Jürgen Umbrich's Homepage

@inproceedings{kublrobe2016aa,
	 author = {Kubler, Sylvain and Robert, Jérémy and Le Traon, Yves and Umbrich, Jürgen and Neumaier, Sebastian},
	 booktitle = {Proceedings of the 17th International Digital Government Research Conference on Digital Government Research},
	 date-added = {2016-06-16 07:30:11 +0000},
	 date-modified = {2016-06-16 07:30:25 +0000},
	 organization = {ACM},
	 pages = {397--407},
	 title = {Open Data Portal Quality Comparison using AHP},
	 year = {2016}
}

@incollection{iselumbr2010aa,
	 author = {Isele, Robert and Umbrich, Jürgen and Bizer, Christian and Harth, Andreas},
	 bdsk-url-1 = {http://iswc2010.semantic%7BW%7Deb.org/pdf/495.pdf},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 booktitle = {Posters{&}Demos at International Semantic Web Conference (ISWC)},
	 date-modified = {2016-06-16 06:17:09 +0000},
	 ee = {http://ceur-ws.org/Vol-658/paper495.pdf},
	 keyword = {other},
	 link = {http://iswc2010.semantic{W}eb.org/pdf/495.pdf},
	 rossref = {DBLP:conf/sem{W}eb/2010pd},
	 title = {{LD}spider: An Open-source Crawling Framework for the {W}eb of {L}inked {D}ata},
	 year = {2010}
}

@article{hogaumbr2012aa,
	 abstract = {There has been a recent, tangible growth in RDF published on the {W}eb
in accordance with the {L}inked {D}ata principles and best practices, the result of which has been dubbed the ``{W}eb of Data''. {L}inked {D}ata
guidelines are designed to facilitate ad hoc re-use and integration
of conformant structured data--across the {W}eb--by consumer applications;
however, thus far, systems have yet to emerge that convincingly demonstrate
the potential applications for consuming currently available Linked
Data. Herein, we compile a list of fourteen concrete guidelines as
given in the ``How to Publish {L}inked {D}ata on the {W}eb'' tutorial. Thereafter, we evaluate conformance of current RDF data providers with respect
to these guidelines. Our evaluation is based on quantitative empirical
analyses of a crawl of ~4 million RDF/XML documents constituting
over 1 billion quadruples, where we also look at the stability of
hosted documents for a corpus consisting of nine monthly snapshots
from a sample of 151 thousand documents. Backed by our empirical
survey, we provide insights into the current level of conformance
with respect to various {L}inked {D}ata guidelines, enumerating lists
of the most (non-)conformant data providers. We show that certain
guidelines are broadly adhered to (esp. use HTTP URIs, keep URIs
stable), whilst others are commonly overlooked (esp. provide licencing
and human-readable meta-data). We also compare PageRank scores for
the data-providers and their conformance to {L}inked {D}ata guidelines, showing that both factors negatively correlate for guidelines restricting
the use of RDF features, while positively correlating for guidelines
encouraging external linkage and vocabulary re-use. Finally, we present
a summary of conformance for the different guidelines, and present
the top-ranked data providers in terms of a combined PageRank and
{L}inked {D}ata conformance score.},
	 addendum = {(impact factor 3.14)},
	 author = {Hogan, Aidan and Umbrich, Jürgen and Harth, Andreas and Cyganiak, Richard and Polleres, Axel and Decker, Stefan},
	 bdsk-url-1 = {http://umbrich.org/pubs/hogan_jws2012-2.pdf},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 date-modified = {2016-06-16 06:14:40 +0000},
	 ee = {http://dx.doi.org/10.1016/j.{W}ebsem.2012.02.001},
	 file = {:pubs\\hogan_jws2012-2.pdf:PDF},
	 journal = {J. {W}eb Sem.},
	 link = {http://umbrich.org/pubs/hogan_jws2012-2.pdf},
	 pages = {14-44},
	 title = {An empirical survey of {L}inked {D}ata conformance},
	 volume = {14},
	 year = {2012}
}

@inproceedings{umbrhart2008aa,
	 author = {Umbrich, Jürgen and Harth, Andreas and Hogan, Aidan and Decker, Stefan},
	 bdsk-url-1 = {http://icwe2008.%7BW%7Debengineering.org/Program/Proceedings/ISBN978-0-7695-3261-5/3261a196.pdf},
	 bdsk-url-2 = {http://dx.doi.org/10.1109/ICWE.2008.42},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 booktitle = {International Conference {W}eb Engineering (ICWE)},
	 date-modified = {2016-06-16 06:16:26 +0000},
	 doi = {http://dx.doi.org/10.1109/ICWE.2008.42},
	 ee = {http://dx.doi.org/10.1109/ICWE.2008.42},
	 link = {http://icwe2008.{W}ebengineering.org/Program/Proceedings/ISBN978-0-7695-3261-5/3261a196.pdf},
	 pages = {196-202},
	 rossref = {DBLP:conf/icwe/2008},
	 title = {Four Heuristics to Guide Structured Content Crawling},
	 year = {2008}
}

@inproceedings{hogahart2007aa,
	 author = {Hogan, Aidan and Harth, Andreas and Umbrich, Jürgen and Decker, Stefan},
	 bdsk-url-1 = {http://wwwconference.org/www2007/posters/poster1027.pdf},
	 bdsk-url-2 = {http://doi.acm.org/10.1145/1242572.1242819},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 booktitle = {International World Wide Web Conferences (WWW)},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 doi = {http://doi.acm.org/10.1145/1242572.1242819},
	 ee = {http://doi.acm.org/10.1145/1242572.1242819},
	 keyword = {other},
	 link = {http://wwwconference.org/www2007/posters/poster1027.pdf},
	 pages = {1301-1302},
	 rossref = {DBLP:conf/www/2007},
	 title = {Towards a scalable search and query engine for the {W}eb},
	 year = {2007}
}

@mastersthesis{umbr2008aa,
	 addendum = {(graded: 1.3 according to the German grade system)},
	 author = {Umbrich, Jürgen},
	 date-modified = {2016-06-16 06:15:38 +0000},
	 owner = {umbrichj},
	 school = {School of Economics and Business Engineering, University of Karlsruhe, Germany},
	 timestamp = {2013.08.29},
	 title = {Discovering and crawling structured content},
	 year = {2008}
}

