Course Project

By February 25, you should have met with me and handed in a project proposal. Please both bring a hardcopy to class, and submit it electronically using the Digital Dropbox feature of Blackboard. By March 25, you should have met with me again and handed in a status report on your project. A draft of your report or paper is due April 15. The final report is due April 22. All of these deadlines must be met to receive credit on the course project. Students will give project presentations during the final days of class. Note that you might also be able to turn your course project into a paper at the following relevant venues (naacl ws, slate ws).

Feel free to discuss your ideas for projects before writing your proposal. Your project should be non-trivial and interesting, yet feasible given the time frame.

There are four options for the project:

  • A community shared task. This project could use the materials developed for the shared task at the FLAIRS conference this spring, or the Learner Answer Corpus (see links for 1/12). You can also use ITSPOKE data (some is publically available via the PSLC - see 1/12 links, but you can also get other data from me) and Pam Jordan said she is willing to make her peer-tutoring dialogue data available. This project may be done in pairs or individually.
  • Implement and evaluate an algorithm that performs some type of spoken or natural language processing targetted for an educational application. This type of project may be done in pairs or individually.
  • Use linguistic knowledge to enhance an educational application system. Processing may be fully automatic, or your system may take manual annotations as input. This type of project may be done in pairs or individually.
  • A corpus annotation project. This type of project must be done in pairs. It will involve developing annotation instructions, gathering or using a corpus, performing a training round of annotation, discussing the results with each other, revising the annotation instructions, and then annotating a fresh test set. Inter-coder reliability should be reported (percentage agreement and Kappa). The amount of data annotated need not be large.

    Further information about project proposals can be found here.