This course will be an advanced topic seminar class on natural language processing for very diverse types of conversational models (rule-based, retrieval-based, neural generative models, grounded/visual, chit-chat vs. task-based, etc.) as well as important related aspects such as evaluation, deployment, etc.:
This will be a research-oriented grad-level seminar course, where we will read lots of interesting research papers, brainstorm about ideas on latest research topics, and code and write up fun and novel projects!
- chitchat vs task-based dialogue
- rule-based chatbots
- retrieval-based chatbots
- neural generative models
- reinforcement learning for dialogue policy
- frame-based and KB-based agents
- grounded visual dialogue
- grounded human-robot task-based dialogue
- dialogue for learning new subactions, mediating shared perceptual basis, referring expression generation, etc.
- language learning via dialogue-based and interactive games
- evaluation of dialogue models
- real-world deployment of dialogue systems (e.g. Alexa Prize)
Please email me or drop by my office if you have any questions!
Since this is an advanced topics NLP class, the student is expected to have equivalent experience to Dr. Bansal's' fall 2016 or fall 2017 regular NLP class.
Grading will consist of:
Details in first class intro lecture slides. There will not be any exams. All submissions should be emailed to: email@example.com
- project presentations and write-ups (midterm = 20% and final = 30%; total = 50%)
- paper presentations (20%)
- paper written summaries (20%)
- class participation, discussion, and brainstorming (10%)
Students are allowed 3 free late days for assignments over the semester. After that, late assignments will be accepted with a 20% reduction in value per day late.
Paper summaries have to be written and submitted individually. Paper presentations have to be done individually. Projects can be individual (e.g., if it relates to your current research) or in pairs (but with proportional work, and with clearly outlined contributions from each team member).
|Date||Topic || Readings ||Discussion Leaders||Todo's|
| Jan 17 (make-up class on Jan19 due to weather) || Intro to Class (summary of different types of dialogue, models, and evaluation issues) || SLP3 Chapters 29, 30; SLP2 Chapters 24 || Mohit ||-
| Jan 26 || Rule-based Chatbots, Retrieval-based Chatbots || Rule-based: |
(1) ELIZA: Weizenbaum, J. (1966). A computer program for the study of natural language communication between man and machine;
(2) PARRY: Colby, K. M., Weber, S., and Hilf, F. D. (1971). Artificial paranoia;
(3) Jafarpour, S., Burges, C., and Ritter, A. (2009). Filter, rank, and transfer the knowledge: Learning to chat;
(4) Leuski, A. and Traum, D. (2011). NPCEditor: Creating virtual human dialogue using information retrieval techniques ;
(5) Isbell, C. L., Kearns, M., Kormann, D., Singh, S., and Stone, P. (2000). Cobot in LambdaMOO: A social statistics agent
| TBD ||-
| Feb 2 (no class due to travel) || || || TBD ||-
| Feb 9 || Frame-based and KB-based Agents || || TBD ||-
| Feb 16 || Neural Generative Models || || TBD ||-
| Feb 23 || Neural Generative Models 2 || || TBD ||-
| Mar 2 || Reinforcement Learning for Dialogue Policy || || TBD ||-
| Mar 9 || Grounded Visual Dialogue || || TBD ||-
| Mar 16 (Spring Break) || || || TBD ||-
| Mar 23 || Midterm Project Presentations || || All Students ||-
| Mar 30 (univ holiday so make-up class TBD, probably on Wed Mar28) || Human-Robot Task Dialogue || || TBD ||-
| Apr 6 || Human-Robot Task Dialogue 2 || || TBD ||-
| Apr 13 || Language Learning via Dialogue-based and Interactive Games || || TBD ||-
| Apr 20 || Going Forward: Better Evaluation and Real-World Deployment of Dialogue Systems || || TBD ||-
| Apr 27 || Final Project Presentations || || All Students ||-
The professor reserves the right to make changes to the syllabus, including project due dates. These changes will be announced as early as possible.