@inproceedings{hallumbr2010aa,
	 author = {Haller, Armin and Umbrich, Jürgen and Hausenblas, Michael},
	 bdsk-url-1 = {http://www.armin-haller.com/publications/raul-wise2010.pdf},
	 bdsk-url-2 = {http://dx.doi.org/10.1007/978-3-642-17616-6_36},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 booktitle = {Web Information Systems Engineering (WISE)},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 doi = {http://dx.doi.org/10.1007/978-3-642-17616-6_36},
	 ee = {http://dx.doi.org/10.1007/978-3-642-17616-6_36},
	 link = {http://www.armin-haller.com/publications/raul-wise2010.pdf},
	 pages = {400-410},
	 publisher = {Springer},
	 rossref = {DBLP:conf/wise/2010},
	 title = {Ra{UL}: {RDF}a User Interface Language - A Data Processing Model for {W}eb Applications},
	 year = {2010}
}

@inproceedings{rakhkarn2013aa,
	 author = {Rakhmawati, Nur Aini and Karnstedt, Marcel and Hausenblas, Michael and Hasnain, Ali and Umbrich, Jürgen},
	 booktitle = {Knowledge Engineering and Semantic {W}eb Conference (KESW)},
	 date-modified = {2016-06-16 06:14:09 +0000},
	 owner = {UmbrichJ},
	 timestamp = {2013.07.09},
	 title = {A Comparison of Federation over {SPARQL} Endpoints Frameworks},
	 year = {2013}
}

@inproceedings{toupumbr2009aa,
	 author = {Toupikov, Nickolai and Umbrich, Jürgen and Delbru, Renaud and Hausenblas, Michael and Tummarello, Giovanni},
	 bdsk-url-1 = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.184.3683&rep=rep1&type=pdf},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 booktitle = {{L}inked {D}ata on the {W}eb (LDOW) at WWW},
	 date-modified = {2016-06-16 06:15:32 +0000},
	 ee = {http://ceur-ws.org/Vol-538/ldow2009_paper21.pdf},
	 keyword = {workshop},
	 link = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.184.3683&rep=rep1&type=pdf},
	 rossref = {DBLP:conf/www/2009ldow},
	 title = {{DING!} Dataset Ranking using Formal Descriptions},
	 year = {2009}
}

@inproceedings{umbrbloh2008aa,
	 author = {Umbrich, Jürgen and Blohm, Sebastian},
	 bdsk-url-1 = {http://ceur-ws.org/Vol-334/paper-08.pdf},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 booktitle = {SemSearch at ESWC},
	 date-modified = {2016-06-16 06:16:13 +0000},
	 ee = {http://ceur-ws.org/Vol-334/paper-08.pdf},
	 keyword = {workshop},
	 link = {http://ceur-ws.org/Vol-334/paper-08.pdf},
	 pages = {89-101},
	 publisher = {Springer},
	 rossref = {DBLP:conf/esws/2008semsearch},
	 title = {Exploring the Knowledge in Semi Structured Data Sets with Rich Queries},
	 year = {2008}
}

@incollection{umbrguti2013aa,
	 abstract = {Inspired by the CAP theorem, we identify three desirable properties
when querying the {W}eb of Data: Alignment (results up-to-date with
sources), Coverage (results covering available remote sources), and
Effciency (bounded resources). In this short paper, we show that no
system querying the {W}eb can meet all three {ACE} properties, but instead
must make practical trade-offs that we outline.},
	 author = {Umbrich, Jürgen and Gutierrez, Claudio and Hogan, Aidan and Karnstedt, Marcel and Parreira, Josiane Xavier},
	 bdsk-url-1 = {http://sw.deri.org/~aidanh/docs/ace-theorem.pdf},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 booktitle = {Posters{&}Demos at International World Wide Web Conferences (WWW)},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 ee = {http://dl.acm.org/citation.cfm?id=2487852},
	 keyword = {other},
	 link = {http://sw.deri.org/~aidanh/docs/ace-theorem.pdf},
	 pages = {133-134},
	 rossref = {DBLP:conf/www/2013c},
	 title = {The {ACE} theorem for querying the {W}eb of {D}ata},
	 year = {2013}
}

@inproceedings{umbrguti2013ab,
	 abstract = {The {W}eb of Data refers to the universal database constituted by interlinked
data sources on the {W}eb. This global system is creating a new way
of publishing and consuming data on the {W}eb. A number of assumption
that were valid in bounded, controlled, closed worlds of data are
now being challenged. In this paper, following the seminal ideas
presented in 1994 by Peter Deutsch and later completed by James Gosling, known as ``The Eight Fallacies of Distributed Computing'' [1], we present
a set of fallacies for the area of the {W}eb of Data.},
	 author = {Umbrich, Jürgen and Gutierrez, Claudio and Hogan, Aidan and Karnstedt, Marcel and Parreira, Josiane Xavier},
	 bdsk-url-1 = {http://users.dcc.uchile.cl/~cgutierr/papers/des%7BW%7Deb2013.pdf},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 booktitle = {Data Engineering meets the Semantic {W}eb (DES{W}eb) at ICDE},
	 date-modified = {2016-06-16 06:15:54 +0000},
	 ee = {http://doi.ieeecomputersociety.org/10.1109/ICDEW.2013.6547418},
	 keyword = {workshop},
	 link = {http://users.dcc.uchile.cl/~cgutierr/papers/des{W}eb2013.pdf},
	 pages = {21-22},
	 publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
	 rossref = {DBLP:conf/icde/2013w},
	 title = {Eight Fallacies when querying the {W}eb of {D}ata},
	 year = {2013}
}

@inproceedings{hagehose2014aa,
	 author = {Hagedorn, Stefan and Hose, Katja and Sattler, Kai{-}Uwe and Umbrich, Jürgen},
	 bdsk-url-1 = {http://ceur-ws.org/Vol-1264/cold2014_HagedornHSU.pdf},
	 bibsource = {dblp computer science bibliography, http://dblp.org},
	 biburl = {http://dblp.uni-trier.de/rec/bib/conf/semweb/HagedornHSU14},
	 booktitle = {Proceedings of the 5th International Workshop on Consuming Linked Data {(COLD} 2014) co-located with the 13th International Semantic Web Conference {(ISWC} 2014), Riva del Garda, Italy, October 20, 2014.},
	 crossref = {harthoga2014aa},
	 date-added = {2015-01-20 14:10:57 +0000},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 keyword = {workshop},
	 link = {http://ceur-ws.org/Vol-1264/cold2014_HagedornHSU.pdf},
	 timestamp = {Sat, 03 Jan 2015 14:06:48 +0100},
	 title = {Resource Planning for {SPARQL} Query Execution on Data Sharing Platforms},
	 year = {2014}
}

