CS 585, Fall 2017, UMass Amherst: Introduction to Natural Language Processing

Final Project

Poster session and list of projects

There will be two poster sessions on Tuesday, 12/12, in CS room 150/151.

Session 1: 3:30-5:00

Session 2: 5:00-6:30


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.

The key requirement is to investigate, analyze, and come to research findings about new methods, or insights about previously existing methods.

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 often works well.

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 10/17)

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 spacing.

Submit via the HotCRP system on cs585projects.cs.umass.edu. It should allow you to do a group submission.

In special cases, some groups may want to change after this point. That's OK, but please be very clear when doing later turn-ins.

Peer feedback

After submitting your project proposal, you will be assigned other proposals to give feedback on.

Progress Report (due November 20 (not 17))

You’ve had a few 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

Poster session presentations (near end of classes)

We will have a poster session where all groups will present their work. It will be open to the community, in conjunction with the Data Science Tea. It should be fun! Logistical details forthcoming.

Final Report (due 12/22 at end of semester)

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 Gradescope, and implementation on Moodle. (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. We suggest the ACL stylesheets, though they're not necessary to use.