SubjectsSubjects(version: 850)
Course, academic year 2019/2020
   Login via CAS
Dialogue systems - NPFL123
Title in English: Dialogové systémy
Guaranteed by: Institute of Formal and Applied Linguistics (32-UFAL)
Faculty: Faculty of Mathematics and Physics
Actual: from 2019
Semester: summer
E-Credits: 5
Hours per week, examination: summer s.:2/2 C+Ex [hours/week]
Capacity: unlimited
Min. number of students: unlimited
State of the course: taught
Language: Czech, English
Teaching methods: full-time
Additional information: http://ufal.mff.cuni.cz/npfl123
Guarantor: Mgr. et Mgr. Ondřej Dušek, Ph.D.
Annotation -
Last update: Mgr. Barbora Vidová Hladká, Ph.D. (25.04.2019)
This course is a detailed introduction into the architecture of spoken dialogue systems, voice assistants and conversational systems (chatbots). We will introduce the main components of dialogue systems (speech recognition, language understanding, dialogue management, language generation and speech synthesis) and show alternative approaches to their implementation. The lab sessions will be dedicated to implementing a simple dialogue system or a selected component.
Aim of the course -
Last update: Mgr. Barbora Vidová Hladká, Ph.D. (25.04.2019)

The course aims to give a general overview of dialogue systems and explain the basic principles of their inner workings.

Course completion requirements -
Last update: Mgr. et Mgr. Ondřej Dušek, Ph.D. (10.06.2019)

Passing the final exam (written test based on the contents of lectures), finishing lab session homeworks (implementation tasks from the field of dialogue systems).

Literature -
Last update: Mgr. et Mgr. Ondřej Dušek, Ph.D. (06.05.2019)

Basic: Jurafsky & Martin: Speech & Language processing. 3rd ed. draft (chapter 29-30). https://web.stanford.edu/~jurafsky/slp3/

Further reading: Jokinen & McTear: Spoken dialogue systems. Morgan & Claypool 2010.

Rieser & Lemon: Reinforcement learning for adaptive dialogue systems. Springer 2011.

McTear: Spoken Dialogue Technology. Springer 2004.

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. (arXiv:1809.08267)

Syllabus -
Last update: Mgr. et Mgr. Ondřej Dušek, Ph.D. (06.05.2019)

1. Dialogue systems and artificial intelligence: introduction

  • dialogue system types (open/closed-domain, task/non-task oriented)
  • dialogue systems application
  • basic dialogue system components (text-to-text, speech-to-speech)
  • knowledge representation in dialogue systems
  • chatbots, AIML

2. Linguistic basics for dialogue processing

  • turn-taking, speech acts
  • conversational implicatures
  • grounding
  • coreference, anaphora, deixis

3. Data for dialogue systems, dialogue system evaluation

  • closed domain: Wizard-of-Oz
  • open domain: data sources, problems (cleanliness, risks of learning from users)
  • dialogue success rate
  • problems of chatbot evaluation

4. Question answering and voice assistants

  • Alexa, Google, Siri etc.
  • Knowledge bases, knowledge graph

5. Dialogue systems API

  • intents, slots, entities
  • Alexa Skills, Google DialogFlow, IBM Watson Assistant

6. Language understanding

  • Sentence classification
  • named entity recognition

7. Dialogue state tracking

  • dialogue representation as an MDP or a POMDP

8. Dialogue management

  • reinforcement learning

9. Language generation

  • templates, rules
  • statistical generation

10. Speech recognition

  • speech signal processing
  • basic recognition approaches

11. Speech synthesis

  • phonetics/acoustics: sounds/phonemes, formants
  • speech synthesis methods

12. Chatbots (open-domain dialogue)

  • AIML
  • Information retrieval (Cleverbot)
  • Statistical generation (seq2seq)
  • Hybrid systems (Alexa Prize)

 
Charles University | Information system of Charles University | http://www.cuni.cz/UKEN-329.html