@inproceedings{tianumbr2011aa,
	 abstract = {Traditionally, {L}inked {D}ata query engines execute SPARQL

queries over a materialised repository which on the one hand, guarantees

fast query answering but on the other hand requires time and resource

consuming preprocessing steps. In addition, the materialised reposito-

ries have to deal with the ongoing challenge of maintaining the index

which is -- given the size of the {W}eb -- practically unfeasible. Thus, the

results for a given SPARQL query are potentially out-dated. Recent
ap-

proaches address the result freshness problem by answering a given
query

directly over dereferenced query relevant {W}eb documents. Our work
in-

vestigate the problem of an efficient selection of query relevant
sources

under this context. As a part of query optimization, source selection

tries to estimate the minimum number of sources accessed in order
to

answer a query. We propose to summarize and index sources based on

frequently appearing query graph patterns mined from query logs. We

verify the applicability of our approach and empirically show that
our

approach significantly reduces the number of relevant sources estimated

while keeping the overhead low.},
	 author = {Tian, Yuan and Umbrich, Jürgen and Yu, Yong},
	 bdsk-url-1 = {http://link.springer.com/content/pdf/10.1007%2F978-3-642-29923-0_12.pdf},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 booktitle = {Joint International Semantic Technolgies (JIST)},
	 date-modified = {2016-06-16 06:16:05 +0000},
	 ee = {http://dx.doi.org/10.1007/978-3-642-29923-0_12},
	 file = {:pubs\\tian_JIST2011.pdf:PDF},
	 link = {http://link.springer.com/content/pdf/10.1007%2F978-3-642-29923-0_12.pdf},
	 pages = {176-191},
	 rossref = {DBLP:conf/aswc/2011},
	 title = {Enhancing Source Selection for Live Queries over {L}inked {D}ata via Query Log Mining},
	 year = {2011}
}

@article{hogahart2011aa,
	 abstract = {In this report, we discuss the architecture and implementation of
the Semantic {W}eb Search Engine (SWSE). Following traditional search
engine architecture, SWSE consists of crawling, data enhancing, indexing
and a user interface for search, browsing and retrieval of information;
unlike traditional search engines, SWSE operates over RDF {W}eb data
(loosely also known as {L}inked {D}ata) which implies unique challenges
for the system design, architecture, algorithms, implementation and
user interface. In particular, many challenges exist in adopting
Semantic {W}eb technologies for {W}eb data: the unique challenges of
the {W}eb (in terms of scale, unreliability, inconsistency and noise)
are largely overlooked by the current Semantic {W}eb standards. In
this report, we detail the current SWSE system, initially detailing
the architecture and later elaborating upon the function, design, implementation and performance of each individual component. In so
doing, we also give an insight into how current Semantic {W}eb standards
can be tailored, in a best-effort manner, for use on {W}eb data. Throughout, we offer evaluation and complementary argumentation to support our
design choices, and also offer discussion on future directions and
open research questions. Later, we also provide candid discussion
relating to the diffculties currently faced in bringing such a search
engine into the mainstream, and lessons learnt from roughly five
years working on the Semantic {W}eb Search Engine project.},
	 addendum = {(56 citations, impact factor 3.14)},
	 author = {Hogan, Aidan and Harth, Andreas and Umbrich, Jürgen and Kinsella, Sheila and Polleres, Axel and Decker, Stefan},
	 bdsk-url-1 = {http://www.deri.ie/fileadmin/documents/DERI-TR-2010-07-23.pdf},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 ee = {http://dx.doi.org/10.1016/j.{W}ebsem.2011.06.004},
	 file = {:pubs\\hogan_DERITR2010.pdf:PDF},
	 journal = {J. {W}eb Sem.},
	 link = {http://www.deri.ie/fileadmin/documents/DERI-TR-2010-07-23.pdf},
	 number = {4},
	 pages = {365-401},
	 publisher = {Elsevier},
	 title = {Searching and browsing {L}inked {D}ata with {SWSE}: The {S}emantic {W}eb {S}earch {E}ngine},
	 volume = {9},
	 year = {2011}
}

@article{umbrhoga2014aa,
	 abstract = {Traditional approaches for querying the Web of Data often involve centralised warehouses that replicate remote data. Conversely, Linked Data principles allow for answering queries live over the Web by dereferencing URIs to traverse remote data sources at runtime. A number of authors have looked at answering SPARQL queries in such a manner; these link-traversal based query execution (LTBQE) approaches for Linked Data offer up-to-date results and decentralised (i.e., client-side) execution, but must operate over incomplete dereferenceable knowledge available in remote documents, thus affecting response times and ``recall'' for query answers. In this paper, we study the recall and effectiveness of LTBQE, in practice, for the Web of Data. Furthermore, to integrate data from diverse sources, we propose lightweight reasoning extensions to help find additional answers. From the state-of-the-art which (1) considers only dereferenceable information and (2) follows rdfs:seeAlso links, we propose extensions to consider (3) owl:sameAs links and reasoning, and (4) lightweight RDFS reasoning. We then estimate the recall of link-traversal query techniques in practice: we analyse a large crawl of the Web of Data (the BTC'11 dataset), looking at the ratio of raw data contained in dereferenceable documents vs. the corpus as a whole and determining how much more raw data our extensions make available for query answering. We then stress-test LTBQE (and our extensions) in real-world settings using the FedBench and DBpedia SPARQL Benchmark frameworks, and propose a novel benchmark called QWalk based on random walks through diverse data. We show that link-traversal query approaches often work well in uncontrolled environments for simple queries, but need to retrieve an unfeasible number of sources for more complex queries. We also show that our reasoning extensions increase recall at the cost of slower execution, often increasing the rate at which results returned; conversely, we show that reasoning aggravates performance issues for complex queries.},
	 author = {Umbrich, Jürgen and Hogan, Aidan and Polleres, Axel and Decker, Stefan},
	 bdsk-url-1 = {http://semantic-web-journal.org/content/link-traversal-querying-diverse-web-data-0},
	 date-added = {2014-04-24 12:31:50 +0000},
	 date-modified = {2016-06-16 06:17:16 +0000},
	 journal = {Semantic Web -- Interoperability, Usability, Applicability},
	 link = {http://semantic-web-journal.org/content/link-traversal-querying-diverse-web-data-0},
	 publisher = {IOS Press},
	 title = {Link Traversal Querying for a Diverse Web of Data},
	 year = {2014}
}

