|
|
Text document plagiarism detector
Kořínek, Lukáš ; Horák, Karel (referee) ; Petyovský, Petr (advisor)
This diploma thesis is concerned with research on available methods of plagiarism detection and then with design and implementation of such detector. Primary aim is to detect plagiarism within academic works or theses issued at BUT. The detector uses sophisticated preprocessing algorithms to store documents in its own corpus (document database). Implemented comparison algorithms are designed for parallel execution on graphical processing units and they compare a single subject document against all other documents within the corpus in the shortest time possible, enabling near real-time detection while maintaining acceptable quality of output.
|
|
|
Transformer Neural Networks for Handwritten Text Recognition
Vešelíny, Peter ; Beneš, Karel (referee) ; Kohút, Jan (advisor)
This Master's thesis aims to design a system using the transformer neural network and perform experiments with this proposed model in the task of handwriting text recognition. In this thesis, a multilingual dataset with predominate Czech texts is used. The experiments examine the influence of basic hyperparameters, such as network size, convolutional encoder type, and the use of different text tokenizers. In this work, I also use text corpora of the Czech language which is used to train the network decoder. Furthermore, I experiment with the usage of additional textual information during the decoding process. This information comes from the previous line of the transcribed image. The transformer achieves a character recognition error rate of 3.41 % on the test data set which is 0.16 % worse performance than the recurrent neural network achieves. To compare this model with other transformer-based models from available articles, the network was trained on the IAM dataset, where it achieved an error of 2.48 % and therefore outperformed other models in handwriting text recognition task.
|
|
|
Transformer Neural Networks for Handwritten Text Recognition
Vešelíny, Peter ; Beneš, Karel (referee) ; Kohút, Jan (advisor)
This Master's thesis aims to design a system using the transformer neural network and perform experiments with this proposed model in the task of handwriting text recognition. In this thesis, a multilingual dataset with predominate Czech texts is used. The experiments examine the influence of basic hyperparameters, such as network size, convolutional encoder type, and the use of different text tokenizers. In this work, I also use text corpora of the Czech language which is used to train the network decoder. Furthermore, I experiment with the usage of additional textual information during the decoding process. This information comes from the previous line of the transcribed image. The transformer achieves a character recognition error rate of 3.41 % on the test data set which is 0.16 % worse performance than the recurrent neural network achieves. To compare this model with other transformer-based models from available articles, the network was trained on the IAM dataset, where it achieved an error of 2.48 % and therefore outperformed other models in handwriting text recognition task.
|
|
|
Text document plagiarism detector
Kořínek, Lukáš ; Horák, Karel (referee) ; Petyovský, Petr (advisor)
This diploma thesis is concerned with research on available methods of plagiarism detection and then with design and implementation of such detector. Primary aim is to detect plagiarism within academic works or theses issued at BUT. The detector uses sophisticated preprocessing algorithms to store documents in its own corpus (document database). Implemented comparison algorithms are designed for parallel execution on graphical processing units and they compare a single subject document against all other documents within the corpus in the shortest time possible, enabling near real-time detection while maintaining acceptable quality of output.
|
|
|
French-Czech online dictionaries: current state and comparison of available tools
RÁDROVÁ, Kristýna
The bachelor thesis´ entitled French-Czech online dictionaries: current state and comparison of available tools aim is to chart current online dictionaries, their availability and to compare their merits. In first, theoretical part I dedicate to different types of dictionaries, their characteristic and to particular dictionaries, whose creation was an important milestone for history of lexicography and linguistics. The practical part of the bachelor thesis describes current online dictionaries, their micro and macrostructure with regard to users to whom the dictionary is intended.
|
|
|
Synchrony Dynamics of Prepositions Introducing Local Adverbials after Selected Verbs Expressing Movement
PETLACHOVÁ, Hana
This bachelor thesis deals with prepositional syntagmas in local adverbial in Italian language. In the theoretical part there are firstly introduced constituent types of local adverbials, their function and the most common prepositional context of incidence; special attention is primarily paid to adverbial of movement at some place. Afterwards, the theory of synchrony dynamics is introduced, with which the variation of prepositions in identical context can be explained. In the practical part follows an exposition about concrete cases of local adverbials after nine selected movement verbs according to data collected from the text corpus "La Repubblica". This research is focused mostly on the cases when the identical incidence admits more synonymous prepositions.
|
guest ::
