|
|
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.
|
|
|
Semantic development of the common lexical basis of Czech, Slovenian and Russian languages
Shchelokova, Galina ; Pilát, Štefan (advisor) ; Hasil, Jiří (referee)
The object of the study is to follow and compare the development of the semantics of lexical units, which have the common Proto-Slavonic base and different meanings in modern languages. The development is studied within a time period ranging from the Proto-Slavonic period up to the modern language state. To cover all three representative groups of Slavic languages: West Slavic, East Slavic and South Slavic were selected the appropriate languages: Czech, Russian and Slovenian. The selection of lexical units is morphologically restricted. The research is focused on adjectives. The work contains theoretical and analytical part. The theoretical part specifies terminology and presents a number views on the potential significance of the development of lexical units in terms of diachronic lexicology. The analysis is devoted to the development and is categorized as follows: each of the twelve selected semantic groups includes sections devoted to Proto-Slavonic, Old Church Slavonic, Russian, Czech and Slovenian languages. Each group is enclosed with a brief summary.
|
|
|
Interplay Between Nomination Tendencies in the Language of Mass Media. The Case of the Analytical Adjectives
Vačkov, Veselin ; Gladkova, Hana (advisor) ; Rangelová, Albena (referee) ; Uhlířová, Ludmila (referee)
The thesis aims to describe and theoretically explain the range of complex nominal word structures and phrases that evolved in all Slavic languages with staggering productivity during the last decades. In particular, it focuses on the so called analytical adjectives, i.e. formally invariant lexical units mostly of foreign origin that manifest their attributive syntactic role (and the word class they belong to) not through a morpheme but through fixed word order position. The thesis rejects the view that analytical adjectives are first parts of compound words and explores several transitional cases. In more general terms, the thesis explores phenomena that test the boundary between words and phrases, morphology and syntax. It concludes that in Bulgarian there already exists a well established word subclass of analytical adjectives. They have resulted from an originally lexical innovation that has been grammatcalized due to intensive borrowings of words and phrase models mainly from English and their replication. The comparative study of present-day Bulgarian and Czech provides evidence of the strategies that the two genetically related languages use to achieve their nomination goals. The search for an explanation of the similarities and differences between both languages offers insights into their...
|
|
|
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.
|
|
|
Linguistic Issues in Machine Translation between Czech and Russian
Klyueva, Natalia ; Kuboň, Vladislav (advisor) ; Panevová, Jarmila (referee) ; Strossa, Petr (referee)
In this thesis we analyze machine translation between Czech and Russian languages from the perspective of a linguist. We work with two types of Machine Translation systems - rule-based (TectoMT) and statistical (Moses). We experiment with different setups of these two systems in order to achieve the best possible quality. One of the questions we address in our work is whether relatedness of the discussed languages has some impact on machine translation. We explore the output of our two experimental systems and two commercial systems: PC Translator and Google Translate. We make a linguistically-motivated classification of errors for the language pair and describe each type of error in detail, analyzing whether it occurred due to some difference between Czech and Russian or is it caused by the system architecture. We then compare the usage of some specific linguistic phenomena in the two languages and state how the individual systems cope with mismatches. For some errors, we suggest ways to improve them and in several cases we implement those suggestions. In particular, we focus on one specific error type - surface valency. We research the mismatches between Czech and Russian valency, extract a lexicon of surface valency frames, incorporate the lexicon into the TectoMT translation pipeline and present...
|
|
|
Semantic development of the common lexical basis of Czech, Slovenian and Russian languages
Shchelokova, Galina ; Pilát, Štefan (advisor) ; Hasil, Jiří (referee)
The object of the study is to follow and compare the development of the semantics of lexical units, which have the common Proto-Slavonic base and different meanings in modern languages. The development is studied within a time period ranging from the Proto-Slavonic period up to the modern language state. To cover all three representative groups of Slavic languages: West Slavic, East Slavic and South Slavic were selected the appropriate languages: Czech, Russian and Slovenian. The selection of lexical units is morphologically restricted. The research is focused on adjectives. The work contains theoretical and analytical part. The theoretical part specifies terminology and presents a number views on the potential significance of the development of lexical units in terms of diachronic lexicology. The analysis is devoted to the development and is categorized as follows: each of the twelve selected semantic groups includes sections devoted to Proto-Slavonic, Old Church Slavonic, Russian, Czech and Slovenian languages. Each group is enclosed with a brief summary.
|
|
|
Interplay Between Nomination Tendencies in the Language of Mass Media. The Case of the Analytical Adjectives
Vačkov, Veselin ; Gladkova, Hana (advisor) ; Rangelová, Albena (referee) ; Uhlířová, Ludmila (referee)
The thesis aims to describe and theoretically explain the range of complex nominal word structures and phrases that evolved in all Slavic languages with staggering productivity during the last decades. In particular, it focuses on the so called analytical adjectives, i.e. formally invariant lexical units mostly of foreign origin that manifest their attributive syntactic role (and the word class they belong to) not through a morpheme but through fixed word order position. The thesis rejects the view that analytical adjectives are first parts of compound words and explores several transitional cases. In more general terms, the thesis explores phenomena that test the boundary between words and phrases, morphology and syntax. It concludes that in Bulgarian there already exists a well established word subclass of analytical adjectives. They have resulted from an originally lexical innovation that has been grammatcalized due to intensive borrowings of words and phrase models mainly from English and their replication. The comparative study of present-day Bulgarian and Czech provides evidence of the strategies that the two genetically related languages use to achieve their nomination goals. The search for an explanation of the similarities and differences between both languages offers insights into their...
|
|
|
Slavic and Nonslavic Synonymy in Romanian Language: A Functional Perspective
Krucká, Barbora ; Ungureanu, Dan (advisor) ; Našinec, Jiří (referee)
(in English): The aim of this paper is to examine the role of Slavic substantive borrowings in Romanian vocabulary. Selected substantive loans are divided into five semantic areas. Analysis of each of them contains a series of synonyms, functional and stylistic inclusion in the Romanian vocabulary, idioms of which is part given lexical unit, and its derivatives. The result is a semantic classification of lexems of Slavic origin in the Romanian vocabulary, their stylistic stratification and position within the synonymic series.
|
|
|
Morphonological features of Sanskrit and their Slavic parallels in the context of relationships between Indo-Iranian and Balto-Slavic languages
Džunková, Katarína ; Kostič, Svetislav (advisor) ; Vacek, Jaroslav (referee)
The present diploma thesis deals with the common morphological and phonological features between Sanskrit and Slavic languages. It contains the list of common lexemes in Sanskrit and Slavic languages added at the end of the thesis. The point of departure of this thesis are the theories of comparative linguistics, which are mentioned in the introduction. Morphophonological parallels are researched in the context of the relationships between Indo- Iranian and Balto-Slavic languages, what helps to distinguish common features between the separated language branches: e. g. common features between Baltic languages and Sanskrit or common features between Slavic and Iranian languages. Iranian and Slavic language contact is analysed in the special chapter. The common features between Sanskrit and Slavic languages supposed to be generally the remnants of common Indo-European principles, which are preserved in both language branches. The special chapter is also devoted to the RUKI sound law, which is regarded as one of the most important common feature between Balto-Slavic and Indo-Iranian languages.
|
|
|
Semantic characteristics of paremias with key word "water" (an attempt at comparative analysis within Russian and Czech)
Kipchatov, Mikhail ; Kedron, Katerina (advisor) ; Rajnochová, Natalie (referee)
The bachelor thesis describes semantic specifics of the Czech and Russian paremias which include "water" as a key word. The aim of the thesis is to discover similarities and differences among paremias which incorporate the "water" component formally. The main methods displayed in the following thesis are comparative and semantic analysis. In Part 1 the main group of paremias (proverbs and sayings) problematics is described, as well as their interaction with other types of fixed expressions (phrasemes, idioms, adages etc.). Part 2 contains two classifications one of which is based on semantic properties of the "water" component; the classification includes the most typical oppositions within which the component is realised in Czech and Russian. The second classification of paremias with key word "water" is founded on the theory of semantic fields (taxa).
|
guest ::
