Objectives

• Define a study topic and an application in language technology. You may define them yourself or with the help of the instructor.
• Survey the relevant literature
• Implement an application prototype
• Evaluate it
• Write a project report in the form of a conference paper
• Submit this paper to a conference (optional). See for instance ACL 2020 .

Organization and Location

The project will take place in the 2nd LP. There is no dedicated location for it. The participants will work on the machines in the basement or on their own machines. The duration of time spent on the project should be of about two weeks. Each participant can work alone or collaborate with one or two other people.

A more complete description with possible subjects is available here.

Report and Programs

After your presentation, you will write a report of 4 to 8 pages that you will hand in together with your slides, and your programs (possibly through a public versioning repository). You will try to write your report as a research paper, like the ones you probably read when carrying your project out.

Please, use Latex and the Association for Computational Linguistics styles to compose your report so that we have a uniform presentation across all the papers. The styles are available here: https://acl2020.org/calls/papers/. Please use the A4 page size. Use also the Latex/Bibtex tool for your references. Should you have questions about it, please ask me. Görel Hedin wrote useful guidelines on how to write a report that you can read here.

When you are done with your project, please send me:

• the final report in PDF with the Latex sources. Do not paginate it;
• the slides in PDF, Powerpoint, OpenOffice, or similar formats; and
• the code in a zipped archive, possibly with a github link.

The deadline to hand in the report, the slides, and the code is Wednesday January 13, 2021.

List of Projects

In total, there are 3 projects and 5 students. I wrote down the names of the students and the project titles as they came to me. They do not represent any commitment, but are just an indication. Students can change or modify the project title as they want.

1. Oliver Dageson and André Hedesand, A Dialogue System to Play Chess
2. Asmail Khalil Abdulkarim and Mohammad al Masri, Multilingual Tokenization
3. Viktor Olsson, Multilingual Dependency Parsing

Schedule of Presentations

The project presentation consists of an oral description of your project and results that should be typically of 15 minutes followed by questions. There will be a beamer available in the room so that you can easily show your slides and demonstrations. Please read the presentation guidelines here before you give your talk: here. [ local copy].

Altogether, the presentation should not last more than 25 minutes. All the presentations will take place on December 18, 2020 with Zoom (https://lu-se.zoom.us/j/67979154753). The table below shows the preliminary schedule.

In the presentation, you will shortly describe the background, your system (architecture and outline of your algorithms), and results. You should provide some kind of evaluation and ideally show a demonstration.

You have other links and tips here: http://cs.lth.se/edan70-project-in-computer-science/projects-in-compilers/