# Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting

arXiv: https://arxiv.org/abs/1805.11080 · HTML: https://mlsanity.com/paper/1805.11080/

## Key facts

- Cited by 158 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2018.

## Built on by (most cited first, 30 of 158)

- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [Benchmarking Large Language Models for News Summarization](https://mlsanity.com/paper/2301.13848/) (2023)
- [QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization](https://mlsanity.com/paper/2104.05938/) (2021)
- [BookSum: A Collection of Datasets for Long-form Narrative Summarization](https://mlsanity.com/paper/2105.08209/) (2021)
- [A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation](https://mlsanity.com/paper/2104.08704/) (2021)
- [Understanding Factual Errors in Summarization: Errors, Summarizers, Datasets, Error Detectors](https://mlsanity.com/paper/2205.12854/) (2022)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Evaluating the Factual Consistency of Large Language Models Through News Summarization](https://mlsanity.com/paper/2211.08412/) (2022)
- [Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback](https://mlsanity.com/paper/2306.00186/) (2023)
- [Can We Automate Scientific Reviewing?](https://mlsanity.com/paper/2102.00176/) (2021)
- [AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization](https://mlsanity.com/paper/2103.11332/) (2021)
- [A Survey on Dialogue Summarization: Recent Advances and New Frontiers](https://mlsanity.com/paper/2107.03175/) (2021)
- [Compilable Neural Code Generation with Compiler Feedback](https://mlsanity.com/paper/2203.05132/) (2022)
- [Exploring Neural Models for Query-Focused Summarization](https://mlsanity.com/paper/2112.07637/) (2021)
- [CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuning](https://mlsanity.com/paper/2112.08713/) (2021)
- [Prompted Opinion Summarization with GPT-3.5](https://mlsanity.com/paper/2211.15914/) (2022)
- [Finding a Balanced Degree of Automation for Summary Evaluation](https://mlsanity.com/paper/2109.11503/) (2021)
- [Automatic Text Evaluation through the Lens of Wasserstein Barycenters](https://mlsanity.com/paper/2108.12463/) (2021)
- [Efficient (Soft) Q-Learning for Text Generation with Limited Good Data](https://mlsanity.com/paper/2106.07704/) (2021)
- [What's in a Summary? Laying the Groundwork for Advances in Hospital-Course Summarization](https://mlsanity.com/paper/2105.00816/) (2021)
- [Data-to-text Generation with Macro Planning](https://mlsanity.com/paper/2102.02723/) (2021)
- [Coreference-Aware Dialogue Summarization](https://mlsanity.com/paper/2106.08556/) (2021)
- [DYLE: Dynamic Latent Extraction for Abstractive Long-Input Summarization](https://mlsanity.com/paper/2110.08168/) (2021)
- [InfoLM: A New Metric to Evaluate Summarization & Data2Text Generation](https://mlsanity.com/paper/2112.01589/) (2021)
- [Bidimensional Leaderboards: Generate and Evaluate Language Hand in Hand](https://mlsanity.com/paper/2112.04139/) (2021)
- [Extractive is not Faithful: An Investigation of Broad Unfaithfulness Problems in Extractive Summarization](https://mlsanity.com/paper/2209.03549/) (2022)
- [Toward Unifying Text Segmentation and Long Document Summarization](https://mlsanity.com/paper/2210.16422/) (2022)
- [The Summary Loop: Learning to Write Abstractive Summaries Without Examples](https://mlsanity.com/paper/2105.05361/) (2021)
- [Controllable Abstractive Dialogue Summarization with Sketch Supervision](https://mlsanity.com/paper/2105.14064/) (2021)
- [CSDS: A Fine-Grained Chinese Dataset for Customer Service Dialogue Summarization](https://mlsanity.com/paper/2108.13139/) (2021)

## Abstract (arXiv)

Inspired by how humans summarize long documents, we propose an accurate and fast summarization model that first selects salient sentences and then rewrites them abstractively (i.e., compresses and paraphrases) to generate a concise overall summary. We use a novel sentence-level policy gradient method to bridge the non-differentiable computation between these two neural networks in a hierarchical way, while maintaining language fluency. Empirically, we achieve the new state-of-the-art on all metrics (including human evaluation) on the CNN/Daily Mail dataset, as well as significantly higher abstractiveness scores. Moreover, by first operating at the sentence-level and then the word-level, we enable parallel decoding of our neural generative model that results in substantially faster (10-20x) inference speed as well as 4x faster training convergence than previous long-paragraph encoder-decoder models. We also demonstrate the generalization of our model on the test-only DUC-2002 dataset, where we achieve higher scores than a state-of-the-art model.