# Unsupervised Learning of Hierarchical Conversation Structure

arXiv: https://arxiv.org/abs/2205.12244 · HTML: https://mlsanity.com/paper/2205.12244/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 42 references that are in the map.
- First posted on arXiv 24 May 2022.

## Builds on (most cited first, 18 of 18)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Decoupling Strategy and Generation in Negotiation Dialogues](https://mlsanity.com/paper/1808.09637/) (2018)
- [Hierarchical Transformers for Long Document Classification](https://mlsanity.com/paper/1910.10781/) (2019)
- [Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2104.00783/) (2021)
- [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)
- [DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues](https://mlsanity.com/paper/2106.00920/) (2021)
- [Augmenting Non-Collaborative Dialog Systems with Explicit Semantic and Strategic Dialog History](https://mlsanity.com/paper/1909.13425/) (2019)
- [Pomegranate: fast and flexible probabilistic modeling in python](https://mlsanity.com/paper/1711.00137/) (2017)
- [Unsupervised Dialog Structure Learning](https://mlsanity.com/paper/1904.03736/) (2019)
- [Hierarchical Transformer for Task Oriented Dialog Systems](https://mlsanity.com/paper/2011.08067/) (2020)
- [Unsupervised Dialogue Act Induction using Gaussian Mixtures](https://mlsanity.com/paper/1612.06572/) (2016)

## Built on by (most cited first, 5 of 5)

- [Turning Conversations into Workflows: A Framework to Extract and Evaluate Dialog Workflows for Service AI Agents](https://mlsanity.com/paper/2502.17321/) (2025)
- [Multimodal Conversation Structure Understanding](https://mlsanity.com/paper/2505.17536/) (2025)
- [Unsupervised Extraction of Dialogue Policies from Conversations](https://mlsanity.com/paper/2406.15214/) (2024)
- [Subversive Characters and Stereotyping Readers: Characterizing Queer Relationalities with Dialogue-Based Relation Extraction](https://mlsanity.com/paper/2410.14978/) (2024)
- [CoDial: Interpretable Task-Oriented Dialogue Systems Through Dialogue Flow Alignment](https://mlsanity.com/paper/2506.02264/) (2025)

## Abstract (arXiv)

Human conversations can evolve in many different ways, creating challenges for automatic understanding and summarization. Goal-oriented conversations often have meaningful sub-dialogue structure, but it can be highly domain-dependent. This work introduces an unsupervised approach to learning hierarchical conversation structure, including turn and sub-dialogue segment labels, corresponding roughly to dialogue acts and sub-tasks, respectively. The decoded structure is shown to be useful in enhancing neural models of language for three conversation-level understanding tasks. Further, the learned finite-state sub-dialogue network is made interpretable through automatic summarization.