Course Project

TL;DR for Deadlines

Overview

The goal of the course project is to give students hands-on experience in a research area of their choice, related to the topics covered in class. By default, each team should consist of three students.

The following types of projects are welcome and encouraged:

• Paper reproduction: Reproduce any paper that is (1) published to ACL, EMNLP, NAACL, COLM, NeurIPS, ICLR, and ICML in 2025-2026, and (2) clearly under the scope of NLP (dealing with natural language, text). Your project should:
  • Include a subset of the original experiments, along with meaningful extensions (e.g., new datasets, base models, or ablations).
  • Provide novel insights or results beyond the original paper.
  • Meta-reproducibility studies across related papers are also encouraged.
• One of recommended project ideas proposed by course staff members (will be posted in Ed).
• Your new project idea, or ongoing research: You may build on your current research (including work with collaborators outside the class), as long as it clearly relates to NLP and is noted in all deliverables (see the project FAQ). If unsure about relevance, ask a question on Ed.

Checkpoint 0: Team matching / registration, for both A3 and project (Due 02/10 Tue)

• Fill out the form with your preferred teammates and project topics. The topic does not have to be finalized; it is only for team matching.
• You may also choose to form a team (registered or matched) for A3 only, and complete the course project separately, e.g., if you plan to use your ongoing research as a course project and your collaborators are not enrolled in the course. Please indicate this in the form.

Checkpoint 1: Project abstract (Due 03/03 Tue)

No more than 250 words.

Checkpoint 2: Midpoint project report (Due 04/09 Thu)

• Format: Use the unmodified COLM template (find the latex template here).
• 2-3 pages, not including references. You are welcome to include an Appendix with no page limit, but the evaluation will primarily be based on the main content.
• Your proposal must have the following sections: Abstract, Introduction, Related work, Proposed approach, Experiments and evaluation plan (including baselines, evaluation datasets, and metrics), Preliminary results, Plans until final report due, Contribution statement (thus far, and plans going forward), and References.
  • In particular, please note that the implementation of baselines and preliminary results are required, not optional.

Checkpoint 3: Project presentations (04/28 and 04/30)

• Duration: TBD
• The goal of the presentation is to convey the important high-level ideas and takeaways of your project, rather than all the details.
• All group members should participate in the presentation. You can split it any way that you see fit, as long as each person presents a significant chunk of it.
• Demos are strongly encouraged where possible!

Checkpoint 4: Final project report (Due 05/07 Thu)

• Format: Use the unmodified COLM template. Find the latex template here.
• 6-8 pages, not including references. You are welcome to include an Appendix with no page limit, but the evaluation will primarily be based on the main paper.
• The final paper should be comparable in quality to a conference or workshop submission. If you’re interested in submitting your work for real, feel free to reach out to the instructor for help.

Acknowledgement

We are grateful to VESSL AI and Google Cloud for providing compute credits to support our final projects.

Instructions for receiving the credits will be shared on Ed.

Project FAQ

Using the same project for CS 288 and another class

While the projects can be related and use a shared codebase, you may not submit an identical project as another class project. If any part of the project is done for another course, please clearly indicate in the Contributions section of your report which part of the project was done for CS 288 and which part was not.

Using your ongoing research as your CS 288 project

This is allowed. In the Contributions section of your writeup, you should indicate this and describe which parts were done prior to the start of the course vs. which parts were done for the course. You will be evaluated on the parts that were done after the start of the course, i.e., you may not reuse a previously completed project.

Collaborating with people outside this course

This is allowed (e.g., your advisor and labmates might be involved in your ongoing research). In the Contributions section of your writeup, you should indicate this and describe which parts you were responsible for. If you are repurposing text or slides that were written by your collaborators, you should also declare this. You will be evaluated on the parts that you worked on.

Generative AI policy

See the course info page.