@inproceedings{umbrhaus2010aa,
	 addendum = {(36 citations)},
	 author = {Umbrich, Jürgen and Hausenblas, Michael and Hogan, Aidan and Polleres, Axel and Decker, Stefan},
	 bdsk-url-1 = {http://vmserver14.nuigalway.ie/xmlui/bitstream/handle/10379/1120/dynamics_ldow2010.pdf?sequence=1},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 booktitle = {{L}inked {D}ata on the {W}eb (LDOW) at WWW},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 ee = {http://ceur-ws.org/Vol-628/ldow2010_paper12.pdf},
	 keyword = {workshop},
	 link = {http://vmserver14.nuigalway.ie/xmlui/bitstream/handle/10379/1120/dynamics_ldow2010.pdf?sequence=1},
	 rossref = {DBLP:conf/www/2010ldow},
	 title = {Towards Dataset Dynamics: Change Frequency of {L}inked {O}pen {D}ata Sources},
	 year = {2010}
}

@inproceedings{umbrneum2015ab,
	 author = {Umbrich, Jürgen and Neumeier, Sebastian and Polleres, Axel},
	 booktitle = {The International Conference on Open and Big Data},
	 date-added = {2015-07-01 15:33:45 +0000},
	 date-modified = {2015-07-01 15:34:57 +0000},
	 month = {August},
	 title = {Quality assessment & evolution of Open Data portals},
	 year = {2015}
}

@inproceedings{umbrneum2015aa,
	 abstract = {In this work, we present the Open Data Portal Watch project, a public framework to continuously monitor and assess the (meta-)data quality in Open Data portals. We critically discuss the objectiveness of various quality metrics. Further, we report on early findings based on 22 weekly snapshots of 90 CKAN portals and highlight interesting observations and challenges.},
	 address = {Munich, Germany},
	 author = {Umbrich, Jürgen and Neumeier, Sebastian and Polleres, Axel},
	 bdsk-url-1 = {http://polleres.net/publications/umbr-etal-2015ODQ.pdf},
	 booktitle = {ODQ2015: Open Data Quality: from Theory to Practice Workshop},
	 date-added = {2015-04-20 13:20:58 +0000},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 keyword = {workshop},
	 link = {http://polleres.net/publications/umbr-etal-2015ODQ.pdf},
	 month = {mar},
	 title = {Towards assessing the quality evolution of Open Data portals},
	 year = {2015}
}

@inproceedings{aranpoll2014aa,
	 author = {Aranda, Carlos Buil and Polleres, Axel and Umbrich, Jürgen},
	 bdsk-url-1 = {http://dx.doi.org/10.1007/978-3-319-11915-1_25},
	 bibsource = {dblp computer science bibliography, http://dblp.org},
	 biburl = {http://dblp.uni-trier.de/rec/bib/conf/semweb/ArandaPU14},
	 booktitle = {The Semantic Web - {ISWC} 2014 - 13th International Semantic Web Conference, Riva del Garda, Italy, October 19-23, 2014. Proceedings, Part {II}},
	 date-added = {2014-12-18 09:27:24 +0000},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 doi = {10.1007/978-3-319-11915-1_25},
	 link = {http://dx.doi.org/10.1007/978-3-319-11915-1_25},
	 pages = {390--405},
	 timestamp = {Sat, 11 Oct 2014 13:34:43 +0200},
	 title = {Strategies for Executing Federated Queries in {SPARQL1.1}},
	 year = {2014}
}

@incollection{harthoga2007aa,
	 addendum = {(47 citations)},
	 author = {Harth, Andreas and Hogan, Aidan and Delbru, Renaud and Umbrich, Jürgen and O'Riain, Seán and Decker, Stefan},
	 bdsk-url-1 = {http://ceur-ws.org/Vol-295/paper18.pdf},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 booktitle = {Semantic {W}eb Challenge at ISWC},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 ee = {http://ceur-ws.org/Vol-295/paper18.pdf},
	 keyword = {other},
	 link = {http://ceur-ws.org/Vol-295/paper18.pdf},
	 rossref = {DBLP:conf/sem{W}eb/2007challenge},
	 title = {{SWSE}: Answers Before Links!},
	 year = {2007}
}

@inproceedings{umbrhoga2012aa,
	 abstract = {{L}inked {D}ata principles allow for processing SPARQL queries on-the-fly
by dereferencing URIs. Link-traversal query approaches for Linked
Data have the benefit of up-to-date results and decentralised execution, but operate only on explicit data from dereferenced documents, affecting
recall. In this paper, we show how inferable knowledge--- specifically
that found through owl:sameAs and RDFS reasoning---can improve recall
in this setting. We first analyse a corpus featuring 7 million Linked
Data sources and 2.1 billion quadruples: we (1) measure expected
recall by only considering dereferenceable information, (2) measure
the improvement in recall given by considering rdfs:seeAlso links
as previous proposals did. We further propose and measure the impact
of additionally considering (3) owl:sameAs links, and (4) applying
lightweight RDFS reasoning for finding more results, relying on static
schema information. We evaluate different configurations for live
queries covering different shapes and domains, generated from random
walks over our corpus.},
	 author = {Umbrich, Jürgen and Hogan, Aidan and Polleres, Axel and Decker, Stefan},
	 bdsk-url-1 = {http://sw.deri.org/~aidanh/docs/rr2012_paper12_final.pdf},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 booktitle = {International Conference on Web Reasoning and Rule Systems (RR)},
	 date-modified = {2016-06-16 06:16:50 +0000},
	 ee = {http://dx.doi.org/10.1007/978-3-642-33203-6_14},
	 file = {:pubs\̆mbrich_rr2012.pdf:PDF},
	 link = {http://sw.deri.org/~aidanh/docs/rr2012_paper12_final.pdf},
	 pages = {188-204},
	 publisher = {Springer},
	 rossref = {DBLP:conf/rr/2012},
	 title = {Improving the Recall of Live {L}inked {D}ata Querying through Reasoning},
	 year = {2012}
}

@article{vandumbraa,
	 abstract = {We describe SPARQLES: an online system that monitors the health of public SPARQL endpoints on the Web by probing them with custom-designed queries at regular intervals. We present the architecture of SPARQLES and the variety of analytics that it runs over public SPARQL endpoints, categorised by availability, discoverability, performance and interoperability. We also detail the interfaces that the system provides for human and software agents to learn more about the recent history and current state of an individual SPARQL endpoint or about overall trends concerning the maturity of all endpoints monitored by the system. We likewise present some details of the performance of the system and the impact it has had thus far.},
	 author = {Vandenbussche, Pierre-Yves and Umbrich, Jürgen and Matteis, Luca and Hogan, Aidan and Buil-Aranda, Carlos},
	 bdsk-url-1 = {http://www.semantic-web-journal.net/content/sparqles-monitoring-public-sparql-endpoints-1},
	 date-added = {2016-06-16 07:32:34 +0000},
	 date-modified = {2016-06-16 07:33:04 +0000},
	 journal = {Semantic Web Journal},
	 language = {EN},
	 link = {http://www.semantic-web-journal.net/content/sparqles-monitoring-public-sparql-endpoints-1},
	 title = {SPARQLES: Monitoring Public SPARQL Endpoints},
	 year = {2016}
}

