MA-INF 4238: DIALOGUE SYSTEMS
Summer Semester 2025
Content:
What is the Dialogue Systems course about?
This course is a detailed introduction to the architecture of conversational systems (chatbots). We will introduce the main components of dialog systems and show approaches to their implementation, including natural language understanding, natural language generation, and dialog sequence management. This course will briefly discuss speech-related components and multi-modal systems, but will primarily focus on text processing and language understanding. The lab sessions will be dedicated to implementing a personal and specialized chatbot with LLM agents.
Recommended participation requirements:
There are no mandatory prerequisites but the following will help you understand the material:
- Introduction to Natural Language Processing
- Introduction to Machine Learning
- Basics of statistics
- Basics of programming (Python)
Logistics:
- Lectures: are on Thursday 12:15 PM - 01:45 PM in Room 0.109 (B-IT-Max) (Friedrich-Hirzebruch-Allee 6). ZOOM LINK
- Exercises: are on Thursday 02:15 PM - 03:45 AM in Room 0.109 (B-IT-Max) (Friedrich-Hirzebruch-Allee 6). ZOOM LINK
- Course Materials: will be uploaded every week on eCampus.
- Contact: Students should ask all course-related questions in our forum discussion on eCampus. For external inquiries, emergencies, or personal matters, you can contact Prof. Lucie Flek or Dr. Akbar Karimi.
- Office Hours: Please reach out to us first via mail to arrange any in-person meeting.
- Prof. Dr. Lucie Flek: Friedrich-Hirzebruch-Allee 6 (B-IT) – Room: 2.123
- Dr. Akbar Karimi (AK): Friedrich-Hirzebruch-Allee 6 (B-IT) – Room: 2.118
NEWS / UPDATES:
- 09.04.2025: The first class will take place on Thursday, 17.04.2025 at 12:15 in Room 0.109 (B-IT-Max).
Instructors:
Coursework:
Software Project (40%):
- Credits:
- 10%: Pitch presentations
- 10%: Code and dataset
- 10%: Final presentation
- 10%: Final report
- Deadlines: (tentative)
- May 21: Pitch presentation slides submission
- July 2: Code and dataset submission
- July 9: Final presentation slides submission
- July 31: Final report submission
- Collaboration: Students will be encouraged to form groups of 2-4 people for the project.
Exam (60%):
- Exam dates:
- First exam: August 5, 9-12
- Second exam: September 19, 9-12
- Allowed material: Calculators are permitted.
Allocation:
- Master in Media Informatics: 4 ECTS credits
- Master in computer science at University of Bonn: MA-INF 4238 6 CP
Literature:
- Jurafsky, D., & Martin, J. E. Speech & Language Processing, An Introduction to Natural Language Processing, Computational Linguistics & Speech Recognition
- Goodfellow, I., Bengio, Y., & Courville, A. Deep Learning. MIT Press.
- McTear, M. Spoken Dialogue Technology: Enabling the Conversational User Interface. ACM.
Literature - Exercise:
- HuggingFace Agents Course: https://huggingface.co/learn/agents-course/en/unit0/introduction
- Self-refine: Iterative refinement with self-feedback (Madaan et al., 2023)
- Reflexion: Language agents with verbal reinforcement learning (Shinn et al., 2023)
- Gorilla: Large language model connected with massive APIs (Patil et al., 2023)
- MM-REACT: Prompting ChatGPT for multimodal reasoning and action (Yang et al., 2023)
- Chain-of-Thought prompting elicits reasoning in large language models (Wei et al., 2022)
- HuggingGPT: Solving AI tasks with ChatGPT and its friends in Hugging Face (Shen et al., 2023)