# TSCAN : Dialog Structure discovery using SCAN

arXiv: https://arxiv.org/abs/2107.06426 · HTML: https://mlsanity.com/paper/2107.06426/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 15 references that are in the map.
- First posted on arXiv 13 Jul 2021.

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

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Self-Supervised Learning of Pretext-Invariant Representations](https://mlsanity.com/paper/1912.01991/) (2019)
- [Self-labelling via simultaneous clustering and representation learning](https://mlsanity.com/paper/1911.05371/) (2019)
- [SCAN: Learning to Classify Images without Labels](https://mlsanity.com/paper/2005.12320/) (2020)
- [Neural Belief Tracker: Data-Driven Dialogue State Tracking](https://mlsanity.com/paper/1606.03777/) (2016)
- [Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Tracking](https://mlsanity.com/paper/2004.03386/) (2020)
- [Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation](https://mlsanity.com/paper/1909.00754/) (2019)
- [Structured Attention for Unsupervised Dialogue Structure Induction](https://mlsanity.com/paper/2009.08552/) (2020)
- [Jointly Optimizing State Operation Prediction and Value Generation for Dialogue State Tracking](https://mlsanity.com/paper/2010.14061/) (2020)
- [Discovering Dialog Structure Graph for Open-Domain Dialog Generation](https://mlsanity.com/paper/2012.15543/) (2020)

## Built on by (most cited first, 2 of 2)

- [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)

## Abstract (arXiv)

Can we discover dialog structure by dividing utterances into labelled clusters. Can these labels be generated from the data. Typically for dialogs we need an ontology and use that to discover structure, however by using unsupervised classification and self-labelling we are able to intuit this structure without any labels or ontology. In this paper we apply SCAN (Semantic Clustering using Nearest Neighbors) to dialog data. We used BERT for pretext task and an adaptation of SCAN for clustering and self labeling. These clusters are used to identify transition probabilities and create the dialog structure. The self-labelling method used for SCAN makes these structures interpretable as every cluster has a label. As the approach is unsupervised, evaluation metrics is a challenge, we use statistical measures as proxies for structure quality