National Repository of Grey Literature 493 records found  beginprevious21 - 30nextend  jump to record: Search took 0.00 seconds. 
Named Entity Recognition
Rylko, Vojtěch ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
In this master thesis are described the history and theoretical background of named-entity recognition and implementation of the system in C++ for named entity recognition and disambiguation. The system uses local disambiguation method and statistics generated from the  Wikilinks web dataset. With implemented system and with alternative implementations are performed various experiments and tests. These experiments show that the system is sufficiently successful and fast. System participates in the Entity Recognition and Disambiguation Challenge 2014.
Plagiarism Identification
Menšík, Jakub ; Dytrych, Jaroslav (referee) ; Smrž, Pavel (advisor)
The aim of this work is to design and implement system for plagiarism identification based on a huge dataset.
Exploring Contextual Information in Neural Machine Translation
Jon, Josef ; Fajčík, Martin (referee) ; Smrž, Pavel (advisor)
Tato práce se zabývá zapojením mezivětného kontextu v neuronovém strojovém překladu (NMT). Dnešní běžné NMT systémy překládají jednu zdrojovou větu na jednu cílovou větu, bez jakéhokoliv ohledu na okolní text. Tento přístup je nedostačující a neodpovídá způsobu práce lidských překladatelů. Pro mnoho jazykových párů je dnes za splnění určitých (přísných) podmínek výstup NMT nerozeznatelný od lidského překladu. Jedna z těchto podmínek je, že hodnotitelé skórují přeložené věty nezávisle, bez znalosti kontextu. Při hodnocení celých dokumentů je výstup NMT stále hodnocen hůře, než lidský překlad, i v případech, kdy byl na úrovni jednotlivých vět preferován. Tato zjištění jsou motivací pro výzkum zapojení kontextu na úrovni dokumentu v NMT, je totiž možné, že na úrovni vět již není mnoho prostoru ke zlepšení, alespoň pro jazykové páry a domény bohaté na trénovací data. Tato práce shrnuje současné přístupy zapojení kontextu do překladu, několik z nich je implementováno a vyhodnoceno v rámci obecné překladové kvality i na překladu specifických fenoménů souvisejících s kontextem. Pro zhodnocení kvality jednotlivých systému byla ručně vytvořena testovací sada pro překlad z anglického do českého jazyka.
Really Off-Line RSS Reading
Dresto, Erik ; Schwarz, Petr (referee) ; Smrž, Pavel (advisor)
This work deals with the problem of reading RSS articles without active internet connection. The goal of this work was to obtain information about ways of reading RSS articles, to get knowledge about RSS format, get to know its structure and history. Also to find existing solutions of RSS readers, review their advantages and disadvantages from point of expandability, actualization, and possibility to back port on mobile devices. This work also contains brief description of technologies, which are used in work with RSS channels. The reasons of using RSS for reading online articles are given in this work, thereafter the scheme of the application for reading RSS articles without active internet connection, and finally description of its implementation is worked out in it. The result of this work is an application called OfflineRSS Reader created in Java programming language.
Scientific Web Portal Generator
Pavelka, Petr ; Schwarz, Petr (referee) ; Smrž, Pavel (advisor)
Scientific web portal generator is a large project. It's purpose is to create a system for building web portals for providing the view of science publications of authors. One of the parts of this project is module for searching of homepages. The goal of this bachelor's thesis is the implementation of of this module using the program or script. Content of this thesis is to find the best way of method of extraction the semantic information from the marked text, design and development o the system and creating the test set for the purpose of testing. The output of this thesis should be prototype of program or script, which will generate XML file with the URL adresses of homepages of authors. System should have XML input. Almost entire thesis is about analyzing of this problem and choosing the best solution.
XML Dictionary Tagging
Šubrt, Jan ; Grézl, František (referee) ; Smrž, Pavel (advisor)
This Bachelor's thesis describes system for managing dictionaries in XML form. It also describes XML standard language family (XSLT, XPath, XSD, ...) and points out the qualities of computer processing of dictionaries stored in form of XML. The practical part shows translation of non-structured forms of dictionaries to XML using grammars.
Commented Scientific Bibliography
Oram, Vojtěch ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
This bachelor's thesis describes science portal with focus on annotated bibliography. The main objective was to create tools for easier searching, organizing and annotating scientific publications. The result application was implemented in web framework Django and supports desired functionality for creating bibliographies.
Analysis of Product Reviews
Klocok, Andrej ; Doležal, Jan (referee) ; Smrž, Pavel (advisor)
Online store customers generate vast amounts of product and service information through reviews, which are an important source of feedback. This thesis deals with the creation of a system for the analysis of product and shop reviews in the czech language. It describes the current methods of sentiment analysis and builds on current solutions. The resulting system implements automatic data download and their indexing, subsequently sentiment analysis together with text summary in the form of clustering of similar sentences based on vector representation of the text. A graphical user interface in the form of a web page is also included. A review data set with a total of more than six million reviews was created during the semester along with an interface for easy data export.
Extraction of Relations among Named Entities Mentioned in Text
Voháňka, Ondřej ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
This bachelor's thesis deals with relation extraction. Explains basic knowledge, that is necessary for creating an extraction system. Then describes design, implementation and comparison of three systems, which works differently. Following methods were used: regular expressions, NER, parser. 
Combat Management in Starcraft II Game by Means of Artificial Intelligence
Krajíček, Karel ; Fajčík, Martin (referee) ; Smrž, Pavel (advisor)
This thesis focuses on the use of Artificial Intelligence and design of working module in Real-Time Strategy (RTS) game, StarCraft II.  The proposed solution uses Neural Network and Q-learning for combat management. For implementation, the StarCraft 2 Learning Environment has been used as a means of communication between the designed system and the game. Evaluation of the system is based on its ability to make progress over time.

National Repository of Grey Literature : 493 records found   beginprevious21 - 30nextend  jump to record:
See also: similar author names
7 SMRŽ, Pavel
5 SMRŽ, Petr
4 Smrž, Peter
5 Smrž, Petr
Interested in being notified about new results for this query?
Subscribe to the RSS feed.