A Survey on Dialogue Summarization: Recent Advances and New Frontiers
Not on the map. Why?
Abstract (arXiv)
Dialogue summarization aims to condense the original dialogue into a shorter version covering salient information, which is a crucial way to reduce dialogue data overload. Recently, the promising achievements in both dialogue systems and natural language generation techniques drastically lead this task to a new landscape, which results in significant research attentions. However, there still remains a lack of a comprehensive survey for this task. To this end, we take the first step and present a thorough review of this research field carefully and widely. In detail, we systematically organize the current works according to the characteristics of each domain, covering meeting, chat, email thread, customer service and medical dialogue. Additionally, we provide an overview of publicly available research datasets as well as organize two leaderboards under unified metrics. Furthermore, we discuss some future directions, including faithfulness, multi-modal, multi-domain and multi-lingual dialogue summarization, and give our thoughts respectively. We hope that this first survey of dialogue summarization can provide the community with a quick access and a general picture to this task and motivate future researches.
Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). Builds on 57 of its 148 references that are in the map. First posted on arXiv 7 Jul 2021.
Builds on
57 of 148 references.
References · 57
- 2017Attention Is All You Needcited by 59,932
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
- 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
- 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,100
- 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
- 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 809
- 2019Unified Language Model Pre-training for Natural Language Understanding and Generationcited by 668
- 2019Text Summarization with Pretrained Encoderscited by 553
- 2019SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarizationcited by 530
- 2018A Discourse-Aware Attention Model for Abstractive Summarization of Long Documentscited by 477
38 more
- 2019MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distancecited by 415
- 2019A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protectioncited by 371
- 2021QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarizationcited by 363
- 2016SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documentscited by 245
- 2019Pay Less Attention with Lightweight and Dynamic Convolutionscited by 211
- 2021DialogSum: A Real-Life Scenario Dialogue Summarization Datasetcited by 181
- 2018Fast Abstractive Summarization with Reinforce-Selected Sentence Rewritingcited by 158
- 2021SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarizationcited by 131
- 2021MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarizationcited by 104
- 2021SummScreen: A Dataset for Abstractive Screenplay Summarizationcited by 80
- 2021The Factual Inconsistency Problem in Abstractive Text Summarization: A Surveycited by 79
- 2020GO FIGURE: A Meta Evaluation of Factuality in Summarizationcited by 75
- 2021Planning with Learned Entity Prompts for Abstractive Summarizationcited by 75
- 2020Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarizationcited by 72
- 2020Generating SOAP Notes from Doctor-Patient Conversations Using Modular Summarization Techniquescited by 64
- 2019This Email Could Save Your Life: Introducing the Task of Email Subject Line Generationcited by 58
- 2018Neural Document Summarization by Jointly Learning to Score and Select Sentencescited by 56
- 2021A Survey on Spoken Language Understanding: Recent Advances and New Frontierscited by 53
- 2021AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarizationcited by 51
- 2020Dr. Summarize: Global Summarization of Medical Dialogue by Exploiting Local Structurescited by 49
- 2018Unsupervised Abstractive Meeting Summarization with Multi-Sentence Compression and Budgeted Submodular Maximizationcited by 46
- 2021Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarizationcited by 46
- 2018Abstractive Dialogue Summarization with Sentence-Gated Modeling Optimized by Dialogue Actscited by 44
- 2020PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generationcited by 42
- 2019Topic-aware Pointer-Generator Networks for Summarizing Spoken Conversationscited by 41
- 2021ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive Summarization with Argument Miningcited by 37
- 2021Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphscited by 36
- 2021Coreference-Aware Dialogue Summarizationcited by 34
- 2021Hierarchical Learning for Generation with Long Source Sequencescited by 32
- 2020Dialogue Discourse-Aware Graph Model and Data Augmentation for Meeting Summarizationcited by 27
- 2021Controllable Abstractive Dialogue Summarization with Sketch Supervisioncited by 27
- 2021RefSum: Refactoring Neural Summarizationcited by 25
- 2020Topic-Oriented Spoken Dialogue Summarization for Customer Service with Saliency-Aware Topic Modelingcited by 23
- 2020Incorporating Commonsense Knowledge into Abstractive Dialogue Summarization via Heterogeneous Graph Networkscited by 22
- 2020Unsupervised Summarization for Chat Logs with Topic-Oriented Ranking and Context-Aware Auto-Encoderscited by 16
- 2020How Domain Terminology Affects Meeting Summarization Performancecited by 14
- 2021A Sliding-Window Approach to Automatic Creation of Meeting Minutescited by 14
- 2020Unsupervised Abstractive Dialogue Summarization for Tete-a-Tetescited by 12
50 most cited of 57 All 57 (JSON)
Built on by
Citing papers per year: 2021: 3; 2022: 20; 2023: 14; 2024: 7; 2025: 3; 2026: 4.
