Formerly, I was research assistant at Digital Enterprise Research Institute (DERI), National University of Ireland, Galway, working in the Unit for Natural Language Processing (UNLP) under Paul Buitelaar.
In my Master’s Thesis I implemented a solution for the automatic extraction of keyphrases from single, textual documents in a variety of languages.
A further description of the work conducted in this context is available on the project page, the resources can be downloaded for a number of different deployment scenarios (GATE plugin, jar, dbus-service) here.
In the NEPOMUK project, which aimed at establishing standards for the Social Semantic Desktop, I contributed to the Task-Force Text Analytics.
In Summer of 2006 I finished my studies of Computational Linguistics at Saarland University, Saarbrücken, with a Bachelor of Science. My thesis, RelExt: A System for Relation Extraction for Ontology Learning from Text (a 2-up version is also available), was written under supervision of Paul Buitelaar in the context of the SmartWeb project. It employed statistical methods over linguistically annotated data in order to identify and to extract relations between highly domain relevant terms.
In August 2008 I submitted my Master’s thesis Keyphrase Extraction from Single Documents in the Open Domain Exploiting Linguistic and Statistical Methods (also available printed 2-up), supervised by Siegfried Handschuh. The outcome of the thesis is a software component capable of automatically extracting keyphrases from textual documents.
More information, including download links, can be found on the dedicated web page.
My research interests comprise of a variety of topics in Natural Language Processing (NLP) and Artificial Intelligence. More specifically, I am interested in
- Robust and scalable (ontology-based) Information Extraction from Text
- Ontology Learning / Population
- Statistical Language Models
Outside of the office, I enjoy playing all kinds of field/team-sports, cycling, swimming, hiking, cooking and listening to music.