[Back to CS585 home page]

Final Project

Introduction

The final project is to either build a natural language processing system, or apply one for some task. The project must use or develop a dataset, and report empirical results or analyses with the dataset. It may use machine learning or rule-based approaches. It may use any type of open-source or widely available software.

You can choose to emphasize:

Different projects will have different balances of these three things.

This course does not have a final exam. The final project is the focus for the final part of the course.

The project will be completed in groups of 1-3. We encourage size 2, which seems to work well in similar courses.

See also the project discussion slides which have pointers to some project ideas and software / linguistic resources.

The project has four components over the second half of the semester: Proposal, Progress Report, Presentation, and Final report.

(Requirements for the items after the proposal are subject to revision as we get closer to them.)

See also Sample projects and resources

Proposal (due 10/24)

A 2-4 page document outlining the problem, your approach, possible dataset(s) and/or software systems to use. This proposal

In general, you should illustrate that you have learned about and thought through some of the problem space and possible avenues of analysis and approaches to the problem.

Ideally, try to answer the following questions as well.

Formatting: please use a 10 to 12 point font with single or 1.5 spacing.

Groups: please include the names of all group members. Only one group member needs to submit on Moodle. (It is OK for groups to change after this, but if your group changes, please email us about it and note this in your later reports. Otherwise it will be difficult for us to track your work.)

Progress Report (due 11/13)

You’ve had three weeks to work on the project! You have now clarified and revised your proposed idea. You have started working on it and have some preliminary results to report.

The progress report is a 5-10 page document that describes your preliminary work and results. You should do and report on work including

Presentations (12/8, 12/10)

We will have short in-class presentations during the last week of classes. Each presentation will have a strict limit of 2 minutes, plus 30 seconds for a question.

Each presentation can have exactly one slide. Submit your slide, in PDF format, to Moodle the day before the presentation. Make sure your slide includes your project title, as well as the names of the group members.

We advise that only one person in the group presents. You should practice the presentation with a timer. We will have to cut you off when time runs out.

Comment assignment: During the day you are not presenting, take notes on the presentations. Afterwards, summarize and comment on one of the projects that you found interesting. You will write this as a short document, at least 150 words long (about half a page). Make sure to (1) describe what they did (as far as you can tell from the short presentation), and (2) discuss it a little bit: pose a question about the work and explain why this question is interesting or significant, or, propose a possible extension or avenue for future work. Submit this summary and comment via Moodle. It will count towards your exercises grade. You should submit this the same day so it will be easier to write, but we’ll accept it until Sunday 12/13.

Final Report (due 12/18)

The final report is a 12 to 20 page document that describes your project and final results. Unlike the proposal (which was only about a possible project and related work), or the progress report (which was only about results), the final report must be a complete, standalone document. Conceptually, it should include the content of both the proposal and progress report, though they will be changed. The final report describes and motivates the problem, places it in context of related work, describes the dataset and your approach, and reports results with discussion and thoughts for future work.

Submit your PDF on Moodle. Also submit a zip file with your implementation code. (Moodle limits the size of the zip file, so don’t include large data files, but feel free to provide us a URL to them.)

Here is a sample outline for your final report. There are different possible ways to structure it (for example, if you can, you can weave related work into the other sections), but we suggest you follow this outline unless you have substantial prior experience writing technical reports and research papers.

Some things to remember:

Writing a paper is like composing a piece of art. Be deliberate in your choice of what to include, when to include it and how to express it. For example, don’t include every plot you generated; pick the ones that best demonstrate your results. Work on the clarity of your writing. At the end of the day, your report is all the reader has to generate an opinion about your work. You don’t want good work to be obscured by poor writing.

Extra requirement for 585-02 students (graduate students): You must cite at least 10 relevant research papers, and describe them and how they relate to your work. It may be convenient to structure this as a related work or literature review section.

Formatting: please use a 10 to 12 point font with single or 1.5 spacing. Please divide your report clearly into sections/subsections.