|
|
Information Extraction from Wikipedia
Krištof, Tomáš ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
This bachelor's thesis describes the issue of information extraction from unstructured text. The first part contains summary of basic techniques used for information extracting. Thereafter, concept and realization of the system for information extraction from Wikipedia is described. In the last part of thesis, results, coming from experiments, are analysed.
|
|
|
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.
|
|
|
Optimalizace výrobního procesu s využitím umělé inteligence
Košťál, Martin
Bachelor’s thesis deals with the creation of solutions that facilitate the planning of production in the company. The first solution was designed with the rule system using a Python programming language. The second solution consisted of building a neural network process that was designed in the TensorFlow framework. The resulting solution is created from the rule system and the neural network. The finished solution is implemented in the company using a web application written in the Flask framework.
|
|
|
Named Entity Normalization in Czech Texts
Kubát, Petr ; Vidová Hladká, Barbora (advisor) ; Popel, Martin (referee)
Named entities are collocations used to refer to real world objects in text. Named entity normalization is a process of generating the basic form for a given named entity. The thesis is focused on creating a rule- based procedure for named entity normalization in Czech texts. The process of designing individual rules is closely examined. Stress is laid on the fact that each rule is motivated by entities from real-world texts. Additionally, some aspects of Czech language syntax are analyzed in order to achieve the highest possible accuracy. Based on the theoretical description of the procedure, a normalization application is implemented, and its accuracy is evaluated by comparison with manually normalized entities. Together with already existing tools for automatic named entity recognition, it is possible to use this normalizer in other text processing tasks, such as machine translation, searching and categorization, etc. Powered by TCPDF (www.tcpdf.org)
|
|
|
Information Extraction from Wikipedia
Krištof, Tomáš ; Otrusina, Lubomír (referee) ; Smrž, Pavel (advisor)
This bachelor's thesis describes the issue of information extraction from unstructured text. The first part contains summary of basic techniques used for information extracting. Thereafter, concept and realization of the system for information extraction from Wikipedia is described. In the last part of thesis, results, coming from experiments, are analysed.
|
|
|
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.
|
|
|
Data Structure Estimation - Rule Based Algorithm
Řimnáč, Martin
The data structure estimation may provide a connection between the semantic web vision and currently used web sources containing no semantic description of presented information. It enables information from web pages to be processed by semantic web tools with the best to be known about these sources, with the source estimated data structure. The paper gives a method description and presents its usage for a inductive logic programming task. The advantages of a rule-based system usage is given as well.
|
|
|
Design of Business Rule Engine solution
Zaplatílek, Jakub ; Stanovská, Iva (advisor) ; Komárek, Jiří (referee)
This diploma thesis defines the issue of Business Rule Approach and the technological aspects connected. The aim is to enclose this relatively new topic to the leader. This paper includes the essential techniques and recommendations for rule approach. The thesis includes basic definition of important terms and theoretical overview of used technology. Important point is to highlight the main benefits for a business people that come up from implementing rule based system into the company's information system. The part of this paper is exploring dependencies between business rules, processes and workflows. There are two classic ways to analyze and design information systems -- structure based and object based. According to business needs the new way arises -- the business rule approach. The practical part include concept of functional specification of an application using a module for analyzing a evaluating business rules. The basic policies how the Rule Engines are implemented into the information systems are specified in the technological chapter along with description. There are also elementary operations which can one do with the rules. In one part of the thesis is a description of an software tool developed by company named ILOG. It is called JRules and it provide a full-fledged tool by which you can design, develop, implement and test whole scale business rule projects.
|
guest ::
