|
|
Artificial Poet
Bančák, Michal ; Szőke, Igor (referee) ; Beneš, Karel (advisor)
The paper presents a work on automatic poetry generation using the Long Short-TermMemory recurrent neural network. The aim of this work is to create an application thatimitates the writing of poems. This is a character-level language modeling in the Slovaklanguage. The neural network model used in the work consists of three layers of LSTM,with 400 hidden units. A collection of poems in the Slovak language with a size of 900k characters was also created for this work. . The final model is generating text that has poemelements. Achieved accuracy of generation is 41.85%.
|
|
|
Tool for Visualization of Plagiarism in Several Programming Languages
Bančák, Michal ; Burget, Radek (referee) ; Křivka, Zbyněk (advisor)
The thesis describes the design and implementation of a plagiarism tool for programming languages C, Python and PHP. It describes techniques that are used to cover a plagiarism. The aim of this work is to create a tool for detection and visualization of plagiarisms covered up using these techniques. The tool performs detection by transforming input projects into an abstract syntactic tree, which is obtained by lexical and syntactic analysis. These trees will be compared by a proposed algorithm that uses node and subtree valuation using the {hash} function. The found parts of the code that could potentially lead to plagiarism are visualized in the form of a subtree of an abstract syntactic tree that represents the parts of the code found by the tool. Further, the work describes testing of this tool on identified plagiarism techniques and specifies which of them it can eliminate. In its conclusion, the work describes the possible further development of the tool.
|
|
|
Tool for Visualization of Plagiarism in Several Programming Languages
Bančák, Michal ; Burget, Radek (referee) ; Křivka, Zbyněk (advisor)
The thesis describes the design and implementation of a plagiarism tool for programming languages C, Python and PHP. It describes techniques that are used to cover a plagiarism. The aim of this work is to create a tool for detection and visualization of plagiarisms covered up using these techniques. The tool performs detection by transforming input projects into an abstract syntactic tree, which is obtained by lexical and syntactic analysis. These trees will be compared by a proposed algorithm that uses node and subtree valuation using the {hash} function. The found parts of the code that could potentially lead to plagiarism are visualized in the form of a subtree of an abstract syntactic tree that represents the parts of the code found by the tool. Further, the work describes testing of this tool on identified plagiarism techniques and specifies which of them it can eliminate. In its conclusion, the work describes the possible further development of the tool.
|
|
|
Artificial Poet
Bančák, Michal ; Szőke, Igor (referee) ; Beneš, Karel (advisor)
The paper presents a work on automatic poetry generation using the Long Short-TermMemory recurrent neural network. The aim of this work is to create an application thatimitates the writing of poems. This is a character-level language modeling in the Slovaklanguage. The neural network model used in the work consists of three layers of LSTM,with 400 hidden units. A collection of poems in the Slovak language with a size of 900k characters was also created for this work. . The final model is generating text that has poemelements. Achieved accuracy of generation is 41.85%.
|
guest ::
RSS feed.