Wissenschaftliche Arbeiten

Hier finden Sie von Know-Center MitarbeiterInnen verfasste wissenschaftliche Abschlussarbeiten

2018

Simic Ilija

A personalized and extensible visualization dashboard for interactive data for interactive data exploration i

Master

Master
Analyzing datasets in tabular form quickly becomes difficult with a growing number of rows and columns in a dataset. In order to detect certain patterns in such datasets, going through the table line by line proves to be inefficient, which is why visual methods are often used for this purpose. One such method is the aggregation of a subset of interest of the dataset and its visualization in a chart. Off-the-shelf tools already offer the possibility to open datasets and display the contents for visual exploration, but they are either intimidating to new users, limited to a small number of visualizations and not extensible, or simply too expensive. Visualizer was developed as a web application for client side data visualization which can be used as a stand-alone service or integrated into existing web-pages. It was created with non-expert and expert users in mind, and offers the options to extend the platform with new configurable charts and to fully customize and control it via the URL. For example, an expert user can create a layout consisting of different charts representing aspects of a dataset. This layout opens in other users‘ profiles to visualize their data.
2018

Milot Gashi

Personalized Visualizations based on user's behavior

Master

Master
2018

Purgstaller Roman

Dynamic N-Gram Based Feature Selection for Text Classification

Master

Master
2018

Anthofer Daniel

A Neural Network for Open Information Extraction from German Text i

Master

Master
Systems that extract information from natural language texts usually need to consider language-dependent aspects like vocabulary and grammar. Compared to the development of individual systems for different languages, development of multilingual information extraction (IE) systems has the potential to reduce cost and effort. One path towards IE from different languages is to port an IE system from one language to another. PropsDE is an open IE (OIE) system that has been ported from the English system PropS to the German language. There are only few OIE methods for German available. Our goal is to develop a neural network that mimics the rules of an existing rule-based OIE system. For that, we need to learn about OIE from German text. By performing an analysis and a comparison of the rule-based systems PropS and PropsDE, we can observe a step towards multilinguality, and we learn about German OIE. Then we present a deep-learning based OIE system for German, which mimics the behaviour of PropsDE. The precision in directly imitating PropsDE is 28.1%. Our model produces many extractions that appear promising, but are not fully correct.
Kontakt Karriere

Hiermit erkläre ich ausdrücklich meine Einwilligung zum Einsatz und zur Speicherung von Cookies. Weiter Informationen finden sich unter Datenschutzerklärung

The cookie settings on this website are set to "allow cookies" to give you the best browsing experience possible. If you continue to use this website without changing your cookie settings or you click "Accept" below then you are consenting to this.

Close