# MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes

arXiv: https://arxiv.org/abs/2107.08929 · HTML: https://mlsanity.com/paper/2107.08929/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 46 references that are in the map.
- First posted on arXiv 19 Jul 2021.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Teaching Machines to Read and Comprehend](https://mlsanity.com/paper/1506.03340/) (2015)
- [Text Summarization with Pretrained Encoders](https://mlsanity.com/paper/1908.08345/) (2019)
- [A Discourse-Aware Attention Model for Abstractive Summarization of Long Documents](https://mlsanity.com/paper/1804.05685/) (2018)
- [Efficient Attentions for Long Document Summarization](https://mlsanity.com/paper/2104.02112/) (2021)
- [Generating Wikipedia by Summarizing Long Sequences](https://mlsanity.com/paper/1801.10198/) (2018)
- [SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents](https://mlsanity.com/paper/1611.04230/) (2016)
- [Beam Search Strategies for Neural Machine Translation](https://mlsanity.com/paper/1702.01806/) (2017)
- [Extractive Summarization as Text Matching](https://mlsanity.com/paper/2004.08795/) (2020)
- [Hierarchical Transformers for Multi-Document Summarization](https://mlsanity.com/paper/1905.13164/) (2019)
- [Ranking Sentences for Extractive Summarization with Reinforcement Learning](https://mlsanity.com/paper/1802.08636/) (2018)
- [HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization](https://mlsanity.com/paper/1905.06566/) (2019)
- [Unsupervised Learning of Sentence Embeddings using Compositional n-Gram Features](https://mlsanity.com/paper/1703.02507/) (2017)
- [On Extractive and Abstractive Neural Document Summarization with Transformer Language Models](https://mlsanity.com/paper/1909.03186/) (2019)
- [Learning to Extract Coherent Summary via Deep Reinforcement Learning](https://mlsanity.com/paper/1804.07036/) (2018)
- [Extractive Summarization of Long Documents by Combining Global and Local Context](https://mlsanity.com/paper/1909.08089/) (2019)
- [Neural Document Summarization by Jointly Learning to Score and Select Sentences](https://mlsanity.com/paper/1807.02305/) (2018)
- [BanditSum: Extractive Summarization as a Contextual Bandit](https://mlsanity.com/paper/1809.09672/) (2018)
- [A Hierarchical Structured Self-Attentive Model for Extractive Document Summarization (HSSAS)](https://mlsanity.com/paper/1805.07799/) (2018)
- [Improving Abstractive Text Summarization with History Aggregation](https://mlsanity.com/paper/1912.11046/) (2019)

## Built on by (most cited first, 19 of 19)

- [Prompted Opinion Summarization with GPT-3.5](https://mlsanity.com/paper/2211.15914/) (2022)
- [Scientific Opinion Summarization: Paper Meta-review Generation Dataset, Methods, and Evaluation](https://mlsanity.com/paper/2305.14647/) (2023)
- [Text summarization via global structure awareness](https://mlsanity.com/paper/2602.09821/) (2026)
- [GoSum: Extractive Summarization of Long Documents by Reinforcement Learning and Graph Organized discourse state](https://mlsanity.com/paper/2211.10247/) (2022)
- [Legal Extractive Summarization of U.S. Court Opinions](https://mlsanity.com/paper/2305.08428/) (2023)
- [Cross-lingual Cross-temporal Summarization: Dataset, Models, Evaluation](https://mlsanity.com/paper/2306.12916/) (2023)
- [Hybrid Long Document Summarization using C2F-FAR and ChatGPT: A Practical Study](https://mlsanity.com/paper/2306.01169/) (2023)
- [SciLit: A Platform for Joint Scientific Literature Discovery, Summarization and Citation Generation](https://mlsanity.com/paper/2306.03535/) (2023)
- [PostDoc: Generating Poster from a Long Multimodal Document Using Deep Submodular Optimization](https://mlsanity.com/paper/2405.20213/) (2024)
- [EDU-level Extractive Summarization with Varying Summary Lengths](https://mlsanity.com/paper/2210.04029/) (2022)
- [Incremental Extractive Opinion Summarization Using Cover Trees](https://mlsanity.com/paper/2401.08047/) (2024)
- [Hierarchical Attention Graph for Scientific Document Summarization in Global and Local Level](https://mlsanity.com/paper/2405.10202/) (2024)
- [Enhancing Coherence of Extractive Summarization with Multitask Learning](https://mlsanity.com/paper/2305.12851/) (2023)
- [MemSum-DQA: Adapting An Efficient Long Document Extractive Summarizer for Document Question Answering](https://mlsanity.com/paper/2310.06436/) (2023)
- [A Cascaded Architecture for Extractive Summarization of Multimedia Content via Audio-to-Text Alignment](https://mlsanity.com/paper/2504.06275/) (2025)
- [From Similarity to Structure: Training-free LLM Context Compression with Hybrid Graph Priors](https://mlsanity.com/paper/2604.23277/) (2026)
- [Modeling Unified Semantic Discourse Structure for High-quality Headline Generation](https://mlsanity.com/paper/2403.15776/) (2024)
- [Policy Learning with a Natural Language Action Space: A Causal Approach](https://mlsanity.com/paper/2502.17538/) (2025)
- [RH-RAG: Trustworthy Long-Form Generation for Privacy-Constrained Settings](https://mlsanity.com/paper/2608.01311/) (2026)

## Abstract (arXiv)

We introduce MemSum (Multi-step Episodic Markov decision process extractive SUMmarizer), a reinforcement-learning-based extractive summarizer enriched at each step with information on the current extraction history. When MemSum iteratively selects sentences into the summary, it considers a broad information set that would intuitively also be used by humans in this task: 1) the text content of the sentence, 2) the global text context of the rest of the document, and 3) the extraction history consisting of the set of sentences that have already been extracted. With a lightweight architecture, MemSum obtains state-of-the-art test-set performance (ROUGE) in summarizing long documents taken from PubMed, arXiv, and GovReport. Ablation studies demonstrate the importance of local, global, and history information. A human evaluation confirms the high quality and low redundancy of the generated summaries, stemming from MemSum's awareness of extraction history.