Biomedical text mining and NLP

Main research interest of this website and its author is text mining and natural language processing. However, since text mining and natural language processing is quite large topic, we focus on information extraction from tabular and semi-structured forms from documents. We are trying to extract information from biomedical and clinical documents on the first place. These documents could make a huge difference in healthcare. It can help discovery of new drugs and medical procedures.


We are examining different approaches how to extract information and knowledge from biomedical documents using rule-based and machine learning approaches with help of UMLS resources.

Serbian and Slavic languages natural language processing

We are also interested in general information extraction and information retrieval. Most of our research is done in text mining of English language, however, our research interest is also text mining of more inflectional languages such as Serbian, Croatian, Slovak, Czech etc. One of our interest is also computer security. However, research in computer security is not active ongoing research except one project that is currently done under OWASP and Google Summer of Code.

Computer and device security

One of the research interest is also computer and device security and its defense. Especially I am interested in malware, data leak prevention, privacy protection. Particulary this topics are emerging on mobile devices and so far my research focus was on them. I am also interested in history of computer security related things.