51 papers.
Sort:
By area:
- 2022Pretrained Language Models for Text Generation: A Surveycited by 121
- 2024A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methodscited by 101
- 2021DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarizationcited by 72
- 2021CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuningcited by 44
- 2022A Survey on Cross-Lingual Summarizationcited by 38
- 2023DialogBench: Evaluating LLMs as Human-like Dialogue Systemscited by 31
- 2022ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarizationcited by 25
- 2023Designerly Understanding: Information Needs for Model Transparency to Support Design Ideation for AI-Powered User Experiencecited by 18
- 2022A Survey on Medical Document Summarizationcited by 14
- 2022Other Roles Matter! Enhancing Role-Oriented Dialogue Summarization via Role Interactionscited by 13
- 2024Towards LifeSpan Cognitive Systemscited by 13
- 2022Analyzing and Evaluating Faithfulness in Dialogue Summarizationcited by 12
38 more
- 2023PULSAR at MEDIQA-Sum 2023: Large Language Models Augmented by Synthetic Dialogue Convert Patient Dialogues to Medical Recordscited by 11
- 2022Abstractive Meeting Summarization: A Surveycited by 9
- 2024What's under the hood: Investigating Automatic Metrics on Meeting Summarizationcited by 9
- 2022The Cross-lingual Conversation Summarization Challengecited by 8
- 2022Human-in-the-loop Abstractive Dialogue Summarizationcited by 8
- 2023Commonsense Reasoning for Conversational AI: A Survey of the State of the Artcited by 7
- 2023Multi-Stage Pre-training Enhanced by ChatGPT for Multi-Scenario Multi-Domain Dialogue Summarizationcited by 7
- 2022A Focused Study on Sequence Length for Dialogue Summarizationcited by 6
- 2022DIONYSUS: A Pre-trained Model for Low-Resource Dialogue Summarizationcited by 6
- 2023Adapter-based Selective Knowledge Distillation for Federated Multi-domain Meeting Summarizationcited by 6
- 2024Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selectioncited by 5
- 2022Post-Training Dialogue Summarization using Pseudo-Paraphrasingcited by 4
- 2023Discourse Structure Extraction from Pre-Trained and Fine-Tuned Language Models in Dialoguescited by 4
- 2021Dialogue Inspectional Summarization with Factual Inconsistency Awarenesscited by 3
- 2022Effectiveness of French Language Models on Abstractive Dialogue Summarization Taskcited by 3
- 2022Leveraging Non-dialogue Summaries for Dialogue Summarizationcited by 3
- 2022Taxonomy of Abstractive Dialogue Summarization: Scenarios, Approaches and Future Directionscited by 3
- 2022Meeting Summarization: A Survey of the State of the Artcited by 3
- 2022GOAL: Towards Benchmarking Few-Shot Sports Game Summarizationcited by 2
- 2022Towards Understanding Omission in Dialogue Summarizationcited by 2
- 2023Agreement Tracking for Multi-Issue Negotiation Dialoguescited by 2
- 2023Surveying the Landscape of Text Summarization with Deep Learning: A Comprehensive Reviewcited by 2
- 2023Action-Item-Driven Summarization of Long Meeting Transcriptscited by 2
- 2026MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversationcited by 2
- 2022TANet: Thread-Aware Pretraining for Abstractive Conversational Summarizationcited by 1
- 2023Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systemscited by 1
- 2025Layer-Specific Scaling of Positional Encodings for Superior Long-Context Modelingcited by 1
- 2022STRUDEL: Structured Dialogue Summarization for Dialogue Comprehensioncited by 0
- 2023Hi Model, generating 'nice' instead of 'good' is not as bad as generating 'rice'! Towards Context and Semantic Infused Dialogue Generation Loss Function and Evaluation Metriccited by 0
- 2023Evaluating Robustness of Dialogue Summarization Models in the Presence of Naturally Occurring Variationscited by 0
