Project

Back to Syllabus

A major component of the class will be the project (worth 50% of your grade). Throughout the course, you will develop an application of NLP techniques to a topic of interest to you. You may work alone or in pairs, as long as you clearly define which person did which parts of the work. Each person should contribute equally. It’s not acceptable to do the same work for this project and another class’s project, but it’s acceptable (and encouraged) for this project to relate to another project as long as the boundary is clearly defined -- if you're unsure, check with the instructor.
The project will consist of 4 deliverables:

Idea

Due 2021/2/12 end-of-day

Worth: 5 credits

For the first milestone, your goal is to choose a problem to work on (and a collaborator, if any). Importantly, we care more about knowing what you're interested in! It will probably be too early for you to know how you might solve your problem. It's okay to change later on. Length guideline: half to 1 page per student.

Try to address the following questions:

  • What are you trying to do? Describe your goal without using any jargon.
  • Write (or draw) an example of the envisioned input/output or user interaction.
  • If your project is successful, how will it be helpful to people?
Submit your idea through Blackboard as a PDF file (not doc or docx) named [gmuid]-pm1.pdf .

Baseline

Due 2021/3/19 end-of-day

Worth: 10 credits

For the second milestone, you should have everything ready that you need to start experimenting with solutions to your problem. Describe what you've done so far. Length guideline: half to 1 page per student.

For most projects, this means you must answer the following questions:

  • What data will you use? Include URLs or LDC catalog numbers. Describe whatever preprocessing steps you used on the data (e.g., cleaning, tokenization).
  • What metric(s) will you use to measure success?
  • What baseline method will you compare against? This should be something that you can implement in about one hour.
  • How well does your baseline method perform (using your evaluation metric)?
For a minority of projects, the above will not apply. Please check with Prof. Anastasopoulos about what to submit.
Submit your work through Blackboard as a PDF file (not doc or docx) named [gmuid]-pm2.pdf .

Presentation

Due sometime after the baseline, final deadline is 2021/4/16 end-of-day

Worth: 10 credits

Your presentation should be no more than 5 minutes per project. You can create a YouTube video with your presentation, or you can do it live in class. If you do it live in class, budget 2-3 more minutes for discussion. It is okay if some of the work is not finished yet! Presentation dates are scattered throughout the second half of the semester. If you choose an early date, you will get feedback that you can actually implement to make your project better!

Your presentation should cover:

  • Goal: What are you trying to do? Describe your goal without using any jargon.
  • Method: How are you trying to do it (briefly)?
  • Experiments: How well does it work (so far)?
  • Conclusions: What did you learn from your experiments (so far)?
Submit your slides through Blackboard as a PDF file (not key or ppt or pptx) named [gmuid]-pm3.pdf .

Report

Due 2021/4/29 end-of-day

Worth: 25 credits

Your report should describe your semester-long efforts on your project. You can reuse parts of your idea and baseline reports, so that your report will read like a concrete contribution. Length guideline: 2–4 pages per undergraduate student.

Your report should cover:

  • Goal: What are you trying to do (using no jargon)? Give an example of inputs/outputs or user interaction. How might it be helpful to people?
  • Method: How are you trying to solve the problem? What are existing approaches to the problem?
  • Experiments: What data do you use? What metric(s) do you use to measure success? What baseline method do you compare against? How well do your methods perform compared with the baseline, and why?
  • Conclusions: What did you learn from your experiments?
  • Replicability: Submit (or include links to) all the code that you wrote and all the data that you used. (a link/invite to a Github repository will suffice).
Submit your work through Blackboard as a PDF file (not doc or docx) named [gmuid]-pm4.pdf .

Previous