Year: 2017
Type: conference-paper
Abstract: 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.
DOI: 10.18653/v1/e17-2078
Authors: Tomáš Brychcín, Pavel Král
Institution: University of West Bohemia in Pilsen
Language: English
Topic: Speech and dialogue systems
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2583461040