- 2023Picking the Underused Heads: A Network Pruning Perspective of Attention Head Selection for Fusing Dialogue Coreference Informationcited by 0
- 2024Instant Answering in E-Commerce Buyer-Seller Messaging using Message-to-Question Reformulationcited by 0
- 2024Unsupervised Extractive Dialogue Summarization in Hyperdimensional Spacecited by 0
- 2024Extra Global Attention Designation Using Keyword Detection in Sparse Transformer Architecturescited by 0
- 2025Minimal Clips, Maximum Salience: Long Video Summarization via Key Moment Extractioncited by 0
- 2025DASH: Dialogue-Aware Similarity and Handshake Recognition for Topic Segmentation in Public-Channel Conversationscited by 0
- 2026Structured Distillation for Personalized Agent Memory: 11x Token Reduction with Retrieval Preservationcited by 0
- 2026Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scalingcited by 0
50 most cited of 51 All 51 (JSON)
- 2026Dialogue Summarization with Emotion Dynamics Using Topic- and Participant-Centric Decomposition16 Jul 2026
- 2026Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling26 Jun 2026
- 2026MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversation9 Apr 2026
- 2026Structured Distillation for Personalized Agent Memory: 11x Token Reduction with Retrieval Preservation13 Mar 2026
- 2025DASH: Dialogue-Aware Similarity and Handshake Recognition for Topic Segmentation in Public-Channel Conversations17 Dec 2025
- 2025Minimal Clips, Maximum Salience: Long Video Summarization via Key Moment Extraction12 Dec 2025
- 2025Layer-Specific Scaling of Positional Encodings for Superior Long-Context Modeling6 Mar 2025
- 2024Extra Global Attention Designation Using Keyword Detection in Sparse Transformer Architectures11 Oct 2024
- 2024Towards LifeSpan Cognitive Systems20 Sep 2024
- 2024Unsupervised Extractive Dialogue Summarization in Hyperdimensional Space16 May 2024
- 2024What's under the hood: Investigating Automatic Metrics on Meeting Summarization17 Apr 2024
- 2024Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection6 Mar 2024
38 more
- 2024A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods5 Mar 2024
- 2024Instant Answering in E-Commerce Buyer-Seller Messaging using Message-to-Question Reformulation18 Jan 2024
- 2023Action-Item-Driven Summarization of Long Meeting Transcripts29 Dec 2023
- 2023Picking the Underused Heads: A Network Pruning Perspective of Attention Head Selection for Fusing Dialogue Coreference Information15 Dec 2023
- 2023Evaluating Robustness of Dialogue Summarization Models in the Presence of Naturally Occurring Variations15 Nov 2023
- 2023DialogBench: Evaluating LLMs as Human-like Dialogue Systems3 Nov 2023
- 2023Multi-Stage Pre-training Enhanced by ChatGPT for Multi-Scenario Multi-Domain Dialogue Summarization16 Oct 2023
- 2023Surveying the Landscape of Text Summarization with Deep Learning: A Comprehensive Review13 Oct 2023
- 2023Hi Model, generating 'nice' instead of 'good' is not as bad as generating 'rice'! Towards Context and Semantic Infused Dialogue Generation Loss Function and Evaluation Metric11 Sep 2023
- 2023Adapter-based Selective Knowledge Distillation for Federated Multi-domain Meeting Summarization7 Aug 2023
- 2023Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systems14 Jul 2023
- 2023Agreement Tracking for Multi-Issue Negotiation Dialogues13 Jul 2023
- 2023PULSAR at MEDIQA-Sum 2023: Large Language Models Augmented by Synthetic Dialogue Convert Patient Dialogues to Medical Records5 Jul 2023
- 2023Designerly Understanding: Information Needs for Model Transparency to Support Design Ideation for AI-Powered User Experience21 Feb 2023
- 2023Commonsense Reasoning for Conversational AI: A Survey of the State of the Art15 Feb 2023
- 2023Discourse Structure Extraction from Pre-Trained and Fine-Tuned Language Models in Dialogues12 Feb 2023
- 2022STRUDEL: Structured Dialogue Summarization for Dialogue Comprehension24 Dec 2022