@inproceedings{hartumbr2006aa,
	 addendum = {(62 citations, 24% acceptance rate)},
	 author = {Harth, Andreas and Umbrich, Jürgen and Decker, Stefan},
	 bdsk-url-1 = {http://sw.deri.org/2006/04/multicrawler/paper/paper.pdf},
	 bdsk-url-2 = {http://dx.doi.org/10.1007/11926078_19},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 booktitle = {International Semantic {W}eb Conference},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 doi = {http://dx.doi.org/10.1007/11926078_19},
	 ee = {http://dx.doi.org/10.1007/11926078_19},
	 link = {http://sw.deri.org/2006/04/multicrawler/paper/paper.pdf},
	 pages = {258-271},
	 publisher = {Springer},
	 rossref = {DBLP:conf/sem{W}eb/2006},
	 title = {Multi{C}rawler: A Pipelined Architecture for Crawling and Indexing {S}emantic {W}eb Data},
	 year = {2006}
}

@inproceedings{johaneum2016aa,
	 author = {Mitlöhner, Johann and Neumeier, Sebastian and Umbrich, Jürgen and Polleres, Axel},
	 booktitle = {2nd International Conference on Open and Big Data},
	 date-added = {2016-06-30 10:39:02 +0000},
	 date-modified = {2016-06-30 10:46:36 +0000},
	 month = {August},
	 note = {invited paper},
	 title = {Characteristics of Open Data CSV Files},
	 year = {2016}
}

@inproceedings{hartumbr2007aa,
	 addendum = {(153 citations 19% acceptance rate)},
	 author = {Harth, Andreas and Umbrich, Jürgen and Hogan, Aidan and Decker, Stefan},
	 bdsk-url-1 = {http://ir.library.nuigalway.ie/xmlui/bitstream/handle/10379/423/iswc2007.pdf},
	 bdsk-url-2 = {http://dx.doi.org/10.1007/978-3-540-76298-0_16},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 booktitle = {International Semantic Web Conference (ISWC)},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 doi = {http://dx.doi.org/10.1007/978-3-540-76298-0_16},
	 ee = {http://dx.doi.org/10.1007/978-3-540-76298-0_16},
	 link = {http://ir.library.nuigalway.ie/xmlui/bitstream/handle/10379/423/iswc2007.pdf},
	 pages = {211-224},
	 publisher = {Springer},
	 rossref = {DBLP:conf/sem{W}eb/2007},
	 title = {{YARS}2: A Federated Repository for Querying Graph Structured Data from the {W}eb},
	 year = {2007}
}

@inproceedings{umbrkarn2009aa,
	 annote = {- Jointly funded by Lion-2 and Clique},
	 author = {Umbrich, Jürgen and Karnstedt, Marcel},
	 bdsk-url-1 = {http://lwa09.informatik.tu-darmstadt.de/pub/KDML/%7BW%7DebHome/kdml09_J.Umbrich_et_al.pdf},
	 booktitle = {Knowledge Discovery, Data Mining, and Machine Learning Workshop (KDML)},
	 date-modified = {2016-06-16 06:16:19 +0000},
	 keyword = {workshop},
	 link = {http://lwa09.informatik.tu-darmstadt.de/pub/KDML/{W}ebHome/kdml09_J.Umbrich_et_al.pdf},
	 owner = {UmbrichJ},
	 timestamp = {2013.07.09},
	 title = {Fast and Scalable Pattern Mining for Media-Type Focused Crawling},
	 year = {2009}
}

@inproceedings{kafeumbr2012aa,
	 abstract = {We describe work-in-progress on the design and methodology of the
DynamicLinkedDataObservatory : a framework to monitor {L}inked {D}ata
over an extended period of time. The core goal of our work is to
collect frequent, continuous snapshots of a subset of the {W}eb of
Data that is interesting for further study and experimentation, with
an aim to capture raw data about the dynamics of {L}inked {D}ata. The
resulting corpora will be made openly and continuously available
to the {L}inked {D}ata research community. Herein, we (1) motivate the
importance of such a corpus; (2) outline some of the use-cases and
requirements for the resulting snapshots; (3) discuss different ̌iews"
of the {W}eb of Data that affect how we define a sample to monitor;
(4) detail how we select the scope of the monitoring experiment through
sampling, (5) discuss the final design of the monitoring framework
that will gather regular snapshots of (subsets of) the {W}eb of Data
over the coming months and years.},
	 author = {Käfer, Tobias and Umbrich, Jürgen and Hogan, Aidan and Polleres, Axel},
	 bdsk-url-1 = {http://events.linkeddata.org/ldow2012/papers/ldow2012-paper-14.pdf},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 booktitle = {{L}inked {D}ata on the {W}eb (LDOW) at WWW},
	 date-modified = {2016-06-16 06:15:46 +0000},
	 ee = {http://ceur-ws.org/Vol-937/ldow2012-paper-14.pdf},
	 keyword = {workshop},
	 link = {http://events.linkeddata.org/ldow2012/papers/ldow2012-paper-14.pdf},
	 publisher = {ACM},
	 rossref = {DBLP:conf/www/2012ldow},
	 title = {Dy{LDO}: Towards a Dynamic {L}inked {D}ata Observatory},
	 year = {2012}
}

@inproceedings{aranhoga2013aa,
	 abstract = {Hundreds of public {SPARQL} endpoints have been deployed on the{W}eb, forming a novel decentralised infrastructure for querying billions
of structured facts from a variety of sources on a plethora of topics.
But is this infrastructure mature enough to support applications?
For 427 public  {SPARQL} endpoints registered on the DataHub, we conduct
various experiments to test their maturity. Regarding discoverability, we find that only one-third of endpoints make descriptive meta-data
available, making it dificult to locate or learn about their content
and capabilities. Regarding interoperability, we find patchy support
for established SPARQL features like {ORDER BY} as well as (understandably)
for new  {SPARQL} 1.1 features. Regarding efficiency, we show that the
performance of endpoints for generic queries can vary by up to 3
- 4 orders of magnitude. Regarding availability, based on a 26-month
long monitoring experiment, we show that only 32.2% of public endpoints
can be expected to have (monthly) "two-nines" uptimes of 99 - 100%.},
	 author = {Aranda, Carlos Buil and Hogan, Aidan and Umbrich, Jürgen and Vandenbussche, Pierre-Yves},
	 booktitle = {Internation Semantic {W}eb Conference (ISWC)},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 owner = {UmbrichJ},
	 publisher = {Springer},
	 timestamp = {2013.07.09},
	 title = {{SPARQL} {W}eb-Querying Infrastructure: Ready for Action?},
	 year = {2013}
}

