# Unsupervised Dialog Structure Learning

arXiv: https://arxiv.org/abs/1904.03736 · HTML: https://mlsanity.com/paper/1904.03736/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2019.

## Built on by (most cited first, 16 of 16)

- [DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues](https://mlsanity.com/paper/2106.00920/) (2021)
- [Schema-Guided Paradigm for Zero-Shot Dialog](https://mlsanity.com/paper/2106.07056/) (2021)
- [AnyTOD: A Programmable Task-Oriented Dialog System](https://mlsanity.com/paper/2212.09939/) (2022)
- [Unsupervised Conversation Disentanglement through Co-Training](https://mlsanity.com/paper/2109.03199/) (2021)
- [Structure Extraction in Task-Oriented Dialogues with Slot Clustering](https://mlsanity.com/paper/2203.00073/) (2022)
- [CTRLStruct: Dialogue Structure Learning for Open-Domain Response Generation](https://mlsanity.com/paper/2303.01094/) (2023)
- [Unsupervised Learning of Hierarchical Conversation Structure](https://mlsanity.com/paper/2205.12244/) (2022)
- [Using Domain Knowledge to Guide Dialog Structure Induction via Neural Probabilistic Soft Logic](https://mlsanity.com/paper/2403.17853/) (2024)
- [Turning Conversations into Workflows: A Framework to Extract and Evaluate Dialog Workflows for Service AI Agents](https://mlsanity.com/paper/2502.17321/) (2025)
- [Towards Efficient Dialogue Pre-training with Transferable and Interpretable Latent Structure](https://mlsanity.com/paper/2210.12461/) (2022)
- [DSBERT:Unsupervised Dialogue Structure learning with BERT](https://mlsanity.com/paper/2111.04933/) (2021)
- [Learning Interpretable Latent Dialogue Actions With Less Supervision](https://mlsanity.com/paper/2209.11128/) (2022)
- [Unsupervised Extraction of Dialogue Policies from Conversations](https://mlsanity.com/paper/2406.15214/) (2024)
- [Reinforcement Learning from Bagged Reward](https://mlsanity.com/paper/2402.03771/) (2024)
- [Only One Relation Possible? Modeling the Ambiguity in Event Temporal Relation Extraction](https://mlsanity.com/paper/2408.07353/) (2024)
- [Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents](https://mlsanity.com/paper/2607.06873/) (2026)

## Abstract (arXiv)

Learning a shared dialog structure from a set of task-oriented dialogs is an important challenge in computational linguistics. The learned dialog structure can shed light on how to analyze human dialogs, and more importantly contribute to the design and evaluation of dialog systems. We propose to extract dialog structures using a modified VRNN model with discrete latent vectors. Different from existing HMM-based models, our model is based on variational-autoencoder (VAE). Such model is able to capture more dynamics in dialogs beyond the surface forms of the language. We find that qualitatively, our method extracts meaningful dialog structure, and quantitatively, outperforms previous models on the ability to predict unseen data. We further evaluate the model's effectiveness in a downstream task, the dialog system building task. Experiments show that, by integrating the learned dialog structure into the reward function design, the model converges faster and to a better outcome in a reinforcement learning setting.