The goal of this course is to cover advanced research topics about conversational AI systems and review founding papers as well as recent work in task-oriented dialog systems, open-domain and social conversational systems, and conversations with embodied systems. We will review previous work on component-wise approaches, as well as end-to-end systems based on large language models (such as ChatGPT), and discuss where they converge and diverge.
The target audience is graduate students who plan to or are already working on these topics. If our time permits, I also plan to invite leading researchers in this field to present guest lectures.
I plan to present background work on conversational systems during the first two weeks, then we will review a set of papers on related topics, and these papers will be presented by students. Given the size of the class, I expect everyone will present one paper in class, and we will have 4 paper presentations for these weeks. Each week, students will also submit a review for one of the papers to be presented that week, and the choice of which one to review will be done by the student. In addition, students are expected to propose and work on a research project in one of these areas; we will discuss the proposals and progress throughout the course. These projects will be group projects of 3 students. In addition to working on their final projects, students will prepare a project report paper and will do a peer review of others’ proposals and project reports.
Course Information:
Lecture times: Wed & Fri, 2pm – 3:15pm
Location: 3217 Everitt Laboratory
Zoom Links for previous classes: <TBD>
Instructor Information:
Dilek Hakkani-Tür
email: dilek@illinois.edu
Office: SC 3304
Office Hours: Mon and Thu, 1-3pm (Please get an appointment using the Calendly link I share in class)
Teaching Assistant:
Kung-Hsiang (Steeve) Huang
email: khhuang3@illinois.edu
Office hour: Tue 4-5pm (Zoom link on canvas)
Grading:
- Paper Presentation: 10%
- ~10 Paper Reviews: 30% in total
- Final Project: 50%
- Proposal write-up 10%
- Final project write-up 20%
- Code & Demo 10%
- Presentations 10%
- Project report peer review: 10%
Absence Policy: In person participation is mandatory. However, circumstances (e.g., serious illness and family emergency) occasionally occur where you may need to miss a class. Please email me and Steeve before the class, if you cannot be present during the class.
SCHEDULE:
Note that the schedule is subject to change.
Check Canvas for specific due dates and times of all assignments.
Week 1:
Jan 17: Introduction
- Class Goals and Logistics
- Brief history of conversational systems
- Types of conversational systems
- Overview of the topics we will cover in this class
Jan 19: Review of task-oriented dialogue systems
- Spoken Language Understanding
- Dialogue State Tracking
- Dialogue Management
- Learning dialogue policies
- Response Generation from Semantic Representations
- End-to-end Models
Week 2:
Jan 24: Review of open-domain dialogue systems
Jan 26: Review of conversational human-robot interactions
Week 3 (Jan 31 and Feb 2): SLU & DST
Week 4 (Feb 7 and 9): Dialog Policy
Week 5 (Feb 14 & 16): Project Proposals (depending on number of students, we may replace this session with paper presentations)
Week 6 (Feb 21 & 23): Augmented LLMs
Week 7 (Feb 28 and Mar 1): Instruction Tuning
Week 8 (Mar 6 & 8): Reasoning
Week 9 (Mar 20 & 22): Preference Learning
Week 10 (Mar 27 & 29): Multi-Agent
Week 11 (April 3 & 5): HRI and multi-modal dialogue
Week 12 (April 10 & 12): Dialogue Safety
Week 13 (April 17 & 19): Evaluation
Week 14 (April 24 & 26): Final Project Presentations (depending on number of students, we may skip this and review papers on commonsense reasoning)