# Deep Communicating Agents for Abstractive Summarization

arXiv: https://arxiv.org/abs/1803.10357 · HTML: https://mlsanity.com/paper/1803.10357/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Mar 2018.

## Built on by (most cited first, 30 of 50)

- [QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization](https://mlsanity.com/paper/2104.05938/) (2021)
- [Efficient Attentions for Long Document Summarization](https://mlsanity.com/paper/2104.02112/) (2021)
- [A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models](https://mlsanity.com/paper/2201.05337/) (2022)
- [Advances and Challenges in Conversational Recommender Systems: A Survey](https://mlsanity.com/paper/2101.09459/) (2021)
- [An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics](https://mlsanity.com/paper/2207.00939/) (2022)
- [DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents](https://mlsanity.com/paper/2101.11796/) (2021)
- [CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning](https://mlsanity.com/paper/2112.08558/) (2021)
- [A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models](https://mlsanity.com/paper/2406.11289/) (2024)
- [Keep it Simple: Unsupervised Simplification of Multi-Paragraph Text](https://mlsanity.com/paper/2107.03444/) (2021)
- [Conditional Generation with a Question-Answering Blueprint](https://mlsanity.com/paper/2207.00397/) (2022)
- [Discrete Prompt Compression with Reinforcement Learning](https://mlsanity.com/paper/2308.08758/) (2023)
- [Hierarchical Learning for Generation with Long Source Sequences](https://mlsanity.com/paper/2104.07545/) (2021)
- [Towards Improving Faithfulness in Abstractive Summarization](https://mlsanity.com/paper/2210.01877/) (2022)
- [BASS: Boosting Abstractive Summarization with Unified Semantic Graph](https://mlsanity.com/paper/2105.12041/) (2021)
- [Faithful to the Document or to the World? Mitigating Hallucinations via Entity-linked Knowledge in Abstractive Summarization](https://mlsanity.com/paper/2204.13761/) (2022)
- [Data Augmentation for Abstractive Query-Focused Multi-Document Summarization](https://mlsanity.com/paper/2103.01863/) (2021)
- [Controllable Summarization with Constrained Markov Decision Process](https://mlsanity.com/paper/2108.03405/) (2021)
- [Abstractive Text Summarization: State of the Art, Challenges, and Improvements](https://mlsanity.com/paper/2409.02413/) (2024)
- [How well do you know your summarization datasets?](https://mlsanity.com/paper/2106.11388/) (2021)
- [ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generation](https://mlsanity.com/paper/2308.02223/) (2023)
- [A New Approach to Overgenerating and Scoring Abstractive Summaries](https://mlsanity.com/paper/2104.01726/) (2021)
- [Enriching Transformers with Structured Tensor-Product Representations for Abstractive Summarization](https://mlsanity.com/paper/2106.01317/) (2021)
- [Keep It Private: Unsupervised Privatization of Online Text](https://mlsanity.com/paper/2405.10260/) (2024)
- [Attention Head Masking for Inference Time Content Selection in Abstractive Summarization](https://mlsanity.com/paper/2104.02205/) (2021)
- [Rethinking Self-Supervision Objectives for Generalizable Coherence Modeling](https://mlsanity.com/paper/2110.07198/) (2021)
- [SgSum: Transforming Multi-document Summarization into Sub-graph Selection](https://mlsanity.com/paper/2110.12645/) (2021)
- [Unsupervised Deep Keyphrase Generation](https://mlsanity.com/paper/2104.08729/) (2021)
- [FCMNet: Full Communication Memory Net for Team-Level Cooperation in Multi-Agent Systems](https://mlsanity.com/paper/2201.11994/) (2022)
- [SummerTime: Text Summarization Toolkit for Non-experts](https://mlsanity.com/paper/2108.12738/) (2021)
- [Automatic Document Sketching: Generating Drafts from Analogous Texts](https://mlsanity.com/paper/2106.07192/) (2021)

## Abstract (arXiv)

We present deep communicating agents in an encoder-decoder architecture to address the challenges of representing a long document for abstractive summarization. With deep communicating agents, the task of encoding a long text is divided across multiple collaborating agents, each in charge of a subsection of the input text. These encoders are connected to a single decoder, trained end-to-end using reinforcement learning to generate a focused and coherent summary. Empirical results demonstrate that multiple communicating encoders lead to a higher quality summary compared to several strong baselines, including those based on a single encoder or multiple non-communicating encoders.