|
AI-based Structured Web Data Extraction
Joneš, Jan ; Klímek, Jakub (advisor) ; Peška, Ladislav (referee)
In this thesis, we explore current approaches for automatic web data extraction, define their limitations, and aim to overcome them. We propose a deep learning model to extract structured data from graph and visual representations of web pages. The model is evaluated on an older dataset from 2011 which we augment with missing visual assets, and a new dataset consisting of modern websites. It achieves results competitive with recent work and outperforms our baseline based on a state-of-the-art model by at least 10 percentage points on the F1 score. We ensure the implementation is reproducible and provide a demo of extraction from live pages.
|
|
iOS emulator for Windows
Joneš, Jan ; Kratochvíl, Miroslav (advisor) ; Kofroň, Jan (referee)
The goal of this thesis is to create a program for Windows that takes a compiled iOS application and emulates it. However, only the application's machine code is emulated, whereas system functionality originally provided by iOS is translated to an equivalent functionality available on Windows. Hence, the emulated application employs a user interface and behavior that feel native on the target platform. At compile time, custom machine code is generated that supports the translation at runtime. The thesis also describes iOS's internals that the emulator needs to imitate and discusses different approaches to cross-platform development. 1
|
| |
| |
| |