|
|
Plot Analysis from Book Summaries and User Reviews
Rúček, Peter ; Dočekal, Martin (referee) ; Smrž, Pavel (advisor)
The aim of this work is to create a system for analysis and classification of plot keywords from summarized storylines and user reviews in English. The chosen problem is solved using a transformer-based machine learning technique. The created solution also implements data downloading and a dataset of user reviews and information about books was created, exceeding 23 million reviews and 900 thousand information about books. The system can predict what plot keywords the data contains.
|
|
|
Multilingual Open-Domain Question Answering
Slávka, Michal ; Dočekal, Martin (referee) ; Fajčík, Martin (advisor)
Táto práca sa zaoberá automatickým viacjazyčným zodpovedaním na otázky v otvorenej doméne. V tejto práci sú navrhnuté prístupy k tejto málo prebádanej doméne. Konkrétne skúma, či: (i) použitie prekladu z angličtiny je dostačujúce, (ii) multilinguálne systémy vedia využiť preklad otázky do iných jazykov (iii) alebo je výhodnejšie nepoužívať žiaden preklad. Porovnávam použitie anglického systému založeného na modeli T5, ktorý využíva strojový preklad s natívne viacjazyčnými systémami založenými na viacjazyčnom modeli MT5. Anglický systém so strojovým prekladom mierne prekonáva svoje jednojazyčné náprotivky vo viacerých úlohách. Napriek tomu, že tento model bol natrénovaný na väčšom množstve dát zlepšenie nie je dostatočne signifikantné. To ukazuje, že použitie natívne viacjazyčných systémov je sľubným prístupom pre budúci výskum. Tiež prezentujem metódu získavania dokumentov v rôznych jazykoch pomocou algoritmu BM25 a porovnávam ju s anglickým retrievalom. Používanie viacjazyčných dôkazov sa javí ako prospešné a zlepšuje výkonnosť systému systémov.
|
|
| |
|
|
Design of the electric locomotive drive
Dočekal, Martin ; Klíma, Bohumil (referee) ; Patočka, Miroslav (advisor)
The focus of the work is the calculation and design of battery-powered drive of locomotive, operating in the sub-siding mode, ie when the locomotive is moving on the track section without the overhead line. The proposed battery groups to ensure the drive train will be installed directly into the locomotive engine room. In the theoretical part of the work there has been done the analysis of the electrical locomotives and electrical unit, which nowadays are used in the Czech Republic in driving of voltage controller with the integrated circuit. Then, in the chapter there is a brief description modern locomotives frequency convertor’s and rectifier’s function. The practical part of the work contains the necessary force and energy calculation for train moving on the determined rails. On the base of the received data, the design of battery groups has been done. These battery groups will work as an independent traction which insures the moving of the train on the determined rails. In the work the design, which consists of STEP-UP and STEP-DOWN convertors, has also been done. The power model and model management were created in Matlab Simulink programme. Data and graphs exported from the Matlab Simulink programm are determined for verifying convertor’s function, which can be found in a separate chapter. In addition to the proposal of the battery drive is at work also has been calculated loss of traction rectifier during normal operation of the locomotive, ie outside siding mode. For this calculation, in the conclusion is listed the theory of calculation of the losses incipient in the transistor and freewheeling diode of rectifier. According to the theory own calculation is performed. Subsequently the liquid cooler calculation of the rectifier is calculated.
|
|
|
Plot Analysis from Book Summaries and User Reviews
Rúček, Peter ; Dočekal, Martin (referee) ; Smrž, Pavel (advisor)
The aim of this work is to create a system for analysis and classification of plot keywords from summarized storylines and user reviews in English. The chosen problem is solved using a transformer-based machine learning technique. The created solution also implements data downloading and a dataset of user reviews and information about books was created, exceeding 23 million reviews and 900 thousand information about books. The system can predict what plot keywords the data contains.
|
|
|
Sentiment Analysis of Czech and Slovak Social Networks and Web Discussions
Sojka, Matěj ; Dočekal, Martin (referee) ; Smrž, Pavel (advisor)
Thanks to digitalization, the spread of opinions in the population has accelerated sharply in the recent years, however the need to understand them has not changed. The goal of this thesis was to create a system for automatic data collection from social media and web discussions and sentiment analysis in Czech and Slovak language. The system has a web interface for visualizing results and configuring data analysis. The system is capable of offering topics to the user that it considers to occur in the selected data and group posts based on user-defined opinions.
|
|
| |
|
|
Multilingual Open-Domain Question Answering
Slávka, Michal ; Dočekal, Martin (referee) ; Fajčík, Martin (advisor)
Táto práca sa zaoberá automatickým viacjazyčným zodpovedaním na otázky v otvorenej doméne. V tejto práci sú navrhnuté prístupy k tejto málo prebádanej doméne. Konkrétne skúma, či: (i) použitie prekladu z angličtiny je dostačujúce, (ii) multilinguálne systémy vedia využiť preklad otázky do iných jazykov (iii) alebo je výhodnejšie nepoužívať žiaden preklad. Porovnávam použitie anglického systému založeného na modeli T5, ktorý využíva strojový preklad s natívne viacjazyčnými systémami založenými na viacjazyčnom modeli MT5. Anglický systém so strojovým prekladom mierne prekonáva svoje jednojazyčné náprotivky vo viacerých úlohách. Napriek tomu, že tento model bol natrénovaný na väčšom množstve dát zlepšenie nie je dostatočne signifikantné. To ukazuje, že použitie natívne viacjazyčných systémov je sľubným prístupom pre budúci výskum. Tiež prezentujem metódu získavania dokumentov v rôznych jazykoch pomocou algoritmu BM25 a porovnávam ju s anglickým retrievalom. Používanie viacjazyčných dôkazov sa javí ako prospešné a zlepšuje výkonnosť systému systémov.
|
|
|
Automatic Humor Evaluation
Katrňák, Josef ; Ondřej, Karel (referee) ; Dočekal, Martin (advisor)
The aim of this thesis is to create a system for automatic humor evaluation. The system allow to predict humor and category for english input. The main essence is to create a classifier and train the model with the created datasets to get the best possible results. The classifier architecture is based on neural networks. The system also includes a web user interface for communication with the user. The result is a web application linked to a classifier that allows user input to be evaluated and user feedback to be provided.
|
|
|
HIL simulation of manipulators or machines
Dočekal, Martin ; Marada, Tomáš (referee) ; Zuth, Daniel (advisor)
The diploma thesis deals with HIL simulation (hardware in the loop). The thesis contains a manipulator created in the virtual software V-REP. The connection of real inputs and virtual outputs of the machine is realized by the microcontroller Arduino UNO. The first task deals with the control of the manipulator using the joystick PS2. The second task is a separate control of the robot using an microcontroller Arduino UNO. The resulting connection can be modified in the furher and the interface modified. The work will be used for educational purposes.
|
guest ::
RSS feed.