# Structured Attention for Unsupervised Dialogue Structure Induction

arXiv: https://arxiv.org/abs/2009.08552 · HTML: https://mlsanity.com/paper/2009.08552/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2020.

## Built on by (most cited first, 19 of 19)

- [Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey](https://mlsanity.com/paper/2105.04387/) (2021)
- [Towards Socially Intelligent Agents with Mental State Transition and Human Utility](https://mlsanity.com/paper/2103.07011/) (2021)
- [Schema-Guided Paradigm for Zero-Shot Dialog](https://mlsanity.com/paper/2106.07056/) (2021)
- [SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues](https://mlsanity.com/paper/2106.01006/) (2021)
- [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)
- [Dialog2Flow: Pre-training Soft-Contrastive Action-Driven Sentence Embeddings for Automatic Dialog Flow Extraction](https://mlsanity.com/paper/2410.18481/) (2024)
- [Using Domain Knowledge to Guide Dialog Structure Induction via Neural Probabilistic Soft Logic](https://mlsanity.com/paper/2403.17853/) (2024)
- [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)
- [DialogQAE: N-to-N Question Answer Pair Extraction from Customer Service Chatlog](https://mlsanity.com/paper/2212.07112/) (2022)
- [TSCAN : Dialog Structure discovery using SCAN](https://mlsanity.com/paper/2107.06426/) (2021)
- [What Did You Say? Task-Oriented Dialog Datasets Are Not Conversational!?](https://mlsanity.com/paper/2203.03431/) (2022)
- [CatVRNN: Generating Category Texts via Multi-task Learning](https://mlsanity.com/paper/2107.05219/) (2021)
- [Data Augmentation for Improving Tail-traffic Robustness in Skill-routing for Dialogue Systems](https://mlsanity.com/paper/2306.04823/) (2023)
- [Towards Automatic Evaluation of Task-Oriented Dialogue Flows](https://mlsanity.com/paper/2411.10416/) (2024)
- [A Multi-view Discourse Framework for Integrating Semantic and Syntactic Features in Dialog Agents](https://mlsanity.com/paper/2504.09073/) (2025)
- [The Graph Language: How Knowledge Graphs Speak to Large Language Models](https://mlsanity.com/paper/2608.01175/) (2026)

## Abstract (arXiv)

Inducing a meaningful structural representation from one or a set of dialogues is a crucial but challenging task in computational linguistics. Advancement made in this area is critical for dialogue system design and discourse analysis. It can also be extended to solve grammatical inference. In this work, we propose to incorporate structured attention layers into a Variational Recurrent Neural Network (VRNN) model with discrete latent states to learn dialogue structure in an unsupervised fashion. Compared to a vanilla VRNN, structured attention enables a model to focus on different parts of the source sentence embeddings while enforcing a structural inductive bias. Experiments show that on two-party dialogue datasets, VRNN with structured attention learns semantic structures that are similar to templates used to generate this dialogue corpus. While on multi-party dialogue datasets, our model learns an interactive structure demonstrating its capability of distinguishing speakers or addresses, automatically disentangling dialogues without explicit human annotation.