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)