Starting on Monday, October 1, 2018 at 9.00 am in SU2!
NPFL101 Competing in Machine Translation is a workshop-style seminar. In the seminar, we will be developing machine translation (MT) systems reaching or surpassing the state-of-the-art translation quality (e.g. Google Translate or Bing).
During the seminar, you will work on your project, usually in a small team, usually with the topic linked to your other interests or school requirements (semester project, software project, thesis).
The seminar will take place in a Unix lab and we will work with large data and fast GPUs.
We Want You!
The seminar will work well for students with very diverse interests. You do not have to fall in love with computational linguistics (let alone linguistics alone ;-) to take part. We seek for pure software engineers, machine learners (or rather teachers) and particularly people interested in deep learning, Linux hackers, but also web frontend developers (e.g. the development of MT evaluation interfaces) or wannabe psycholinguists (conducting various experiments on perceived translation quality, including eye-tracking; the school has a good eye-tracker). Linguists are still welcome, don't worry.
Every year, the key requirement, for which you will receive the credit, is to submit a report describing your project for the seminar. Depending on your particular project, we may also agree on a presentation at the seminar, which then contributes the content to your report.
The report shall be at least 2-4 pages long and include proper introduction (the "big picture" of what your work is contributing to), technical details, as well as a standard conclusion. You can work on your project alone or in a small group, as agreed at the seminar.
If the resulting project leads to a workshop or a conference paper, there is no need to write a separate report.
The official description in SIS is a little outdated, it does not mention neural machine translation (NMT) at all, but we will primarily work with NMT.
You can enroll into the NPFL101 seminar repeatedly, i.e. in more than one year.