Při výběru garanta předmětu se zobrazují připomínky jak k němu, tak ke všem vyučujícím daného předmětu. Při výběru vyučujícího, který garantem není, se zobrazují připomínky vztažené pouze k němu.
RNDr. Daniel Zeman, Ph.D. [32-UFAL], Morfologická a syntaktická analýza [NPFL094, přednáška]
Student zakázal zobrazování osobních údajů, 06.01.2024, 1. ročník, Computer Science - Language Technologies and Computational Linguistics, navazující magisterské
The lecturer seems to be very well-educated and experienced in the course topic, but his knowledge covers mainly old techniques and very niche solutions. Moreover, the whole lecture about the Chinese language seems unnecessary since the unique features of this language and solutions to processing hieroglyphs can be discussed in less than 90 minutes. Finally, the homework assignments were a bit unclear in the formulation.
RNDr. Daniel Zeman, Ph.D. [32-UFAL], Zpracování přirozeného jazyka [NPFL124, přednáška]
The lectures were very poor documented: I tried to read the slides and the recorded lecture to understand the concept of 2 level grammar, and it's use in the transducer models, but after 2 watches I still couldn't understand anything. My solution, in this case was to take a look at Jurafsky book about speech and text translation which was much better documented, provided examples for a lot of interesting cases. This was mostly for answering the exam questions: regarding the surface and the lexical language level, I could not understand, what is the input and what is the output? What is the task we want to solve? What is the problem, what is the issue? etc... It was more like a very poor documented solution and extremely disappointing.
Připomínka k předmětu, Morfologická a syntaktická analýza [NPFL094, přednáška]
Student zakázal zobrazování osobních údajů, 06.01.2024, 1. ročník, Computer Science - Language Technologies and Computational Linguistics, navazující magisterské
In the middle of the course, I realized that I don't want to work on MSA in the future, and prefer to stay far away from it - the course is worth taking just to get this insight. MSA is one of the most vague aspects of NLP and there are a lot of ambiguous problems in terms of word/sentence processing. Implementing stem extraction and part-of-speech tagging for English (not even Czech) words was pretty challenging since I had to write a handful of rules by myself and make sure the algorithm was accurate enough. To be honest, I have rewritten the code several times because the assignment task sounded too easy to give up - it fired me up with a sporting interest to make the program work in the right way. To sum up, it's an interesting one, but I'd rather not spend my time on something like that in my academic career.
