

## Built on by (most cited first, 12 of 12)

- [Time Waits for No One! Analysis and Challenges of Temporal Misalignment](https://mlsanity.com/paper/2111.07408/) (2021)
- [What's in a Summary? Laying the Groundwork for Advances in Hospital-Course Summarization](https://mlsanity.com/paper/2105.00816/) (2021)
- [Multiplex Graph Neural Network for Extractive Text Summarization](https://mlsanity.com/paper/2108.12870/) (2021)
- [A Character-Level Length-Control Algorithm for Non-Autoregressive Sentence Summarization](https://mlsanity.com/paper/2205.14522/) (2022)
- [Generating EDU Extracts for Plan-Guided Summary Re-Ranking](https://mlsanity.com/paper/2305.17779/) (2023)
- [SgSum: Transforming Multi-document Summarization into Sub-graph Selection](https://mlsanity.com/paper/2110.12645/) (2021)
- [EASE: Extractive-Abstractive Summarization with Explanations](https://mlsanity.com/paper/2105.06982/) (2021)
- [Abstractive Summarization Guided by Latent Hierarchical Document Structure](https://mlsanity.com/paper/2211.09458/) (2022)
- [RoLargeSum: A Large Dialect-Aware Romanian News Dataset for Summary, Headline, and Keyword Generation](https://mlsanity.com/paper/2412.11317/) (2024)
- [Supervising the Centroid Baseline for Extractive Multi-Document Summarization](https://mlsanity.com/paper/2311.17771/) (2023)
- [Efficient and Interpretable Compressive Text Summarisation with Unsupervised Dual-Agent Reinforcement Learning](https://mlsanity.com/paper/2306.03415/) (2023)
- [Extract-and-Abstract: Unifying Extractive and Abstractive Summarization within Single Encoder-Decoder Framework](https://mlsanity.com/paper/2409.11827/) (2024)

## Abstract (arXiv)

We present a new neural model for text summarization that first extracts sentences from a document and then compresses them. The proposed model offers a balance that sidesteps the difficulties in abstractive methods while generating more concise summaries than extractive methods. In addition, our model dynamically determines the length of the output summary based on the gold summaries it observes during training and does not require length constraints typical to extractive summarization. The model achieves state-of-the-art results on the CNN/DailyMail and Newsroom datasets, improving over current extractive and abstractive methods. Human evaluations demonstrate that our model generates concise and informative summaries. We also make available a new dataset of oracle compressive summaries derived automatically from the CNN/DailyMail reference summaries.