As I planned, finalizing my (quick) studies on ontology learning techniques. Ontologies play a key role in semantic web and technologies by defining concepts and relations between these concepts. Thus, there are significant studies on this subject and some useful techniques discussed in ontology learning:
Ontology learning from texts
Ontology learning from dictionary
Ontology learning from knowledge base
Ontology learning from semi-structured schemata
Ontology learning from relational schemata
Almost all of the techniques above require a good knowledge and infrastructure of NLP (Natural Language Processing) to obtain effective results. I though ontology learning from dictionary would be easy compared to other methods for Turkish language. However, it requires WordNet like dictionaries that what I don’t have. Sabancı University NLP group works on BalkanNet but I don’t think it is ready to use.
When I first see the book “Semantic Web Technologies: Trends and research in ontology-based systems (Hardcover)” hadn’t enough time to go on the previous week. This, morning I couldn’t sleep and so had some free time to search http://ieeexplore.ieee.org/. The query “Ontology-Based” in titles hit 100 papers and most of them are published in 2008 or 2007. I’ve got printed copies of studies from various versions of ontology based systems like “Ontology-Based Knowledge Management”,” Ontology-based Information Integration in Virtual Learning Environment”, ”An Ontology-based Approach to Text Summarization” … etc.
My adviser already has a proposal on multimedia related systems and suggests me to consider it. I may combine those studies with ontology based infrastructure and come up with new subjects. But still an idea …
After, Red Alert 2 I’m getting familiar with Red Alert 3 (RA3) and enjoying the game when I win Japanese forces. My favorite nation in the game is Russians. Yes, I like to hear the sound “Kirov Reporting!”. My main strategy in the game is;
Train soldiers (mixed)
2 Ore Mines
I always follow my opponent’s movements and decide how to strike. It may air, ground or super weapon attack.
I’m not just playing games but reading papers on machine learning techniques which are used in ontology learning for semantic web. Also, I’m preparing a schedule for 2009 conferences and our plan is to have something valuable till April so, we can submit it this year’s events.
I blogged before about semantic web research topics which I’ve been interested in. While I have a little free time I planned to focus on ontology learning. I know it is a big issue and cannot be handled in a tiny time span. However, at least, I can write a review on ontology learning techniques such as machine learning and machine language translation techniques that would be useful to decide to go on this subject.