# Unsupervised Dialogue Act Induction using Gaussian Mixtures

arXiv: https://arxiv.org/abs/1612.06572 · HTML: https://mlsanity.com/paper/1612.06572/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Dec 2016.

## Built on by (most cited first, 6 of 6)

- [Learning Discriminative Representations and Decision Boundaries for Open Intent Detection](https://mlsanity.com/paper/2203.05823/) (2022)
- [Workflow Discovery from Dialogues in the Low Data Regime](https://mlsanity.com/paper/2205.11690/) (2022)
- [Unsupervised Learning of Hierarchical Conversation Structure](https://mlsanity.com/paper/2205.12244/) (2022)
- [Learning Interpretable Latent Dialogue Actions With Less Supervision](https://mlsanity.com/paper/2209.11128/) (2022)
- [Learning Better Intent Representations for Financial Open Intent Classification](https://mlsanity.com/paper/2210.14304/) (2022)
- [Effective Open Intent Classification with K-center Contrastive Learning and Adjustable Decision Boundary](https://mlsanity.com/paper/2304.10220/) (2023)

## Abstract (arXiv)

This paper introduces a new unsupervised approach for dialogue act induction. Given the sequence of dialogue utterances, the task is to assign them the labels representing their function in the dialogue. Utterances are represented as real-valued vectors encoding their meaning. We model the dialogue as Hidden Markov model with emission probabilities estimated by Gaussian mixtures. We use Gibbs sampling for posterior inference. We present the results on the standard Switchboard-DAMSL corpus. Our algorithm achieves promising results compared with strong supervised baselines and outperforms other unsupervised algorithms.