2018-02-01 23:30:49 +01:00
|
|
|
\chapter*{Abstract}
|
2018-06-22 07:28:04 +02:00
|
|
|
The thesis presents the process of creating a system for extracting information
|
|
|
|
|
about opening hours
|
|
|
|
|
of holy masses. The methods of collecting data of Polish parishes are being
|
|
|
|
|
described, especially the process of creating spiders. Then two methods are shown
|
|
|
|
|
for the extraction of opening hours of masses: a rule-based method and
|
|
|
|
|
machine learning-based method. More attention is devoted to machine
|
|
|
|
|
learning-based method that uses a text classifier.
|
2018-02-01 23:30:49 +01:00
|
|
|
|
2018-06-22 07:28:04 +02:00
|
|
|
\textbf{Key words:} information extraction, web spidering, text classification
|
