# Unsupervised Flow Discovery from Task-oriented Dialogues

arXiv: https://arxiv.org/abs/2405.01403 · HTML: https://mlsanity.com/paper/2405.01403/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 19 references that are in the map.
- First posted on arXiv 2 May 2024.

## Builds on (most cited first, 7 of 7)

- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines](https://mlsanity.com/paper/2007.12720/) (2020)
- [A Neural Conversational Model](https://mlsanity.com/paper/1506.05869/) (2015)
- [Discovering New Intents with Deep Aligned Clustering](https://mlsanity.com/paper/2012.08987/) (2020)
- [Open Intent Discovery through Unsupervised Semantic Clustering and Dependency Parsing](https://mlsanity.com/paper/2104.12114/) (2021)
- [Knowledge-Grounded Dialogue Flow Management for Social Robots and Conversational Agents](https://mlsanity.com/paper/2108.02174/) (2021)
- [Analysis of Utterance Embeddings and Clustering Methods Related to Intent Induction for Task-Oriented Dialogue](https://mlsanity.com/paper/2212.02021/) (2022)

## Built on by (most cited first, 1 of 1)

- [A Computational Approach to Modeling Conversational Systems: Analyzing Large-Scale Quasi-Patterned Dialogue Flows](https://mlsanity.com/paper/2507.13544/) (2025)

## Abstract (arXiv)

The design of dialogue flows is a critical but time-consuming task when developing task-oriented dialogue (TOD) systems. We propose an approach for the unsupervised discovery of flows from dialogue history, thus making the process applicable to any domain for which such an history is available. Briefly, utterances are represented in a vector space and clustered according to their semantic similarity. Clusters, which can be seen as dialogue states, are then used as the vertices of a transition graph for representing the flows visually. We present concrete examples of flows, discovered from MultiWOZ, a public TOD dataset. We further elaborate on their significance and relevance for the underlying conversations and introduce an automatic validation metric for their assessment. Experimental results demonstrate the potential of the proposed approach for extracting meaningful flows from task-oriented conversations.