mlsanityData to 7 Oct 2026

Post-Training Dialogue Summarization using Pseudo-Paraphrasing

arXiv 2204.13498 ↗First posted 28 Apr 2022cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Previous dialogue summarization techniques adapt large language models pretrained on the narrative text by injecting dialogue-specific features into the models. These features either require additional knowledge to recognize or make the resulting models harder to tune. To bridge the format gap between dialogues and narrative summaries in dialogue summarization tasks, we propose to post-train pretrained language models (PLMs) to rephrase from dialogue to narratives. After that, the model is fine-tuned for dialogue summarization as usual. Comprehensive experiments show that our approach significantly improves vanilla PLMs on dialogue summarization and outperforms other SOTA models by the summary quality and implementation costs.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 24 of its 33 references that are in the map. First posted on arXiv 28 Apr 2022.

Builds on

24 of 33 references.

References · 24

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  4. 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
  5. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  6. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,100
  7. 2015Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Bookscited by 1,041
  8. 2019DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generationcited by 842
  9. 2019SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarizationcited by 530
  10. 2018A Discourse-Aware Attention Model for Abstractive Summarization of Long Documentscited by 477
  11. 2021DialogSum: A Real-Life Scenario Dialogue Summarization Datasetcited by 181
  12. 2018Fast Abstractive Summarization with Reinforce-Selected Sentence Rewritingcited by 158
12 more
  1. 2019PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variablecited by 145
  2. 2020Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarizationcited by 72
  3. 2018Neural Document Summarization by Jointly Learning to Score and Select Sentencescited by 56
  4. 2021A Survey on Dialogue Summarization: Recent Advances and New Frontierscited by 51
  5. 2021Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarizationcited by 46
  6. 2019A Repository of Conversational Datasetscited by 45
  7. 2018Abstractive Dialogue Summarization with Sentence-Gated Modeling Optimized by Dialogue Actscited by 44
  8. 2021ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive Summarization with Argument Miningcited by 37
  9. 2021Structure-Aware Abstractive Conversation Summarization via Discourse and Action Graphscited by 36
  10. 2021Coreference-Aware Dialogue Summarizationcited by 34
  11. 2021Controllable Abstractive Dialogue Summarization with Sketch Supervisioncited by 27
  12. 2021Topic-Aware Contrastive Learning for Abstractive Dialogue Summarizationcited by 23

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 1.

4 papers.

  1. 2022Human-in-the-loop Abstractive Dialogue Summarizationcited by 8
  2. 2023Multi-Stage Pre-training Enhanced by ChatGPT for Multi-Scenario Multi-Domain Dialogue Summarizationcited by 7
  3. 2022DIONYSUS: A Pre-trained Model for Low-Resource Dialogue Summarizationcited by 6
  4. 2022Taxonomy of Abstractive Dialogue Summarization: Scenarios, Approaches and Future Directionscited by 3