- 2022DIONYSUS: A Pre-trained Model for Low-Resource Dialogue Summarization20 Dec 2022
- 2022Human-in-the-loop Abstractive Dialogue Summarization19 Dec 2022
- 2022Meeting Summarization: A Survey of the State of the Art16 Dec 2022
- 2022A Survey on Medical Document Summarization3 Dec 2022
- 2022Towards Understanding Omission in Dialogue Summarization14 Nov 2022
- 2022Analyzing and Evaluating Faithfulness in Dialogue Summarization21 Oct 2022
- 2022Taxonomy of Abstractive Dialogue Summarization: Scenarios, Approaches and Future Directions18 Oct 2022
- 2022Leveraging Non-dialogue Summaries for Dialogue Summarization17 Oct 2022
- 2022A Focused Study on Sequence Length for Dialogue Summarization24 Sep 2022
- 2022Abstractive Meeting Summarization: A Survey8 Aug 2022
- 2022GOAL: Towards Benchmarking Few-Shot Sports Game Summarization18 Jul 2022
- 2022Effectiveness of French Language Models on Abstractive Dialogue Summarization Task17 Jul 2022
- 2022Other Roles Matter! Enhancing Role-Oriented Dialogue Summarization via Role Interactions26 May 2022
- 2022The Cross-lingual Conversation Summarization Challenge1 May 2022
- 2022Post-Training Dialogue Summarization using Pseudo-Paraphrasing28 Apr 2022
- 2022TANet: Thread-Aware Pretraining for Abstractive Conversational Summarization9 Apr 2022
- 2022A Survey on Cross-Lingual Summarization23 Mar 2022
- 2022ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization11 Feb 2022
- 2022Pretrained Language Models for Text Generation: A Survey14 Jan 2022
- 2021CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuning16 Dec 2021
- 2021Dialogue Inspectional Summarization with Factual Inconsistency Awareness5 Nov 2021
50 newest of 51 All 51 (JSON)
- 2022Pretrained Language Models for Text Generation: A Surveycited by 121
- 2024A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methodscited by 101
- 2021DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarizationcited by 72
- 2021CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuningcited by 44
- 2022A Survey on Cross-Lingual Summarizationcited by 38
- 2023DialogBench: Evaluating LLMs as Human-like Dialogue Systemscited by 31
- 2022ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarizationcited by 25
- 2023Designerly Understanding: Information Needs for Model Transparency to Support Design Ideation for AI-Powered User Experiencecited by 18
- 2022A Survey on Medical Document Summarizationcited by 14
- 2022Other Roles Matter! Enhancing Role-Oriented Dialogue Summarization via Role Interactionscited by 13
- 2024Towards LifeSpan Cognitive Systemscited by 13
- 2022Analyzing and Evaluating Faithfulness in Dialogue Summarizationcited by 12
12 most cited of 47 All 47 (JSON)
- 2026Dialogue Summarization with Emotion Dynamics Using Topic- and Participant-Centric Decomposition16 Jul 2026
- 2026Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling26 Jun 2026
- 2026MT-OSC: Path for LLMs that Get Lost in Multi-Turn Conversation9 Apr 2026
- 2025DASH: Dialogue-Aware Similarity and Handshake Recognition for Topic Segmentation in Public-Channel Conversations17 Dec 2025
- 2025Layer-Specific Scaling of Positional Encodings for Superior Long-Context Modeling6 Mar 2025
- 2024Extra Global Attention Designation Using Keyword Detection in Sparse Transformer Architectures11 Oct 2024
- 2024Towards LifeSpan Cognitive Systems20 Sep 2024
- 2024Unsupervised Extractive Dialogue Summarization in Hyperdimensional Space16 May 2024
- 2024What's under the hood: Investigating Automatic Metrics on Meeting Summarization17 Apr 2024
- 2024Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection6 Mar 2024
- 2024A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods5 Mar 2024
- 2024Instant Answering in E-Commerce Buyer-Seller Messaging using Message-to-Question Reformulation18 Jan 2024
12 newest of 47 All 47 (JSON)