Syllabus
Unit 1
Introduction to Conversational AI, Principles of dialogue – common ground, sub dialogues, Gricean principles of conversation, Computational models of dialogue systems, Chatbots architectures – Rule-based and Corpus based, Case study: Sounding board
Unit 2
Architecture for dialogue systems: Pipelines behind common assistant programs, collaborative problem-solving model, dialogue acts. cognitive architectures, Question Answering: Sources of knowledge, Case Study: IBM’s Deep Q/A approach
Unit 3
Dialog Management and System Evaluation, Dialog Manager Architectures, Natural Language Generation, evaluation of performance, reward propagation. Case study: Social chatbot evaluation
Objectives and Outcomes
Course Objectives
- This course relates the principles and practice of creating AI conversational interface systems.
- This course includes knowledge-rich natural language understanding, multimodal interaction (speech and sketching), principles of dialogue drawn from cognitive science, question-answering, and architectures for building conversational systems.
Course Outcomes
CO1: Understand computational models of dialogue systems.
CO2: Understand architectures for building conversational systems.
CO3: Apply problem-solving dialogue model for question answering.
CO4: Analyze dialogue management and chatbots.
CO-PO Mapping
|
PO/PSO
|
PO1
|
PO2
|
PO3
|
PO4
|
PO5
|
PO6
|
PO7
|
PO8
|
PO9
|
PO10
|
PO11
|
PO12
|
PSO1
|
PSO2
|
|
CO
|
|
CO1
|
3
|
2
|
2
|
2
|
1
|
0
|
0
|
2
|
3
|
2
|
0
|
0
|
3
|
3
|
|
CO2
|
3
|
2
|
2
|
2
|
1
|
0
|
0
|
2
|
3
|
2
|
0
|
0
|
3
|
3
|
|
CO3
|
3
|
3
|
3
|
3
|
3
|
0
|
0
|
2
|
3
|
2
|
0
|
0
|
3
|
3
|
|
CO4
|
3
|
3
|
3
|
3
|
3
|
0
|
0
|
2
|
3
|
2
|
0
|
0
|
3
|
3
|
Evaluation Pattern
Evaluation Pattern: 70:30
|
Assessment
|
Internal
|
End Semester
|
|
Midterm
|
20
|
|
|
Continuous Assessment – Theory (*CAT)
|
10
|
|
|
Continuous Assessment – Lab (*CAL)
|
40
|
|
|
**End Semester
|
|
30 (50 Marks; 2 hours exam)
|
*CAT – Can be Quizzes, Assignments, and Reports
*CAL – Can be Lab Assessments, Project, and Report
**End Semester can be theory examination/ lab-based examination/ project presentation
Text Books / References
Textbook(s)
Seminck, O., Michael McTear.“Conversational AI: Dialogue Systems, Conversational Agents, and Chatbots”, Computational Linguistics, 2023.
Reference(s)
Tur, G. and De Mori, R., “Spoken language understanding: Systems for extracting semantic information from speech”. John Wiley & Sons. 2011.
Jokinen, K. and McTear, M., “Spoken dialogue systems. Synthesis Lectures on Human Language Technologies”, vol. 2, no. 1, 2009.
