SubjectsSubjects(version: 953)
Course, academic year 2023/2024
   Login via CAS
Statistical Dialogue Systems - NPFL099
Title: Statistické dialogové systémy
Guaranteed by: Institute of Formal and Applied Linguistics (32-UFAL)
Faculty: Faculty of Mathematics and Physics
Actual: from 2021
Semester: winter
E-Credits: 4
Hours per week, examination: winter s.:2/1, C+Ex [HT]
Capacity: unlimited
Min. number of students: unlimited
4EU+: no
Virtual mobility / capacity: no
State of the course: taught
Language: English, Czech
Teaching methods: full-time
Teaching methods: full-time
Additional information:
Guarantor: Mgr. et Mgr. Ondřej Dušek, Ph.D.
Incompatibility : NPFX099
Interchangeability : NPFX099
Is incompatible with: NPFX099
Is interchangeable with: NPFX099
Annotation -
This course will present advanced problems and current state-of-the-art in the field of dialogue systems, voice assistants, and conversational systems (chatbots). After a brief introduction into the topic, the course will focus mainly on the application of machine learning – especially deep learning/neural networks – in the individual components of the traditional dialogue system architecture as well as in end-to-end approaches (joining multiple components together). This course is a loose follow up to the course NPFL123 Dialogue Systems, but can be taken independently.
Last update: Vidová Hladká Barbora, doc. Mgr., Ph.D. (25.01.2019)
Course completion requirements -

Passing the final exam (written test based on the contents of lectures), finishing lab session homeworks (implementation of machine learning models for dialogue systems).

Last update: Vidová Hladká Barbora, doc. Mgr., Ph.D. (13.05.2019)
Literature -
  • McTear: Conversational AI: Dialogue Systems, Conversational Agents, and Chatbots. Morgan & Claypool 2021.
  • Jurafsky & Martin: Speech & Language processing. 3rd ed. draft, Chapter 24-25,
  • Lemon & Pietquin (eds.): Data-Driven Methods for Adaptive Spoken Dialogue Systems. Springer 2012.
  • Rieser & Lemon: Reinforcement learning for adaptive dialogue systems. Springer 2011.
  • Jokinen & McTear: Spoken dialogue systems. Morgan & Claypool 2010.
  • McTear et al.: The Conversational Interface: Talking to Smart Devices. Springer 2016.
  • Gao et al.: Neural Approaches to Conversational AI: Question Answering, Task-oriented Dialogues and Social Chatbots. now publishers 2019.
  • Psutka et al.: Mluvíme s počítačem česky. Academia 2006.
  • + current papers from the field

Last update: Dušek Ondřej, Mgr. et Mgr., Ph.D. (10.05.2022)
Syllabus -

Brief introduction into dialogue systems

  • dialogue systems applications
  • basic components of dialogue systems
  • knowledge representation in dialogue systems
  • data and evaluation
  • linguistic aspects of dialogue

Natural language understanding (NLU)

  • semantic representation of utterances
  • statistical methods for NLU

Dialogue management

  • dialogue representation as a (Partially Observable) Markov Decision Process
  • dialogue state tracking
  • action selection
  • reinforcement learning
  • user simulation
  • deep reinforcement learning (using neural networks)

Response generation (NLG)

  • introduction to NLG, basic methods (templates)
  • generation using neural networks

End-to-end dialogue systems

  • training based on dialogue logs in a limited domain
  • multi-task learning
  • multi-domain systems, few-shot learning
  • use of pretrained language models

Open-domain systems (chatbots)

  • generative systems (sequence-to-sequence, hierarchical models)
  • information retrieval
  • hybrid systems

Ethical issues in dialogue systems

Multimodal systems

  • classical multimodal dialogue systems
  • neural systems, visual dialogue

Last update: Dušek Ondřej, Mgr. et Mgr., Ph.D. (10.05.2022)
Charles University | Information system of Charles University |