Zum Inhalt springenZur Suche springen

Aktuelle Lehrveranstaltungen

Spoken Dialogue Systems

Wintersemester 2021/22

Der Kurs wird zentral über das ILIAS verwaltet. Hier werden auch alle aktuellen Ankündigungen mitgeteilt.

Lehrveranstaltungen:

13.10.2021 bis 02.02.2022

  • Vorlesung: 2 SWS, mittwochs 14:30 – 16:00 Uhr, digital
  • Übung: 2 SWS, mittwochs 16:30 – 18:00 Uhr, digital

Dozent:in:

Studiengang:

  • Master-Studiengang Informatik (PO 2005, PO 2015)
  • Master-Studiengang Artificial Intelligence and Data Science (PO 2019, PO 2021)

Leistungspunkte:

  • 5 LP

Sprache:

  • Englisch

Inhalte Vorlesung:

  • Introduction: Architecture of a spoken dialogue system, dialogue acts, turn management issues
  • Semantic decoding: Representing and decoding meaning from user inputs, semantic decoding as a classification task, semantic decoding as a sequence-to-sequence learning task
  • Dialogue state tracking: Tracking beliefs over multiple turns, classical generative and discriminative approaches, recent deep learning approaches, integration of decoding and tracking
  • Dialogue Management: Modelling via Markov Decision Processes, reinforcement learning, gradient methods, Gaussian Processes
  • Response Generation: Template methods, generative models, recent neural network approaches
  • Current research topics: Incremental dialogue, towards open-domain systems, end-to-end neural network architectures

Inhalte Übung:

Students will be provided with a set of Python tools which will enable them to configure and test a simple spoken dialogue system. They will be asked to implement a simple dialogue state tracker and a reinforcementlearning algorithm and optimize the dialogue manager in interaction with a simulated user. This will give them an opportunity to explore a practical example of reinforcement learning.

 

Verantwortlichkeit: