|
|
Text data mining as an viable method of Japanese studies
Štefková, Tereza ; Kanasugi, Petra (advisor) ; Rosen, Alexandr (referee)
In this thesis we address the problem of possible utilization of text mining methods in the field of Japanese studies. We review the fundamental text mining approaches and their practical applications in the first part. Then we elaborate on the topic of preprocessing with special focus on techniques used for Japanese and English texts. In the main part of the thesis we apply text mining methods to three concrete research questions relevant in Japanese studies. The first research topic illustrates the technique of clustering applied to works written by two Japanese proletarian authors to reveal interesting topic patterns in their writings. The second topic makes use of the sentiment analysis with the aim of studying the extent of negative sentiment expressed in both foreign and Japanese newspaper articles that refer to Japanese officials' visits to Yasukuni shrine. Finally, we address methods of automatic summarization and their application to Japanese as well as English sample texts. The results obtained are discussed in detail with a special focus on the assessment of viability of the presented methods in Japanese studies.
|
|
|
Textual equivalency of selected Polish adjectives: corpus-based analysis
Holmanová, Vladimíra ; Zasina, Adrian Jan (advisor) ; Rosen, Alexandr (referee)
This bachelor thesis deals with textual equivalence of selected Polish adjectives (lichy, bezcenny, pozostały, konieczny and ostatni). Chosen adjectives are also sneaky words (so- called false friend - faux amis), which have their similar-sounding counterpart in Czech. This thesis is divided into a theoretical and a practical part. In the theoretical part, significant space is devoted to the concept of equivalence and literature, which deals with this topic. Afterwards, the concept of false friends is specified, especially in Czech and Polish. Next passage deals with corpora, it also focuses on advanteges of corpus in comparisonto dictionary. The aim of the analytical part is to find out the current state of Czech translation equivalentsthat are not always described in the dictionary. Therefore, dictionary equivalence is compared with textual equivalence. The subcorpus of the parallel corpus InterCorp v14 is used as a source of texts. It contains original Polish texts and their Czech translations. In the conclusion of the thesis, the results proceed from the corpus material analysis are summarized. Key words: corpus linguistics, parallel corpus, InterCorp, textual equivalence, Polish, Czech, Translation Studies.
|
|
| |
|
|
Netgraph-A Tool for Searching in the Prague Dependency Treebank 2.0
Mírovský, Jiří ; Hajič, Jan (advisor) ; Rosen, Alexandr (referee) ; Ondruška, Roman (referee)
Three sides existed whose connection is solved in this thesis. First, it was the Prague Dependency Treebank 2.0, one of the most advanced treebanks in the linguistic world. Second, there existed a very limited but extremely intuitive search tool - Netgraph 1.0. Third, there were users longing for such a simple and intuitive tool that would be powerful enough to search in the Prague Dependency Treebank. In the thesis, we study the annotation of the Prague Dependency Treebank 2.0, especially on the tectogrammatical layer, which is by far the most complex layer of the treebank, and assemble a list of requirements on a query language that would allow searching for and studying all linguistic phenomena annotated in the treebank. We propose an extension to the query language of the existing search tool Netgraph 1.0 and show that the extended query language satisfies the list of requirements. We also show how all principal linguistic phenomena annotated in the treebank can be searched for with the query language. The proposed query language has also been implemented - we present the search tool as well and talk about the data format for the tool. An attached CD-ROM contains the installation of the tool.
|
|
|
An HPSG-based Formal Grammar of a Core Fragment of Georgian Implemented in TRALE
Abzianidze, Lasha ; Rosen, Alexandr (advisor) ; Hana, Jiří (referee)
Georgian is remarkably different from Indo-European languages. The language has several linguistic phenomena that are challenging both from theoretical and computational points of view. In addition, it is low- resourced and insufficiently studied from the computational point of view. In the thesis, we model morphology and syntax of a core fragment of the language in a formal grammar. Namely, the formal grammar is written in the HPSG framework - one of the most powerful grammar frameworks nowadays. We also implement the grammar in TRALE - a grammar implementation platform, which is faithful to "hand-written" HPSG-based grammars. Note that this is the first application of HPSG to Georgian.
|
|
| |
|
| |
|
|
Verbal resources for affective stance display in Japanese conversational interactions
Zawiszová, Halina ; Barešová, Ivona (advisor) ; Jabłoński, Arkadiusz (referee) ; Rosen, Alexandr (referee)
This thesis focuses on verbal resources for affective stance display in Japanese conversational interactions. Its aim was to determine the major types of linguistic forms and formats that are systematically and methodically employed by Japanese speakers for the purpose of constructing affective stance displays in their everyday informal conversational interactions and to demonstrate some of the ways in which they may be used together with other resources to accomplish particular affective stance displays in the context of specific actions and activities. The thesis considers various affective-stance-display-related uses of lexical categories, verbal morphology, demonstratives, zero-marking, topic-marking, person reference, connective expressions, non-predicate-final constituent order, direct speech constructions, question forms, syntactically incomplete utterance constructions, and utterance-final elements. It is based on the study of recordings of spontaneous conversational interactions primarily of Japanese young adults in close personal relationships. Methodically, the thesis draws mainly on conversation analysis and interactional linguistics.
|
|
|
Text data mining as an viable method of Japanese studies
Štefková, Tereza ; Kanasugi, Petra (advisor) ; Rosen, Alexandr (referee)
In this thesis we address the problem of possible utilization of text mining methods in the field of Japanese studies. We review the fundamental text mining approaches and their practical applications in the first part. Then we elaborate on the topic of preprocessing with special focus on techniques used for Japanese and English texts. In the main part of the thesis we apply text mining methods to three concrete research questions relevant in Japanese studies. The first research topic illustrates the technique of clustering applied to works written by two Japanese proletarian authors to reveal interesting topic patterns in their writings. The second topic makes use of the sentiment analysis with the aim of studying the extent of negative sentiment expressed in both foreign and Japanese newspaper articles that refer to Japanese officials' visits to Yasukuni shrine. Finally, we address methods of automatic summarization and their application to Japanese as well as English sample texts. The results obtained are discussed in detail with a special focus on the assessment of viability of the presented methods in Japanese studies.
|
|
|
Coreference from the Cross-lingual Perspective
Novák, Michal ; Žabokrtský, Zdeněk (advisor) ; Stede, Manfred (referee) ; Rosen, Alexandr (referee)
Coreference from the Cross-lingual Perspective Michal Nov'ak The subject of this thesis is to study properties of coreference using cross- lingual approaches. The work is motivated by the research on coreference-related linguistic typology. Another motivation is to explore whether differences in the ways how languages express coreference can be exploited to build better models for coreference resolution. We design two cross-lingual methods: the bilingually informed coreference resolution and the coreference projection. The results of our experiments with the methods carried out on Czech-English data suggest that with respect to coreference English is more informative for Czech than vice versa. Furthermore, the bilingually informed resolution applied on parallel texts has managed to outperform the monolingual resolver on both languages. In the experiments, we employ the monolingual coreference resolver and an improved method for alignment of coreferential expressions, both of which we also designed within the thesis. 1
|
guest ::