@inproceedings{kafeabde2013aa,
	 addendum = {(26% acceptance rate)},
	 author = {Käfer, Tobias and Abdelrahman, Ahmed and Umbrich, Jürgen and O'Byrne, Patrick and Hogan, Aidan},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 booktitle = {Extended Semantic Web Conference (ESWC)},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 ee = {http://dx.doi.org/10.1007/978-3-642-38288-8_15},
	 pages = {213-227},
	 publisher = {Springer},
	 rossref = {DBLP:conf/esws/2013},
	 title = {Observing {L}inked {D}ata Dynamics},
	 year = {2013}
}

@inproceedings{fernumbr2016aa,
	 author = {Fernandec Garcia, Javier David and Umbrich, Jürgen and Knuth, Magnus and Polleres, Axel},
	 booktitle = {12th International Conference on Semantic Systems (SEMANTICS)},
	 date-added = {2016-06-16 07:34:28 +0000},
	 date-modified = {2016-06-16 07:36:57 +0000},
	 month = {Sept},
	 title = {Evaluating Query and Storage Strategies for RDF Archives},
	 year = {2016}
}

@inproceedings{hogapoll2010aa,
	 author = {Hogan, Aidan and Polleres, Axel and Umbrich, Jürgen and Zimmermann, Antoine},
	 bdsk-url-1 = {http://aidanhogan.com/docs/cons_nefors10.pdf},
	 booktitle = {Workshop on New Forms of Reasoning for the Semantic {W}eb: Scalable & Dynamic (NeFoRS2010) at ESWC},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 keyword = {workshop},
	 link = {http://aidanhogan.com/docs/cons_nefors10.pdf},
	 owner = {UmbrichJ},
	 publisher = {Springer},
	 timestamp = {2013.07.09},
	 title = {Some entities are more equal than others: statistical methods to consolidate {L}inked {D}ata},
	 year = {2010}
}

@inproceedings{harthoga2008aa,
	 author = {Harth, Andreas and Hogan, Aidan and Umbrich, Jürgen and Decker, Stefan},
	 bdsk-url-1 = {http://hdl.handle.net/10379/440},
	 booktitle = {3rd XTech Conference},
	 date-modified = {2016-06-16 06:14:52 +0000},
	 keyword = {about entities,and return specific information,engines allow more expressive,for example people,from documents,from multiple,glean the required information,in contrast,manually trawl through lists,of links and,queries,queries over information integrated,semantic search,sources,users have to then},
	 link = {http://hdl.handle.net/10379/440},
	 owner = {UmbrichJ},
	 timestamp = {2013.07.09},
	 title = {Building a {S}emantic {W}eb Search Engine: Challenges and Solutions},
	 year = {2008}
}

@inproceedings{umbrkarn2012aa,
	 abstract = {Querying over cached indexes of {L}inked {D}ata often suffers from stale
or missing results due to infrequent updates and partial coverage
of sources. Conversely, live decentralised approaches offer fresh
results directly from the {W}eb, but exhibit slow response times due
to accessing numerous remote sources at runtime. We thus propose
a hybrid query approach that improves upon both paradigms, offering
fresher results from a broader range of sources than {L}inked {D}ata
caches while offering faster results than live querying. Our hybrid
query engine takes a cached and live query engine as black boxes, where a hybrid query planner splits an input query and delegates
the appropriate sub-queries to each interface. In this paper, we
discuss query planning alternatives and their main strengths and
weaknesses. We also present coherence measures to quantify the coverage
and freshness for cached indexes of {L}inked {D}ata, and show how these
measures can be used for hybrid query planning to optimise the trade-off
between fresh results and fast runtimes.},
	 addendum = {(16% acceptance rate)},
	 author = {Umbrich, Jürgen and Karnstedt, Marcel and Hogan, Aidan and Parreira, Josiane Xavier},
	 bdsk-url-1 = {http://sw.deri.org/~aidanh/docs/ekaw2012_paper71_final.pdf},
	 bdsk-url-2 = {http://dx.doi.org/10.1007/978-3-642-33876-2_16},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 booktitle = {International Conference on Knowledge Engineering and Knowledge Management (EKAW)},
	 date-modified = {2016-06-16 06:16:31 +0000},
	 doi = {http://dx.doi.org/10.1007/978-3-642-33876-2_16},
	 ee = {http://dx.doi.org/10.1007/978-3-642-33876-2_16},
	 file = {:pubs\̆mbrich_ekaw2012.pdf:PDF},
	 link = {http://sw.deri.org/~aidanh/docs/ekaw2012_paper71_final.pdf},
	 pages = {164-174},
	 publisher = {Springer},
	 rossref = {DBLP:conf/ekaw/2012},
	 title = {Freshening up while Staying Fast: Towards Hybrid {SPARQL} Queries},
	 year = {2012}
}

@inproceedings{umbrkarn2012ab,
	 abstract = {For {L}inked {D}ata query engines, there are inherent trade-offs between
centralised approaches that can eciently answer queries over data
cached from parts of the {W}eb, and live decentralised approaches that
can provide fresher results over the entire {W}eb at the cost of slower
response times. Herein, we propose a hybrid query execution approach
that returns fresher results from a broader range of sources vs.
the centralised scenario, while speeding up results vs. the live
scenario. We first compare results from two public SPARQL stores
against current versions of the {L}inked {D}ata sources they cache; results
are often missing or out-of-date. We thus propose using coherence
estimates to split a query into a sub-query for which the cached
data have good fresh coverage, and a sub-query that should instead
be run live. Finally, we evaluate different hybrid query plans and
split positions in a real-world setup. Our results show that hybrid
query execution can improve freshness vs. fully cached results while
reducing the time taken vs. fully live execution.},
	 addendum = {(22% acceptance rate)},
	 author = {Umbrich, Jürgen and Karnstedt, Marcel and Hogan, Aidan and Parreira, Josiane Xavier},
	 bdsk-url-1 = {http://sw.deri.org/~aidanh/docs/iswc2012.pdf},
	 bdsk-url-2 = {http://dx.doi.org/10.1007/978-3-642-35176-1_38},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 booktitle = {International Semantic {W}eb Conference (ISWC)},
	 date-modified = {2016-06-16 06:16:38 +0000},
	 doi = {http://dx.doi.org/10.1007/978-3-642-35176-1_38},
	 ee = {http://dx.doi.org/10.1007/978-3-642-35176-1_38},
	 file = {:pubs\̆mbrich_iswc2012.pdf:PDF},
	 link = {http://sw.deri.org/~aidanh/docs/iswc2012.pdf},
	 pages = {608-624},
	 publisher = {Springer},
	 rossref = {DBLP:conf/sem{W}eb/2012-1},
	 title = {Hybrid {SPARQL} Queries: Fresh vs. Fast Results},
	 year = {2012}
}

