# Abstractive Dialog Summarization with Semantic Scaffolds

arXiv: https://arxiv.org/abs/1910.00825 · HTML: https://mlsanity.com/paper/1910.00825/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2019.

## Built on by (most cited first, 12 of 12)

- [MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarization](https://mlsanity.com/paper/2103.06410/) (2021)
- [CONFIT: Toward Faithful Dialogue Summarization with Linguistically-Informed Contrastive Fine-tuning](https://mlsanity.com/paper/2112.08713/) (2021)
- [ConvoSumm: Conversation Summarization Benchmark and Improved Abstractive Summarization with Argument Mining](https://mlsanity.com/paper/2106.00829/) (2021)
- [TWEETSUMM -- A Dialog Summarization Dataset for Customer Service](https://mlsanity.com/paper/2111.11894/) (2021)
- [TODSum: Task-Oriented Dialogue Summarization with State Tracking](https://mlsanity.com/paper/2110.12680/) (2021)
- [Dialogue Summarization with Supporting Utterance Flow Modeling and Fact Regularization](https://mlsanity.com/paper/2108.01268/) (2021)
- [Taxonomy of Abstractive Dialogue Summarization: Scenarios, Approaches and Future Directions](https://mlsanity.com/paper/2210.09894/) (2022)
- [Few-Shot Dialogue Summarization via Skeleton-Assisted Prompt Transfer in Prompt Tuning](https://mlsanity.com/paper/2305.12077/) (2023)
- [Who speaks like a style of Vitamin: Towards Syntax-Aware DialogueSummarization using Multi-task Learning](https://mlsanity.com/paper/2109.14199/) (2021)
- [TANet: Thread-Aware Pretraining for Abstractive Conversational Summarization](https://mlsanity.com/paper/2204.04504/) (2022)
- [Spot the BlindSpots: Systematic Identification and Quantification of Fine-Grained LLM Biases in Contact Center Summaries](https://mlsanity.com/paper/2508.13124/) (2025)
- [Evaluating Robustness of Dialogue Summarization Models in the Presence of Naturally Occurring Variations](https://mlsanity.com/paper/2311.08705/) (2023)

## Abstract (arXiv)

The demand for abstractive dialog summary is growing in real-world applications. For example, customer service center or hospitals would like to summarize customer service interaction and doctor-patient interaction. However, few researchers explored abstractive summarization on dialogs due to the lack of suitable datasets. We propose an abstractive dialog summarization dataset based on MultiWOZ. If we directly apply previous state-of-the-art document summarization methods on dialogs, there are two significant drawbacks: the informative entities such as restaurant names are difficult to preserve, and the contents from different dialog domains are sometimes mismatched. To address these two drawbacks, we propose Scaffold Pointer Network (SPNet)to utilize the existing annotation on speaker role, semantic slot and dialog domain. SPNet incorporates these semantic scaffolds for dialog summarization. Since ROUGE cannot capture the two drawbacks mentioned, we also propose a new evaluation metric that considers critical informative entities in the text. On MultiWOZ, our proposed SPNet outperforms state-of-the-art abstractive summarization methods on all the automatic and human evaluation metrics.