|
|
Low-Resource Neural Machine Translation
Filo, Denis ; Fajčík, Martin (referee) ; Jon, Josef (advisor)
This thesis deals with neural machine translation (NMT) for low-resource languages. The goal was to evaluate current techniques by using the experiments and suggest their improvements. The translation systems in this thesis used the neural network transformer architecture and were trained by the Marian framework. The selected language pairs were Slovak with Croatian and Slovak with Serbian. The subjects of the experiments were the transfer learning techniques and semi-supervised learning.
|
|
|
Web as a Source for Automatic Creation of Morphological Dictionary
Bulka, Pavol ; Matějka, Pavel (referee) ; Smrž, Pavel (advisor)
Creation of natural language words is based on rules, which are generally complex. Often it is very difficult or even impossible to describe them precisely in a formal way. That is why we use a morphological dictionary to process natural language. In this paper we discuss the creation of morphological dictionary from Slovak's top level domain web. We talk about web crawling, data processing for morphological analysis and data structures too. This document makes basic principle and conception of morphological analysis clear. Final system, which is described in this thesis, produces morphological dictionary. This dictionary can be use in various application, for example spell checker, machine translation and so on.
|
|
|
Low-Resource Neural Machine Translation
Filo, Denis ; Fajčík, Martin (referee) ; Jon, Josef (advisor)
This thesis deals with neural machine translation (NMT) for low-resource languages. The goal was to evaluate current techniques by using the experiments and suggest their improvements. The translation systems in this thesis used the neural network transformer architecture and were trained by the Marian framework. The selected language pairs were Slovak with Croatian and Slovak with Serbian. The subjects of the experiments were the transfer learning techniques and semi-supervised learning.
|
|
|
Czech and Slovak Contact Lexical Phenomena in Their Metalanguage Reflection (text corpus-based)
Gajdošová, Katarína ; Nábělková, Mira (advisor) ; Hoffmannová, Jana (referee) ; Slančová, Daniela (referee)
The present work focuses on metalanguage comments in Slovak and Czech texts. The comments occur together with contact-induced phenomena employed by both languages and can be identified in text fragments, such as Áno, taký som aj ostanem, lebo vraj starého psa novým kouskúm nenaučíš - ako hovoria bratia Česi / Nebyl jsem schopen jídla, ale lemtal jsem vodu "ani ťava", jak říkají bratia Slováci. The given issue is presented in the context of research focusing on the non-theoretic (folk, naive) metalinguistic reflection. The usage of metalanguage comments, accompanying deliberately contact-induced phenomena, is a testament to the existence of the Czech-Slovak and Slovak-Czech language contact and it clearly shows how Slovak and Czech language users intentionally employ words, multi-word units, idioms and other linguistic devices from the other language to fulfill their communicative intention. By using the contact-induced phenomena from the closely related language the speaker can achieve various communicativ e goals and effects including actualization and refreshing of his or her utterance, being more expressive and filling in subjectively perceived intro-linguistic lacuna. The starting point of the analysis of the metalanguage comments were the data from the Slovak and Czech corpus. A range of...
|
|
|
Particles in Slovak and Czech. System and Corpus Analysis
Šimková, Mária ; Nábělková, Mira (advisor) ; Vondráček, Miloslav (referee) ; Sokolová, Miloslava (referee)
The youngest word class type used to arouse great interest and discussions when entering the grammar; in some countries (e. g. in Germany) particles have been an object of systematic research. However, many other languages still lack a complex description of particles as a class on its own - they represent an appropriate material also for comparative researches. Differences in functioning and theoretical treatment of particles have been present in typologically different languages but they can emerge also in related languages, even in the case of Slovak and Czech. Lexicographical and grammar descriptions of these languages provide only small sets of particles (in Slovak roughly amounting to 400, in Czech exceeding 200) and are usually divided by authors into small groups and further on into even smaller subgroups. Due to specific features as well as to paradigmatic and syntagmatic relations with other language or speech phenomena even one particle or a couple of them or a narrowly defined group of particles can become an object of individual scientific and research projects. Step by step, our thesis presents the development of attitudes towards particles as an independent word class in general and in Russian linguistics in particular, grammar descriptions of particles in Slovak, Czech and other...
|
|
|
Assimilation of voicing in Slovak speakers of English
Ortutayová, Dominika ; Skarnitzl, Radek (advisor) ; Popelíková, Jiřina (referee)
The aim of this thesis is to examine the influence of the mother tongue, more specifically Slovak, in the speech of the Slovak speakers of English and subsequent appearance of the assimilation of voicing in the environments in which it is expected in both Slovak and English and then in those which are typical only for Slovak - and the production of the assimilation of voicing in those environments in English is considered an error. In the first part we introduce and specify the process of voicing in speech in general and then in the second part we proceed with the presentation of the concept of the second language acquisition and language interference. The empirical part is based on the analysis of the material spoken by 18 students, both males and females, reading the BBC bulletins. Our results show that the assimilation of voicing is an integral part of the speech of Slovaks in English, proving that they assimilate extensively in the environments typical for the Slovak language. Those are only partially typical for English as well - and thus they simultaneously produce assimilation errors. This knowledge could be taken in account during the learning process in order to eliminate such errors as much as possible. Key words: voicing, assimilation, Slovak, English, interference
|
|
|
The occurrence of word-initial glottalization in Slovak English
Uhrinová, Mária ; Skarnitzl, Radek (advisor) ; Popelíková, Jiřina (referee)
The occurrence of word-initial glottalization in Slovak English Mária Uhrinová Praha, 2012 Abstract The features of prosodic structure were shown to influence the occurrence of word-initial glottalization in English. The aim of the present thesis is to analyze the occurrence of glottalization in word-initial vowels in Slovak English in relation to prosodic structure, specifically to word stress and position in the intonational phrase. The semantic status of words (lexical vs. grammatical) is also considered. The first part provides a brief overview of key concepts in second language acquisition with focus on acquisition of second language phonology. In addition, a summary of previous research on glottalization is given. The empirical part of this thesis is based on the recordings of 15 Slovak speakers of English. The results suggest that Slovak speakers use glottalization extensively in their production of English. This should be taken into consideration when looking for better methods for teaching English pronunciation. Keywords: glottalization, prosodic structure, Slovak, English, foreign accent
|
|
|
Web as a Source for Automatic Creation of Morphological Dictionary
Bulka, Pavol ; Matějka, Pavel (referee) ; Smrž, Pavel (advisor)
Creation of natural language words is based on rules, which are generally complex. Often it is very difficult or even impossible to describe them precisely in a formal way. That is why we use a morphological dictionary to process natural language. In this paper we discuss the creation of morphological dictionary from Slovak's top level domain web. We talk about web crawling, data processing for morphological analysis and data structures too. This document makes basic principle and conception of morphological analysis clear. Final system, which is described in this thesis, produces morphological dictionary. This dictionary can be use in various application, for example spell checker, machine translation and so on.
|
guest ::