@inproceedings{umbrkarn2012ac,
	 abstract = {Enabling the ``{W}eb of Data'' has recently gained increased attention, particularly driven by the success of {L}inked {D}ata. The agreed need
for technologies from the database domain is therein often referred
to as the ``{W}eb as a Database'', a concept that is still more a vision
than a reality. Meanwhile, the database community proposed the notion
of dataspaces managed by support platforms, as an alternative view
on the data management problem for small-scale, loosely connected
environments of heterogenous data sources. The {W}eb of Data can actually
be seen as a collection of inter-connected dataspaces. In this work, we propose a combination of {L}inked {D}ata and database technologies
to provide support platforms for these {W}eb dataspaces. We argue that
while separated, {L}inked {D}ata still lacks database technology and
the dataspace idea lacks openness and scale. We put particular focus
on the challenge of how to index, search and query structured data
on the {W}eb in a way that is appropriate for its dynamic, heterogeneous, loosely connected, and open character. Based on an empirical study, we argue that none of the two extremes on its own -- centralised repositories
vs. on-demand distributed querying -- can meet all requirements. We
propose and discuss an alternative hybrid approach combining the
best of both sides to find a better tradeoff between result freshness
and fast query response times.},
	 author = {Umbrich, Jürgen and Karnstedt, Marcel and Parreira, Josiane Xavier and Polleres, Axel and Hauswirth, Manfred},
	 bdsk-url-1 = {http://axel.deri.ie/publications/umbr-etal-2012DES%7BW%7Deb.pdf},
	 bdsk-url-2 = {http://doi.ieeecomputersociety.org/10.1109/ICDEW.2012.55},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 booktitle = {Data Engineering meets the Semantic {W}eb (DES{W}eb) at ICDE},
	 date-modified = {2016-06-16 06:17:22 +0000},
	 doi = {http://doi.ieeecomputersociety.org/10.1109/ICDEW.2012.55},
	 ee = {http://doi.ieeecomputersociety.org/10.1109/ICDEW.2012.55},
	 file = {:pubs\̆mbrich_DES{W}eb2012.pdf:PDF},
	 keyword = {workshop},
	 link = {http://axel.deri.ie/publications/umbr-etal-2012DES{W}eb.pdf},
	 pages = {23-28},
	 publisher = {Institute of Electrical and Electronics Engineers (IEEE)},
	 rossref = {DBLP:conf/icde/2012w},
	 title = {{L}inked {D}ata and Live Querying for Enabling Support Platforms for {W}eb Dataspaces},
	 year = {2012}
}

@article{hogazimm2012aa,
	 abstract = {With respect to large-scale, static, {L}inked {D}ata corpora, in this
paper we discuss scalable and distributed methods for entity consolidation
(aka. smushing, entity resolution, object consolidation, etc.) to
locate and process names that signify the same entity. We investigate
(i) a baseline approach, which uses explicit owl:sameAs relations
to perform consolidation; (ii) extended entity consolidation which
additionally uses a subset of OWL 2 RL/RDF rules to derive novel
owl:sameAs relations through the semantics of inverse-functional
properties, functional-properties and (max-)cardinality restrictions
with value one; (iii) deriving weighted concurrence measures between
entities in the corpus based on shared inlinks/outlinks and attribute
values using statistical analyses; (iv) disambiguating (initially)
consolidated entities based on inconsistency detection using OWL
2 RL/RDF rules. Our methods are based upon distributed sorts and
scans of the corpus, where we deliberately avoid the requirement
for indexing all data. Throughout, we offer evaluation over a diverse
{L}inked {D}ata corpus consisting of 1.118 billion quadruples derived
from a domain-agnostic, open crawl of 3.985 million RDF/XML {W}eb documents, demonstrating the feasibility of our methods at that scale, and giving
insights into the quality of the results for real-world data.},
	 addendum = {(impact factor 3.14)},
	 author = {Hogan, Aidan and Zimmermann, Antoine and Umbrich, Jürgen and Polleres, Axel and Decker, Stefan},
	 bdsk-url-1 = {http://sw.deri.org/~aidanh/docs/entcons_jws_final.pdf},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 ee = {http://dx.doi.org/10.1016/j.{W}ebsem.2011.11.002},
	 file = {:pubs\\hogan_jws2012.pdf:PDF},
	 journal = {J. {W}eb Sem.},
	 link = {http://sw.deri.org/~aidanh/docs/entcons_jws_final.pdf},
	 pages = {76-110},
	 title = {Scalable and distributed methods for entity matching, consolidation and disambiguation over {L}inked {D}ata corpora},
	 volume = {10},
	 year = {2012}
}

@article{vandhoga2014aa,
	 author = {Vandenbussche, Pierre-Yves and Hogan, Aidan and Umbrich, Jürgen and Aranda, Carlos Buil},
	 bdsk-url-1 = {http://ercim-news.ercim.eu/en96/special/sparql-a-gateway-to-open-data-on-the-web},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 date-added = {2014-04-24 12:30:01 +0000},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 journal = {ERCIM News},
	 number = {96},
	 title = {SPARQL: A Gateway to Open Data on the Web?},
	 volume = {2014},
	 year = {2014}
}

@article{umbrhose2011aa,
	 addendum = {(impact factor 1.196)},
	 author = {Umbrich, Jürgen and Hose, Katja and Karnstedt, Marcel and Harth, Andreas and Polleres, Axel},
	 bdsk-url-1 = {http://www.mpi-inf.mpg.de/~khose/publications/WWWJ2011.pdf},
	 bdsk-url-2 = {http://dx.doi.org/10.1007/s11280-010-0107-z},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 date-modified = {2016-06-16 06:15:03 +0000},
	 doi = {http://dx.doi.org/10.1007/s11280-010-0107-z},
	 ee = {http://dx.doi.org/10.1007/s11280-010-0107-z},
	 journal = {World Wide {W}eb},
	 link = {http://www.mpi-inf.mpg.de/~khose/publications/WWWJ2011.pdf},
	 number = {5-6},
	 pages = {495-544},
	 title = {Comparing data summaries for processing live queries over {L}inked {D}ata},
	 volume = {14},
	 year = {2011}
}

