|
| |
|
|
Web page analyzer for scraping
Christozov, Valentín ; Macková, Kateřina (advisor) ; Petříček, Tomáš (referee)
Web scraping is a technique used for a variety of applications to extract data from the web. To create a scraper, a developer needs to perform an analysis of the scraped website using tools like web devtools or Postman. This analysis is necessary to locate the data and to determine an effective way to scrape the website. The structure of websites varies greatly and the process of analysis is tedious and time-consuming. The goal of this project is to create a tool, that a non-developer could use to get an insight into where the data is stored on the website and how it can be scraped. An analysis is performed on the input website. Results of the analysis are presented in a minimalist user interface. Output of the analysis can be used as a guide for no code web scraping tools configuration as well as a baseline for a web scraper development.
|
|
|
Question Answering in Czech via Machine Translation and Cross-lingual Transfer
Macková, Kateřina ; Straka, Milan (advisor) ; Mareček, David (referee)
Reading comprehension and question answering are computer science disciplines in the field of natural language processing and information retrieval. Reading comprehension is the ability of the model to read text, process it and understand its meaning. One of its applications is in question answering tasks, which is concerned with building a system that can automatically find an answer in the text to a certain question relied on the content of the text. It is a well-studied task, with huge training datasets in English. However, there are no Czech datasets and models for this task. This work focuses on building reading comprehension and question answering systems for Czech, without requiring any manually annotated Czech training data. Our main focus is to create Czech training and development datasets, create the models for the Czech question answering system using Czech data, and create the models for the Czech question answering system using English data and cross-lingual transfer and compare the results and select the best model. First of all, we translated freely available English question answering datasets SQuAD 1.1 and SQuAD 2.0 to Czech to create training and development datasets. We then trained and evaluated several BERT and XLM-RoBERTa baseline models used for the question answering task in...
|
|
|
Web Browser Recorder
Sauerová, Markéta ; Macková, Kateřina (advisor) ; Šmelko, Adam (referee)
The goal of this thesis is to develop an intuitive RPA tool in the form of a client- server web application. This tool can be used for recording web automation workflows and their subsequent execution, modification and management. Even though there are many similar tools available, it is difficult to find one that can support a variety of web automation use cases and that is simple enough to be used by untrained users. This thesis aims to build such a solution, a tool producing recordings in the easy to understand Web Automation Workflow format and leveraging from the Web Browser Robot library Interpreter. The result is a powerful GUI recorder providing numerous useful features. 1
|
|
|
Generator of nanotubes
Macková, Kateřina ; Mareš, Martin (advisor) ; Král, Karel (referee)
The clay mineral called halloysite with crystalline structure is widely used in the world of physics due to its effective properties. The main goal of this thesis is to create a program that creates various tubular nanostructures of this material according to input crystal cell and other parameters. After the creation, whole halloysite structure can be used for other physical research.
|
|
|
Novel treatment modalities for pelvic floor dysfunction
Macková, Kateřina ; Krofta, Ladislav (advisor) ; Džupová, Olga (referee) ; Čelko, Alexander (referee)
We aimed to test selected novel treatment modalities for pelvic floor dysfunctions and genitourinary syndrome of menopause. Both conditions are common in female, they negatively affect their quality of life, and current treatment options are not optimal. We started our research with an extensive literature search. First, we summarized the information on animal models for, and the utility they may have in the investigation of the pathophysiology of POP and novel therapies. We systematically searched 7426 articles from which 51 fulfilled the inclusion criteria. From all screened animals, only the non-human primate develops POP spontaneously, however their use is controversial. We concluded that many studies have methodological shortcomings and lack standardization in reporting outcomes. Also, several other animals can be used as a model of surgery for POP, each of them with different purposes. For our later research we chose the rat model to simulate POP repair with synthetic mesh. We also systematically reviewed the literature on the objective effects of non-ablative Er:YAG LASER on the skin and vaginal wall. We identified 7187 articles of which we included 15 in our review, including four that tested Er:YAG LASER on vaginal tissue. Er:YAG LASER energy induces measurable changes in the deeper skin...
|
|
|
Software solution for digital archives
Nápravník, David ; Macková, Kateřina (advisor) ; Hoffmannová, Petra (referee)
This bachelor's thesis is on the modernisation of library systems. It focuses on tech- nologies such as single-page application, which streamlines network communication and reduces server usage. The goal was to describe and use modern technologies into a working application, that provides the user with a modern, streamlined and fast input environment metadata with the addition of the system for managing web content. A clear API has been created on the server to provide all the data not only for the main application, but for the related modules or other projects as well. The work also describes the technologies that make these streamlinings possible. 1
|
|
|
Automatic Bird Species Audio Detection
Zasadil, Tomáš ; Macková, Kateřina (advisor) ; Pilát, Martin (referee)
Birds have been long monitored manually, which is very labor intensive. This work tries to explore and compare different types of neural networks (MLP,CNN,RNN,CRNN) to automatically find and classify acoustic activity of birds within audio recordings of wilderness. It could save a lot of time and effort, since people wouldn't have to go through the recordings and manually identify the birds. By saving lots of time, bird monitoring could be done at greater scale, helping with conservation and scientific research. The objective is to build a user-friendly application, where the user can train a new bird- identifying model and use it without needing any computer skills. 1
|
|
| |
|
|
Crosslingual Transfer in Question Answering
Macková, Kateřina ; Straka, Milan (advisor) ; Rosa, Rudolf (referee)
Question answering is a computer science discipline in the field of natural language processing and information retrieval. The goal is to build a system that can automatically find an answer to a certain question in the text. Nowadays, there exist a lot of models trained on huge training data sets in English. This work focuses on building similar models in Czech without having any Czech training datasets. In this work, we have used SQuAD 1.1 and translated it to Czech to create training and development datasets. Then, we have trained and tested BiDirectional Attention Flow and BERT models. The best obtained result on the Czech dataset is from BERT model trained on Czech with exact match 60.48% and F1 score 73.46%. In addition, we have also trained BERT model on English dataset and we have evaluated it on Czech testing dataset without translation. We have reached exact match 63.71% and F1 score 74.78%, which is extremely good in spite of the fact that the model has not seen any Czech question answering data before. Such a model is very flexible and provide a question answering system in any language for which we have enough monolingual raw texts.
|
guest ::
RSS feed.