Pristupačnost
We're excited to announce the 10th edition of the Text Analysis and Retrieval (TAR) course. If you're interested in search engines, text analysis, statistical natural language processing, and the application of machine learning to natural language processing, then this course is for you. However, since TAR might be a bit different than the courses you took in the past, we ask you to consider the following information before you make your final decision about enrolling in the course.
- Due to organizational constraints, we accept a limited number of students. This year, we offer 51 places and the selection among the applicants will be based on the motivation letter and undergraduate grade point average. Four spots will be reserved for Erasmus students.
- TAR is taught in English only (level L3). All course material, including tests, will be in English. There is no "Croatian group" and no material in Croatian. If you enroll in this course, we assume that you're accepting these terms and that you have a good enough command of English to follow the lectures and participate in class.
- TAR has no midterms and no finals. Instead, you are expected to attend all classes and participate. You can be absent from some of the classes but at the cost of losing points. Note that you need to meet several thresholds, so being absent from too many classes means you risk failing the course and having to enroll again next year. Be aware that the course can only be passed via continuous (in-class) assessments; there are no regular exams for this course.
- In the first half of the course, there is weekly prep work (pre-reading and/or watching video lectures), so you will be expected to prepare for each class. There will be weekly quizzes that cover prep work as well as last week's in-class material. Additionally, you will have several lab assignments to solve during the first half of the course.
- In the second half of the course, the classes will revolve exclusively around paper reading sessions. What this means is that you will be asked to read scientific papers (which are in English) published at recent and renowned conferences, summarize the papers, answer key questions about them, and finally participate in discussions, which we'll be having together in class. There will be no way around this: reading sessions are an integral part of the course, we're doing them for you and you only, and you can't make up for them by doing something else. There will be reading quizzes, and if you don't attend the reading, you'll lose points and risk not meeting the threshold. Now, why are we doing all this? Because we firmly believe that being able to read, review, and discuss scientific papers is a tremendously important skill, regardless of whether you intend to pursue an academic career. We're also doing it because we found out it's a much better and more amusing way to engage with the topics we want to cover. And while most students felt that reading and discussing papers was indeed a lot of fun, it is certainly not for everybody.
- The central activity of the course is team project work. Projects are done primarily in the second half of the course and revolve around a practical and trendy information retrieval or natural language processing task. You get to choose a topic from a list of topics. Three points deserve a mention here. First, the projects are done in 3-person teams. There is no way around this; you can't do the project on your own, and you have to team up by yourself. Second, the project results will need to be wrapped up in the form of a short scientific paper. You can write the paper in English or Croatian. Third, you'll present your work in a 15-min talk at the end of the course. This again can be done in English or Croatian, and it suffices that one project member presents your work, however, all students must attend all presentations.
- Although machine learning is not a formal prerequisite for TAR, taking the course without knowing the ML basics will probably cause much frustration. Here we don't necessarily mean that you should have completed FER's ML course (or you intend to complete it before TAR starts in the summer semester): any other course or self-study that provided you with the basics of ML will be fine. On the other hand, if you absolutely had no prior exposure to ML, we don't advise enrolling in TAR.
If all this sounds like your cup of tea, we'll be happy to have you on board! ;)
In the extended post, you can read about the previous experiences of students who have completed the course.
***
I LOVED that this course is different from all the others I've had so far. Reading papers is something I've been interested in for a while but it's hard to decide where to start from, how to choose papers and properly read them, so the weekly reading sessions were extremely helpful. The first part of the course ("lectures" about NLP topics) is very useful, especially for people like me who had no experience in the field before. Lab assignments were not too demanding but still managed to be fun and useful, a cool addition to TAR! And of course, since this was quite a hard semester for me, having one less exam to worry about was the cherry on top :)
***
TAR is the best course I've attended so far. No exams. Laboratory exercises. The lecturers, albeit not very successfully, encourage discourse among students. Exposure to the world of research in AI/NLP. Very nice and unique. An excellent "simulation" of working in research and publishing a paper.
***
Very interesting lectures in the first cycle, a good introduction to fundamentals of paper reading, lots of time and energy invested by the lecturers into guiding us with the projects and giving us constructive critiques for improvement, no classic exams :-)
***
I like the out-of-the-box way of teaching and how the subject is divided across the semester. I found that this way of teaching really makes me a lot more interested in the subject and i quite enjoyed it.
***
Reading papers, writing a paper, getting valuable feedback (both project-wise and in lectures), hearing experiences from people currently involved in the field.