%0 Conference Paper %1 P:BTC:2011:KonrathGS %A Konrath, Mathias %A Gottron, Thomas %A Scherp, Ansgar %B Semantic Web Challenge, Submission to the Billion Triple Track %D 2011 %K linked-open-data lod myown robust-project schema schema-index schemex stream-processing %T SchemEX -- Web-Scale Indexed Schema Extraction of Linked Open Data %U http://dl.dropbox.com/u/20411070/Publications/2011-BTC-Konrath-GS.pdf %X We present SchemEX, an approach and tool for web-scale, real-time indexing and schema extraction of Linked Open Data (LOD) at linear runtime complexity. As we cannot assume that a complete retrieval of the LOD cloud on a local machine is feasible, we follow a stream-based approach that makes no assumption about how the RDF triples are retrieved from the web by a data crawler. We show the applicability of our approach by applying SchemEX to the Billion Triple Challenge Dataset 2011 and a smaller dataset with 11M triples.

@inproceedings{P:BTC:2011:KonrathGS, abstract = {We present SchemEX, an approach and tool for web-scale, real-time indexing and schema extraction of Linked Open Data (LOD) at linear runtime complexity. As we cannot assume that a complete retrieval of the LOD cloud on a local machine is feasible, we follow a stream-based approach that makes no assumption about how the RDF triples are retrieved from the web by a data crawler. We show the applicability of our approach by applying SchemEX to the Billion Triple Challenge Dataset 2011 and a smaller dataset with 11M triples.}, added-at = {2012-11-23T16:11:31.000+0100}, author = {Konrath, Mathias and Gottron, Thomas and Scherp, Ansgar}, biburl = {https://www.bibsonomy.org/bibtex/2515e36eda0389ec5c1b8a6cae287e6f7/tgottron}, booktitle = {Semantic Web Challenge, Submission to the Billion Triple Track}, file = {:/home/gottron/Dropbox/Public/Publications/2011-ISWC-Konrath-GS.pdf:PDF}, interhash = {6fa61607e0c72e3c18b232fac7be6227}, intrahash = {515e36eda0389ec5c1b8a6cae287e6f7}, keywords = {linked-open-data lod myown robust-project schema schema-index schemex stream-processing}, timestamp = {2012-12-05T11:50:15.000+0100}, title = {SchemEX -- Web-Scale Indexed Schema Extraction of Linked Open Data}, url = {http://dl.dropbox.com/u/20411070/Publications/2011-BTC-Konrath-GS.pdf}, year = 2011 }