|
|
Recognition of emotions in Czech texts
Červenec, Radek ; Smékal, Zdeněk (referee) ; Burget, Radim (advisor)
With advances in information and communication technologies over the past few years, the amount of information stored in the form of electronic text documents has been rapidly growing. Since the human abilities to effectively process and analyze large amounts of information are limited, there is an increasing demand for tools enabling to automatically analyze these documents and benefit from their emotional content. These kinds of systems have extensive applications. The purpose of this work is to design and implement a system for identifying expression of emotions in Czech texts. The proposed system is based mainly on machine learning methods and therefore design and creation of a training set is described as well. The training set is eventually utilized to create a model of classifier using the SVM. For the purpose of improving classification results, additional components were integrated into the system, such as lexical database, lemmatizer or derived keyword dictionary. The thesis also presents results of text documents classification into defined emotion classes and evaluates various approaches to categorization.
|
|
|
Recognition of emotions in Czech texts
Červenec, Radek ; Smékal, Zdeněk (referee) ; Burget, Radim (advisor)
With advances in information and communication technologies over the past few years, the amount of information stored in the form of electronic text documents has been rapidly growing. Since the human abilities to effectively process and analyze large amounts of information are limited, there is an increasing demand for tools enabling to automatically analyze these documents and benefit from their emotional content. These kinds of systems have extensive applications. The purpose of this work is to design and implement a system for identifying expression of emotions in Czech texts. The proposed system is based mainly on machine learning methods and therefore design and creation of a training set is described as well. The training set is eventually utilized to create a model of classifier using the SVM. For the purpose of improving classification results, additional components were integrated into the system, such as lexical database, lemmatizer or derived keyword dictionary. The thesis also presents results of text documents classification into defined emotion classes and evaluates various approaches to categorization.
|
|
|
On the exemplification of nouns in the Pralex Lexical Database
Koutová, Marta
The treatment of the individual database entries is focused principally on the exemplary part (exemplification), which in the Pralex LDB has a specifically defined structure (classification into exemplification subblocks) for each word class. With nouns, we have focused on a detailed description of the syntactic and semantic collocablity. What is important for us in the treatment is the selection of relevant corpus evidence, i.e. examples of the specific usage for the meanings pre-established in the Standard Czech Language (SSJČ), as well as capturing the evidence for new meanings not listed in that dictionary. We illustrate the nouns primarily by uncited evidence, i.e. exemplary collocations in the form of syntagmata, which represent the common collocations of the treated nouns; to a lesser extent we present also sentential citation evidence, i.e. with the citation of the source.
|
|
|
Bulgarian-Czech Dictionary Database Project
Rangelova, Albena ; Sixtová, Hedvika ; Kalajdžievová, N.
In connection with the successful international cooperation of the Institute of the Czech Language of the ASCR, v. v. i., (ICL) with the Institute for the Bulgarian Language of the BAS and the Ľudovít Štúr Institute of Linguistics of the SAS, a section of multilingual lexicography was established at the Department of Modern Lexicology and Lexicography of the ICL, which since 2008 has dealt with the confrontation research of Czech lexis in comparison with selected Slavic languages (Slovak, Bulgarian and Slovenian). One of the dictionary databases which is currently being prepared in this section is a Bulgarian-Czech dictionary database constructed using wiki-based internet collaboration system. In the article, we outline the basic conceptual features of this dictionary database and present the topical treatment questions such as the creation of the list of entries and its relation to the microstructure of the entry (in connection with the software resolution of the project).
|
|
|
Neology in Department of Contemporary Lexicology and Lexicography (OSLL) – Results and Plans
Tichá, Zdeňka
The neological issue in the OSLL is a component of the wider framework of the research plan Creation of a Lexical Database of the Czech Language of the Beginning of the 21st Century (2005–2011, head – K. Oliva). The construction of the lexical collections (archives of lexical dynamics) is dealt with by the excerption section; the theoretical understanding and lexicographic treatment are assured by an independent working group of lexicographers. Thanks to the research plan being resolved, it was possible to ensure the continual complementation of the neological excerption, modify the method of the accumulation of the material in connection with the new tasks of the department and modernise the software equipment (in connection with that to make part of the neological material accessible to the wider public). These results are built on by the theoretical and practical activities of the neological working group, focusing on the treatment of new material (2002–2010).
|
|
|
The lexical database MADLA and possibilities of its use
Chybová, Barbora ; Záhořová, E.
The lexical database of the humanistic and baroque Czech MADLA covers vocabulary from 1500–1780. It contains about 750 000 hand-excerpted documents stemming from dictionaries, herbaria, chronicles and other literary documents from this historical period. Using this database, it is possible to monitor the development of meaning, word formation, paradigm and other grammatical categories, and it serves as a basis for further research on the vocabulary from the 16th–18th centuries. The text describes a representative sample of change in the meaning of the substantive kredenc („cupboard“), the meaning of which has shifted from the original „tasting“ to the contemporary „dresser“. Emphasis is placed on the proof and comparison of different meanings of this word.
|
|
|
Working with Praled and the entry structure in Pralex lexical database
Světlá, Jindra ; Habrová, Martina
In this article, we first present the overall structure of the Pralex lexical database, the work with the data entry form and Praled’s functions. We then focus on the general principles of the elementary processing of database entries, which are subsequently specified according to the individual word classes and entry types. The article ends with a specific example of the processing of an entry in the Pralex lexical database.
|
|
|
The Pralex Lexical Database: a tool and basis for the research and description of the contemporary Czech lexis
Světlá, Jindra
The program part of the lexical database was developed as the Mozilla Firefox application (2005-2006); the processing software is designed as a modern lexicographic workstation. Since 2007, we have gradually complemented the database with the lexicographicallly relevant data (research project Creation of a Lexical Database of the Czech Language of the Beginning of the 21st Century, 2005-2011). We have focused predominantly on detailed treatment of the example part, which demonstrates the breadth of the collocability of the lemmas.
|
|
| |
|
| |
guest ::
