%0 Journal Article %1 Oren:2008:SDL %A Oren, Eyal %A Delbru, Renaud %A Catasta, Michele %A Cyganiak, Richard %A Stenzhorn, Holger %A Tummarello, Giovanni %D 2008 %J International Journal of Metadata, Semantics and Ontologies %K research.ir.metadata research.sw %N 1 %T Sindice.com: A Document-oriented Lookup Index for Open Linked Data %U http://www.sindice.com/pdf/sindice-ijmso2008.pdf %V 3 %X Developers of Semantic Web applications face a challenge with respect to the decentralised publication model: how and where to find statements about encountered resources. The ``linked data'' approach mandates that resource URIs should be de-referenced to return resource metadata. But for data discovery linkage itself is not enough, and crawling and indexing of data is necessary. Existing Semantic Web search engines are focused on database-like functionality, compromising on index size, query performance and live updates. We present Sindice, a lookup index over resources crawled on the Semantic Web. Our index allows applications to automatically locate documents containing information about a given resource. In addition, we allow resource retrieval through uniquely identifying inverse-functional properties, offer a full-text search and index SPARQL endpoints. Finally we introduce an extension to the sitemap protocol which allows us to efficiently index large Semantic Web datasets with minimal impact on the data providers.

@article{Oren:2008:SDL, abstract = { Developers of Semantic Web applications face a challenge with respect to the decentralised publication model: how and where to find statements about encountered resources. The ``linked data'' approach mandates that resource URIs should be de-referenced to return resource metadata. But for data discovery linkage itself is not enough, and crawling and indexing of data is necessary. Existing Semantic Web search engines are focused on database-like functionality, compromising on index size, query performance and live updates. We present Sindice, a lookup index over resources crawled on the Semantic Web. Our index allows applications to automatically locate documents containing information about a given resource. In addition, we allow resource retrieval through uniquely identifying inverse-functional properties, offer a full-text search and index SPARQL endpoints. Finally we introduce an extension to the sitemap protocol which allows us to efficiently index large Semantic Web datasets with minimal impact on the data providers.}, added-at = {2010-10-07T11:08:50.000+0200}, author = {Oren, Eyal and Delbru, Renaud and Catasta, Michele and Cyganiak, Richard and Stenzhorn, Holger and Tummarello, Giovanni}, biburl = {https://www.bibsonomy.org/bibtex/2cc14ea46d65557560bdaf92ef460dc18/msn}, interhash = {ecefb84104412695c250c45089102d94}, intrahash = {cc14ea46d65557560bdaf92ef460dc18}, journal = {International Journal of Metadata, Semantics and Ontologies}, keywords = {research.ir.metadata research.sw}, number = 1, timestamp = {2010-10-07T11:08:50.000+0200}, title = {Sindice.com: {A} Document-oriented Lookup Index for Open Linked Data}, url = {http://www.sindice.com/pdf/sindice-ijmso2008.pdf}, volume = 3, year = 2008 }