|
|
Encyclopedia Expert
Krč, Martin ; Schmidt, Marek (referee) ; Smrž, Pavel (advisor)
This project focuses on a system that answers questions formulated in natural language. Firstly, the report discusses problems associated with question answering systems and some commonly employed approaches. Emphasis is laid on shallow methods, which do not require many linguistic resources. The second part describes our work on a system that answers factoid questions, utilizing Czech Wikipedia as a source of information. Answer extraction is partly based on specific features of Wikipedia and partly on pre-defined patterns. Results show that for answering simple questions, the system provides significant improvements in comparison with a standard search engine.
|
|
|
Information Extraction from Wikipedia
Musil, Martin ; Otrusina, Lubomír (referee) ; Schmidt, Marek (advisor)
This bachelor thesis deals with the problem of automatic information extraction from text. Goal is to create an application, which captures knowledge out of the articles from online information server Wikipedia, using extraction patterns. At the beginning, we interpret the basic terms of the subject and the main part of the publication is focused to the experiments and above all to the implementation, divided into two parts, processing of the text and following information extraction. The conclusion of the thesis analyses the results coming from experiments and efficiency of created rules.
|
|
|
Wikipedia Page Classification
Suchý, Ondřej ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
The goal of this paper is to design and implement a system for selection of Wikipedia articles relevant to a given topic in order to reduce the amount of memory taken by its offline version. The solution of this problem was achieved with use of methods from information retrieval and theirs implementation using Elasticsearch search engine. The system tries to determine the area of user's interest by given keywords and make a selection of articles from that area. This is achieved by measuring of similarity of articles and adding all articles from frequent categories in the selection. The sizes of the output files for queries over Simple English Wikipedia are usually below 30 MB.
|
|
|
Methods of Information Extraction
Adamček, Adam ; Smrž, Pavel (referee) ; Kouřil, Jan (advisor)
The goal of information extraction is to retrieve relational data from texts written in natural human language. Applications of such obtained information is wide - from text summarization, through ontology creation up to answering questions by QA systems. This work describes design and implementation of a system working in computer cluster which transforms a dump of Wikipedia articles to a set of extracted information that is stored in distributed RDF database with a possibility to query it using created user interface.
|
|
| |
|
| |
|
|
Web 2.0 and its impact on business
Vachovec, Milan ; Donát, Jiří (advisor) ; Tůma, Pavel (referee)
The thesis Web 2.0 and its impact on business introduces the Web 2.0 concept and its characteristics in the first chapter. Owing to the fact that Web 2.0 is still a controversial theme to a certain extent, the following chapter is focused on the question, whether Web 2.0 is only a marketing label (buzzword) or a conception with a real content. In the third chapter there are examples of concrete web applications and services, which illustrates the areas, where the new Web is successfully established. These representatives are Web 2.0 flagships to a certain degree and for many people synonymous with this term too. The thesis is also concerned with the possibilities of commercial Web 2.0 usage. Web 2.0 has been discussed for several years and since relevant services have been in existence, there have been visible impacts of those new Webs on business. The last but one chapter deals with its possible impacts on selected areas of business. The content of the last chapter is a contemplation on how the Web is going to develop in the next years. There are also discussed social questions connected with quick development of the Internet and Web 2.0.
|
|
|
Comparison of the use of New Media between the Czech Republic and Spain
Pirela, Maríacristina Cáceres ; Pavlíček, Antonín (advisor) ; Montani, Antonio (referee)
The purpose of this study was to determinate the differences and similarities in the use of Internet and New Media between Czech Republic and Spain. This thesis defined the Internet user's profile and the usage of the Internet in both nations. It was also analyzed the social software Facebook, Tuenti (Spain) and Lidé (Czech Republic); the online encyclopedia Wikipedia and the server YouTube (and its closest competitor in each country). The information was mainly gathered from Internet. Then it was analyzed and compared. The author used her personal experience and knowledge of both cultures for the interpretation of the results. This work showed that there is not a big difference in the usage of Internet and New Media between these countries. For example, the difference in the Internet usage is not bigger than 5%. It also showed that Czech Republic has experienced the biggest growth in the area, even though Spain has more users. Both countries showed similar interest in web pages such as Facebook, Google and YouTube. Additionally, it demonstrated that the Spanish market is reacting better to the new opportunities offered by the social software. For this reason, they had created their own -- called Tuenti -- which is the main competition of Facebook in this country. On the other hand, Czech Republic does not have a website that counts with all the services offered by Facebook, which can explain the growth on the numbers of Czech users the last year. Wikipedia has versions available on the native languages of both countries. It is widely used, not only by the students who use it as a source for their paper work, but also in areas like marketing and journalism. YouTube is one of the most popular servers in these nations. They have their local video servers, but none of them have the same importance as YouTube. The author hopes this work will be a base for future investigators who will be interested on the comparison of these countries on the new technologies.
|
|
|
Kredibilita informací na internetu
Dobrovolný, Tomáš ; Rosický, Antonín (advisor) ; Brabec, Jan (referee)
Internet obsahuje spoustu nedůvěryhodných informací, a proto je důležité umět tuto důvěryhodnost posoudit a umět vybrat jen kredibilní data. Mít základní přehled o tom, co od některých konkrétních zdrojů na internetu očekávat a vědět které jsou považovány za velmi seriózní a které naopak jsou příznačné svou velkou míru nedůvěryhodnosti.
|
|
|
Community web services and their business usage
Lapotka, Aliaksandr ; Raška, Ondřej (advisor) ; Zakharenkava, Sviatlana (referee)
The bachelor thesis deals with the community web services and their business usage. It is divided into four parts. The first part is an introduction in which it discussed the issue and derivation of the community web services, on what they are based. The second part of the thesis is an about accessibility and the usability of the web services. Part of the chapter are graphic features, functionality and selection of the address of website service. Another part is based on the classification of web services, a description of social networks as one of the elements of community services. An example of the Facebook is used for a wider understanding of the possibilities of community web services. Also in this section are analyzed the future and the development of web services. One of the most interesting part of the bachelor thesis is the last fourth part. It is about the development phase, ensuring the good will and image of the community web services.
|
guest ::
