Additional course information available on Canvas.
Syllabus
Course Goals
The learning goals of the course are as follows:
- To introduce basic concepts of NLP and HCI, to the extent that students can read research papers in the relevant field.
- To introduce a variety of emerging topics related to human-centered NLP.
- To introduce practical tools for building and analyzing model-infused applications.
Notice that this new course is mostly designed to be a graduate-level, semi-seminar-style course for students interested in HCI+NLP research. This means:
- The course is largely project-oriented, and does not involve exames.
- A large proportion of your grade will depend on research paper reading and digestion.
- This is a special topic course (not well-established) and may only be offered once, so please expect some glitches in the schedule or assignments :)
- I cannot guarantee it will count as a part of a technical requirement.
Prerequisites
There is no explicit prerequisite; However, students are expected to (1) be proficient in Python (for completing assignments). You should not take the course if you find programming or debugging extremely difficult because you will have to master several programming languages/concepts/libraries in very short order. That being said, the assignments that require these will have useful resources for brushing up on the topics. Students are also expected to (2) know basic ML concept — To the extent that you understand concepts like train/dev/test set, model fitting, feature, supervised learning, etc. (We will not cover these in this course!)
If you are familiar with NLP and relevant programming libraries (e.g. HuggingFace, Smolagents), you might find certain parts of the course introducing NLP concepts significantly easier (or, unnecessary :D).
Course Materials and Communications
- Slides will be on this page; You will need to log in with your Andrew ID to access them.
- Assignments and discussions will be on Canvas when their time comes. All assignments must be turned in using Canvas.
- If you have questions related to course materials or logistics, please post them on Slack (See the link on Canvas).
- If you have special requests, please DM the instructor on Slack or email the instructor at sherryw@cs.cmu.edu.
Major Research Work
Grading
Assignments will be posted to canvas as well as their due dates. Each day late will result in a 10% deduction (up to a maximum of 50% off). Students caught cheating or plagiarizing will receive no credit for the assignment. As a reminder, here is the university policy on academic integrity.
Your final grade in this course will be based on:
- 30% Homework Assignments
- 40% Final Project
- 5% Form group + short project description
- 10% Midterm presentation
- 15% Final presentation
- 10% Project report
- 15% Leading paper discussions
- 10% Paper discussions on Canvas
- 5% In-class attendance
Attendance
Lectures will be held in-person twice a week. A good portion of the learning in any class comes from intelligent discussion. If you don’t attend class, you cannot participate, and your performance in the class will reflect that. Rather than taking attendance, there will be pop quizzes and also artifacts collected at the end of class that were generated from in-class activities.
Excused absences this course accepts are medical and family emergencies, academic conference travel, religious events, and a small set of approved collegiate activities. If in doubt, contact me to find a solution. Note that interviews, family vacations, weddings, sleeping through alarms, etc. are not excused. Your lowest two participation grades will be dropped, allowing you to miss up to two classes without impacting your grade.
Assignments
There will be two major assignments, one creating an LLM agent based on certain human-AI interaction principles, and another one evaluating this agent. We will provide a Colab Notebook template to walkthrough the required steps. More details will be posted on Canvas once the assignments are released.
Presentations and Discussions
Four class sessions are designated as Discussion Sessions. These are student-led, seminar-style sessions where we critically debate important issues in Human-Centered NLP.
-
Paper presentation. The reading lectures will be led by students. Each student would sign up for one session, and within each session 2-3 students can lead the same paper that help ground discussions. As presenters, you will (1) do a concise presentation of the paper (so everyone has context), (2) connect the paper to the broader discussion questions provided, and (3) seed discussion with reflection prompts, not necessarily argue one side.
To achieve deep paper digestion, you can take inspirations from the role playing model of Jacobson and Raffel. No need to pick explicit roles, just cover relevant discussion points.
-
Earn participation scores through discussions. Before each reading lecture, we will open corresponding discussion threads on Canvas. Students not leading the session are expected to participate submit comments on those required readings on Canvas. This is how you earn discussion scores! Good comments typically exhibit one or more of the following:
- Critiques of arguments made in the papers
- Analysis of implications or future directions for work discussed in lecture or readings
- Clarification of some point or detail presented in the class
- Insightful questions about the readings or answers to other people’s questions
- Links to web resources or examples that pertain to a lecture or reading
Final Project
The most substantial portion of your coursework is a team-based project (2-4 people). You will self-propose a project broadly relevant to HCI+NLP, with four milestones (they will be posted on Canvas when the time comes):
-
Form research group + topic selection. You will fill in a short Google Form that documents your group members, and a general description of your project. This will act as a forcing function for you to start think about the project. In the form, you will mostly address these questions: 1 (what are you trying to do), 2 (how is it done today), 3 (what’s new), 4 (who cares), 5 (your proposed method), and 6 (metrics of success). If you are looking for project partners, please post to Canvas!
-
Midterm presentation + peer feedback. Shortly after the Fall Break, Each group will do a 7-8 minute in-class presentation on the project progress, so the instructor and other students can provide feedback.
-
Final presentation. Each group will do a 7-8 minute in-class presentation on the final project result. This will be similar to the midterm presentation.
-
Final report. Each group will also submit a 4-8 page final report (not counting references) written in the form of a conference paper submission. The paper might include content that is typical of papers that appear at ACL or CHI.
Respect for Diversity
It is our intent that students from all diverse backgrounds and perspectives be well served by this course, that students’ learning needs be addressed both in and out of class, and that the diversity that students bring to this class be viewed as a resource, strength and benefit. It is our intent to present materials and activities that are respectful of diversity: gender, sexuality, disability, age, socioeconomic status, ethnicity, race, and culture. Your suggestions are encouraged and appreciated. Please let us know ways to improve the effectiveness of the course for you personally or for other students or student groups. In addition, if any of our class meetings conflict with your religious events, please let us know so that we can make arrangements for you.
Accommodations for Students with Disabilities
If you have a disability and are registered with the Office of Disability Resources, we encourage you to use their online system to notify us of your accommodations and discuss your needs with us as early in the semester as possible. We will work with you to ensure that accommodations are provided as appropriate. If you suspect that you may have a disability and would benefit from accommodations but are not yet registered with the Office of Disability Resources, we encourage you to contact them at access@andrew.cmu.edu.
Health and Well-being
If you are experiencing COVID-like symptoms or have a recent COVID exposure, do not attend class if we are meeting in-person. Please email the instructors for accomodations.
If you or anyone you know experiences any academic stress, difficult life events, or feelings like anxiety or depression, we strongly encourage you to seek support. Counseling and Psychological Services (CaPS) is here to help; call 412-268-2922 and visit their website at www.cmu.edu/counseling/. Consider reaching out to a friend, faculty or family member you trust for help getting connected to the support that can help. If you or someone you know is feeling suicidal or in danger of self-harm, call someone immediately, day or night:
If the situation is life threatening, call the police. On campus call CMU Police: 412-268-2323. Off campus: 911.
If you have questions about this, please let the instructors know. Thank you, and have a great semester.