|
|
Information Extraction from Loosely Structured Text
Minárik, Matej ; Bartík, Vladimír (referee) ; Burget, Radek (advisor)
Nowadays we are speaking about Web 2.0, which means the web of documents rather than the web of data. Documents are mostly unstructured, or just partially structured, but search engines need data in structured form in order to provide better search results. The process of extracting structured data from partially structured documents is the main goal of this work. In this work we are analyzing information extraction methods, namely classification methods, which need annotated training data, in order to create their inner model. We also analyze methods, which do not need training. These methods are initialized with a few data examples we are interested in extracting. We propose an extraction method in order to extract therapeutic indications and active substances from medical information sheets.
|
|
|
Organization of children's summer camp with a focus on first aid and protection of the population
MINÁRIK, Matej
The key aim of this thesis was to create a complex and detailed guide for organization of a children's camp focusing on the first aid and population protection. Based on the guide, a lay reader will be able to create their own camp and that without any experience with the issue. Among partial aims, preparing material for camp's realization including the camp's narrative preparation, assessing program and games, and producing teaching materials for the program and camp leaders training were listed. Another partial aim was the camp execution and overall detailed assessment. In a theoretical part of the thesis, we took a closer look into the issue of free time pedagogy and its influence on child upbringing. We also wrote what kind and type of camps we know and what camp organization involves, including legislation, budget and financing, activities and program structure. In the thesis results, we describe an exact organization procedure of our own camp focusing on the first aid and population protection, which took place from July 30, 2017 to August 6, 2017 in Rajecká Lesná. The exact same procedure is described as a guide, which includes two parts, the preparation organized before the beginning of the camp and the camp's execution itself. The preparation part involves the grounds selection, budget and financing determination, and specifically determined monthly preparation schedule. The realization part includes the camp's motivational narrative, a whole-camp game, the manuals for camp leaders and a general framework program for the specific camp days. The days are individually stated in the precise timetable which includes a program prepared for the given camp focus. In the discussion, we assess the success of the camp execution along with the individual days description. We believe this thesis will serve as a basis for organization of the camps with the similar focus in the future.
|
|
|
Information Extraction from Loosely Structured Text
Minárik, Matej ; Bartík, Vladimír (referee) ; Burget, Radek (advisor)
Nowadays we are speaking about Web 2.0, which means the web of documents rather than the web of data. Documents are mostly unstructured, or just partially structured, but search engines need data in structured form in order to provide better search results. The process of extracting structured data from partially structured documents is the main goal of this work. In this work we are analyzing information extraction methods, namely classification methods, which need annotated training data, in order to create their inner model. We also analyze methods, which do not need training. These methods are initialized with a few data examples we are interested in extracting. We propose an extraction method in order to extract therapeutic indications and active substances from medical information sheets.
|
guest ::
RSS feed.