This thesis deals with associations between words. Describes the design and implementation of a system that can represent a human in the word-association game Codenames. The system uses the Gensim and FastText libraries to create semantic models. The relationship between words is taught by the analysis of the text corpus CWC-2011.

This thesis describes opinions about generating code from PNtalk language into more standard object orinted languages, such as C++ or Java. Goal is to construct model of the formalism of Object Oriented Petri Nets (OOPN), represented in PNtalk languege in mentioned languages. This model should be simlpier and more effective than actual implementation in Smalltalk language. Thesis also contains ideas about abstactization the code generator to be able to generate code in various languages.

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.

Title: Knowledge Graph Extraction from Project Documentation Author: Bc. Tomáš Helešic Department: Department of Software Engineering Supervisor: Mgr. Martin Nečaský, Ph.D. Abstract: With the new research progress in the natural language processing and information extraction from text, new possibility of automatic knowledge acqui- sition and its grouping into Knowledge graphs, that are catching the semantic relations between these entities is emerging. For these Knowledge graphs, data storages and also query languages already exists, which allow more precise and relevant search possibilities compare with current full text search engines. The goal of this thesis is to explore the opportunity of automatic extraction of infor- mation from project documentation with the use of linguistic text processing, design a proper data storage and build a search engine over it. Keywords: Knowledge grahs, Information extraction, Natural language process- ing, Resource Description Framework 1

Title: Knowledge Graph Extraction from Project Documentation Author: Bc. Tomáš Helešic Department: Department of Software Engineering Supervisor: Mgr. Martin Nečaský, Ph.D. Abstract: The goal of this thesis is to explore the possibilities of automatic in- formation extraction from company project documentation with the use of ma- chine natural language processing and the analysis of the precision of linguistic processing of these documents. Furthermore suggest methods how acquire key terms and dependencies between them. From this terms and dependencies cre- ate knowledge graphs, that are stored in an appropriate database with search engine. The work is trying to interconnect already existing technologies in a shape of a simple application and test their readiness for a practical use. The goal is to inspire future research in this field, identify critical parts and propose improvements. The main gain is in the interconnection between natural lan- guage processing, methods of information extraction and semantic searching in corporate documents. The gain of the practical part reside in the way how to identify key information that is uniquely describing each document and its use in search. Keywords: Knowledge graphs, Information extraction, Natural language pro- cessing, Resource Description Framework 1

The dissertation provides a grammatical description of a cluster of Romani varieties, called 'Eastern Uzh Romani', which are spoken in Transcarpathian Ukraine in an area adjacent to the Slovak border. These varieties are associated with five traditional locations, two of which are situated in the city of Uzhhorod, representing an eastern margin of a North Central Romani dialect continuum. The focus is not only on describing the common characteristics of the entire Eastern Uzh dialect, but also on highlighting its variation with respect to specific features of the individual varieties. The description is based on first-hand data collected during numerous fieldwork trips of the author between 2007 and 2016. The dissertation is organised into thirteen chapters. Alongside the proper grammatical description, it provides a detailed overview of the speakers' historical, ethnocultural and sociolinguistic background. The main attention is given to describing inflectional, derivational as well as functional patterns of word classes. In addition, it discusses issues of phonology, including historical phonology within the North Central Romani context, and also covers various syntactic structures.

While recent neural sequence-to-sequence models have greatly improved the quality of speech synthesis, there has not been a system capable of fast training, fast inference and high-quality audio synthesis at the same time. In this the- sis, we present a neural speech synthesis system capable of high-quality faster- than-real-time spectrogram synthesis, with low requirements on computational resources and fast training time. Our system consists of a teacher and a student network. The teacher model is used to extract alignment between the text to synthesize and the corresponding spectrogram. The student uses the alignments from the teacher model to synthesize mel-scale spectrograms from a phonemic representation of the input text efficiently. Both systems utilize simple convo- lutional layers. We train both systems on the english LJSpeech dataset. The quality of samples synthesized by our model was rated significantly higher than baseline models. Our model can be efficiently trained on a single GPU and can run in real time even on a CPU. 1

In this thesis, we explore the potential benefits of leveraging eye-tracking information for dependency parsing on the English part of the Dundee corpus. To achieve this, we cast dependency parsing as a sequence labelling task and then augment the neural model for sequence labelling with eye-tracking features. We also augment a graph-based parser with eye-tracking features and parse the Dundee Corpus to corroborate our findings from the sequence labelling parser. We then experiment with a variety of parser setups ranging from parsing with all features to a delexicalized parser. Our experiments show that for a parser with all features, although the improvements are positive for the LAS score they are not significant whereas our delexicalized parser significantly outperforms the baseline we established. We also analyze the contribution of various eye-tracking features towards the different parser setups and find that eye-tracking features contain information which is complementary in nature, thus implying that augmenting the parser with various gaze features grouped together provides better performance than any individual gaze feature. 1

(in English): This thesis focuses on pragmatic competence of Czech students of Japanese, specifically on the speech act of refusal. The aim is to find out how students differ in comparison to native speakers of Japanese. Another aim is to compare Japanese students based on the length of their stay in Japan, their Japanese proficiency, and the textbook used at the beginner level. The theoretical part describes pragmatic competence, politeness theory, the speech act of refusal and its specifics in Japanese. The practical part focuses at the analysis of refusals from the Discourse Completion Task (DCT) using semantic formulas. Usage of these formulas by native speakers and student are then compared. Found differences from the native speakers are further examined among students according to Japanese proficiency, length of their stay in Japan and textbook used at the begginer level. Finally, the results are summarized.

Although the term CLIL standing for Content and Language Integrated Learning appeared as early as in 1994, and the European Union recognized it very quickly as a prospective and effective way of learning and teaching languages, it seems neither to have been used extensively within the Czech education system, nor there appears to be a general awareness of the method. However, this approach represents a great opportunity for creating more authentic atmosphere within language classrooms and simultaneously teaching and learning a content subject. When speaking of CLIL, several factors must be considered, such as its objectives, principles, methodology, discourse and materials, furthermore we have to take into account the criteria for designing and analysing material for language teaching (of course also in the view of the chosen content subject principles and objectives). In order to raise the awareness of CLIL as an effective approach to language and subject content teaching and to partly supply the lack of CLIL-focused materials, this thesis aims to take into account all the factors and present and analyse them in logical sequences, so finally an effective piece of material usable in CLIL classes could be created and subsequently analysed and evaluated. The present thesis is divided into three parts...