# A Bag of Tricks for Dialogue Summarization

arXiv: https://arxiv.org/abs/2109.08232 · HTML: https://mlsanity.com/paper/2109.08232/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 28 references that are in the map.
- First posted on arXiv 16 Sep 2021.

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://mlsanity.com/paper/1912.08777/) (2019)
- [Personalizing Dialogue Agents: I have a dog, do you have pets too?](https://mlsanity.com/paper/1801.07243/) (2018)
- [SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization](https://mlsanity.com/paper/1911.12237/) (2019)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [A Corpus and Evaluation Framework for Deeper Understanding of Commonsense Stories](https://mlsanity.com/paper/1604.01696/) (2016)
- [Multi-View Sequence-to-Sequence Models with Conversational Structure for Abstractive Dialogue Summarization](https://mlsanity.com/paper/2010.01672/) (2020)
- [Unsupervised Abstractive Meeting Summarization with Multi-Sentence Compression and Budgeted Submodular Maximization](https://mlsanity.com/paper/1805.05271/) (2018)
- [Abstractive Dialogue Summarization with Sentence-Gated Modeling Optimized by Dialogue Acts](https://mlsanity.com/paper/1809.05715/) (2018)
- [ANA at SemEval-2020 Task 4: mUlti-task learNIng for cOmmonsense reasoNing (UNION)](https://mlsanity.com/paper/2006.16403/) (2020)

## Built on by (most cited first, 13 of 13)

- [ArgLegalSumm: Improving Abstractive Summarization of Legal Documents with Argument Mining](https://mlsanity.com/paper/2209.01650/) (2022)
- [Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Tracking](https://mlsanity.com/paper/2203.01552/) (2022)
- [Summaries, Highlights, and Action items: Design, implementation and evaluation of an LLM-powered meeting recap system](https://mlsanity.com/paper/2307.15793/) (2023)
- [NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization](https://mlsanity.com/paper/2505.24575/) (2025)
- [Towards Argument-Aware Abstractive Summarization of Long Legal Opinions with Summary Reranking](https://mlsanity.com/paper/2306.00672/) (2023)
- [What's Wrong? Refining Meeting Summaries with LLM Feedback](https://mlsanity.com/paper/2407.11919/) (2024)
- [Enhancing Dialogue Summarization with Topic-Aware Global- and Local- Level Centrality](https://mlsanity.com/paper/2301.12376/) (2023)
- [Summarizing Speech: A Comprehensive Survey](https://mlsanity.com/paper/2504.08024/) (2025)
- [Leveraging Non-dialogue Summaries for Dialogue Summarization](https://mlsanity.com/paper/2210.09474/) (2022)
- [Taxonomy of Abstractive Dialogue Summarization: Scenarios, Approaches and Future Directions](https://mlsanity.com/paper/2210.09894/) (2022)
- [He Said, She Said: Style Transfer for Shifting the Perspective of Dialogues](https://mlsanity.com/paper/2210.15462/) (2022)
- [Reducing Sensitivity on Speaker Names for Text Generation from Dialogues](https://mlsanity.com/paper/2305.13833/) (2023)
- [ReflectSumm: A Benchmark for Course Reflection Summarization](https://mlsanity.com/paper/2403.19012/) (2024)

## Abstract (arXiv)

Dialogue summarization comes with its own peculiar challenges as opposed to news or scientific articles summarization. In this work, we explore four different challenges of the task: handling and differentiating parts of the dialogue belonging to multiple speakers, negation understanding, reasoning about the situation, and informal language understanding. Using a pretrained sequence-to-sequence language model, we explore speaker name substitution, negation scope highlighting, multi-task learning with relevant tasks, and pretraining on in-domain data. Our experiments show that our proposed techniques indeed improve summarization performance, outperforming strong baselines.