Hi everybody,
My name is Cong Wang, a Ph.D. student from Wright State University with
Pascal Hitzler. I have an idea related to the topic "Pattern Discovery and
Knowledge Base Completion".
My idea is to extract ontology patterns from dbpedia ontology. For example,
input "football", output an ontology describing football pattern. The
motivation is for localized developers to engineer their own ontology. Also
the output small ontology can help to resolve inconsistency (redefine or
remove).
To develop the idea, I believe we need to enrich dbpedia ontology first,
because the Tbox of dbpedia is quite small and naive. So we may use
DL-learning to learn more schemas. Then, secondly, using modularization
technique (maybe bernado's) to extract component regarding the input.
Thirdly, and optionally, cross-check with other existing ontology of the
input (by some alighment method). Finally, show the pattern to user to let
him refine.
Also, to enrich ontology axiom, we may ask user to input some key axiom
regarding the topic. Since in [1], the pattern is actually generic, it has
no semantics regarding a topic. Like, the pattern are just A \sub B, A \sub
\exists R.B, etc. Then we use such axiom type to learn axioms. However, i
believe it can be better if we have some guideline.
If everyone is interested in this topics, or any mentors like to guide me,
please let me know.
[1].Lorenz Bühmann, Jens Lehmann: Pattern Based Knowledge Base Enrichment
And, there might be a more interesting research topic, but quite difficult.
I believe the way people use SPARQL query is somehow related to the
mechanism of reasoning. Like given such query,
Select ?p
Where { ?p :a :football_player . ?p :in ?team. ?team :locate :Brazil.}
We may be able to conclude there should be an axiom Player \sub \exists In.
Team and Team \sub \exists Locates. Country.
Thus, by collecting the SPARQL query log, we may find something
interesting. The thing is I think it's difficult. But I still like to
mention it here.
Best regards.
--
Cong Wang
Ph.D Candidate,
Kno.e.sis Center,
Wright State University.
------------------------------------------------------------------------------
Learn Graph Databases - Download FREE O'Reilly Book
"Graph Databases" is the definitive new guide to graph databases and their
applications. Written by three acclaimed leaders in the field,
this first edition is now available. Download your free book today!
http://p.sf.net/sfu/13534_NeoTech
_______________________________________________
Dbpedia-gsoc mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/dbpedia-gsoc