@inproceedings{umbrvill2010aa,
	 author = {Umbrich, Jürgen and Villazón-Terrazas, Boris and Hausenblas, Michael},
	 bdsk-url-1 = {http://ceur-ws.org/Vol-665/UmbrichEtAl_COLD2010.pdf},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 booktitle = {Consuming {L}inked {D}ata (COLD) at ISWC},
	 date-modified = {2016-06-16 06:15:19 +0000},
	 ee = {http://ceur-ws.org/Vol-665/UmbrichEtAl_COLD2010.pdf},
	 keyword = {workshop},
	 link = {http://ceur-ws.org/Vol-665/UmbrichEtAl_COLD2010.pdf},
	 publisher = {Springer},
	 rossref = {DBLP:conf/sem{W}eb/2010cold},
	 title = {Dataset Dynamics Compendium: A Comparative Study},
	 year = {2010}
}

@inproceedings{umbrkarn2010aa,
	 author = {Umbrich, Jürgen and Karnstedt, Marcel and Land, Sebastian},
	 bdsk-url-1 = {http://www.kde.cs.uni-kassel.de/conf/lwa10/papers/kdml22.pdf},
	 booktitle = {Knowledge Discovery, Data Mining, and Machine Learning (KDML) at LWA},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 keyword = {workshop},
	 link = {http://www.kde.cs.uni-kassel.de/conf/lwa10/papers/kdml22.pdf},
	 owner = {UmbrichJ},
	 timestamp = {2013.07.09},
	 title = {Towards Understanding the Changing {W}eb: Mining the Dynamics of {L}inked-{D}ata Sources and Entities},
	 year = {2010}
}

@inproceedings{neumumbr2016aa,
	 author = {Neumeier, Sebastian and Umbrich, Jürgen},
	 booktitle = {2nd International Conference on Open and Big Data},
	 date-added = {2016-06-16 06:12:09 +0000},
	 date-modified = {2016-06-16 06:13:50 +0000},
	 title = {Measures for assessing the data freshness in Open Data portals},
	 year = {2016}
}

@incollection{umbrhoga2011aa,
	 abstract = {Aside from crawling, indexing, and querying RDF data centrally, Linked
Data principles allow for processing SPARQL queries on-the-fly by
dereferencing URIs. Proposed link-traversal

query approaches for {L}inked {D}ata have the benefits of up-to-date results
and decentralised (i.e., client-side) execution, but operate on incomplete
knowledge available in dereferenced documents, thus affecting recall. In this paper, we investigate how implicit
knowledge -- specifically that found through owl:sameAs and RDFS reasoning
-- can improve the recall in this setting. We start with

an empirical analysis of a large crawl featuring 4 m {L}inked {D}ata sources
and 1.1 g quadruples: we (1) measure expected recall by only considering
dereferenceable information, (2) measure the

improvement in recall given by considering rdfs:seeAlso links as previous
proposals did. We further propose and measure the impact of additionally
considering (3) owl:sameAs links, and (4) applying lightweight RDFS
reasoning (specifically rhoDF) for finding more results, relying
on static schema information. We evaluate our methods for live queries
over our crawl.},
	 author = {Umbrich, Jürgen and Hogan, Aidan and Polleres, Axel},
	 bdsk-url-1 = {http://arxiv.org/pdf/1109.0181v1.pdf},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 date-modified = {2016-06-16 06:16:44 +0000},
	 ee = {http://arxiv.org/abs/1109.0181},
	 file = {:pubs\̆mbrich_tr2011.pdf:PDF},
	 journal = {CoRR},
	 keyword = {other},
	 link = {http://arxiv.org/pdf/1109.0181v1.pdf},
	 title = {Improving the recall of decentralised {L}inked {D}ata querying through implicit knowledge},
	 volume = {abs/1109.0181},
	 year = {2011}
}

@inproceedings{neumumbr2016ac,
	 address = {Kobe, Japan},
	 author = {Neumaier, Sebastian and Umbrich, Jürgen and Parreira, Josiane Xavier and Polleres, Axel},
	 booktitle = {The 15th International Semantic Web Conference},
	 date-added = {2016-07-01 14:31:49 +0000},
	 date-modified = {2016-07-01 14:33:31 +0000},
	 month = {October},
	 note = {fourthcoming},
	 title = {Multi-level semantic labelling of numerical values},
	 year = {2016}
}

@article{neumumbr2016ab,
	 author = {Neumaier, Sebastian and Umbrich, Jürgen and Polleres, Axel},
	 date-added = {2016-06-30 10:36:23 +0000},
	 date-modified = {2016-06-30 10:47:31 +0000},
	 journal = {ACM Journal of Data and Information Quality (JDIQ)},
	 keyword = {open data, quality assessment},
	 note = {fourthcoming},
	 title = {Automated Quality Assessment of Metadata across Open Data Portals},
	 year = {2016}
}

@inproceedings{harthose2010aa,
	 addendum = {(101 citations, 14% acceptance rate)},
	 author = {Harth, Andreas and Hose, Katja and Karnstedt, Marcel and Polleres, Axel and Sattler, Kai-Uwe and Umbrich, Jürgen},
	 bdsk-url-1 = {http://www.mpi-inf.mpg.de/~khose/publications/WWW2010.pdf},
	 bdsk-url-2 = {http://doi.acm.org/10.1145/1772690.1772733},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 booktitle = {International World Wide Web Conferences (WWW)},
	 date-modified = {2016-06-16 06:15:12 +0000},
	 doi = {http://doi.acm.org/10.1145/1772690.1772733},
	 ee = {http://doi.acm.org/10.1145/1772690.1772733},
	 file = {:pubs\\harth_WWW2010.pdf:PDF},
	 link = {http://www.mpi-inf.mpg.de/~khose/publications/WWW2010.pdf},
	 pages = {411-420},
	 publisher = {ACM},
	 rossref = {DBLP:conf/www/2010},
	 title = {Data summaries for on-demand queries over {L}inked {D}ata},
	 year = {2010}
}

@inproceedings{blohumbr2009aa,
	 author = {Blohm, Sebastian and Umbrich, Jürgen and Cimiano, Philipp and Sure, York},
	 bdsk-url-1 = {http://uima.apache.org/downloads/gldv/gldv07-uima-blohm.pdf},
	 booktitle = {In {UIMA} Workshop at {GLDV} Frühjahrstagung},
	 date-modified = {2016-06-16 06:17:04 +0000},
	 keyword = {workshop},
	 link = {http://uima.apache.org/downloads/gldv/gldv07-uima-blohm.pdf},
	 organization = {PJM},
	 owner = {UmbrichJ},
	 publisher = {Citeseer},
	 timestamp = {2013.07.09},
	 title = {Iterative Learning of Relation Patterns for Market Analysis with {UIMA}},
	 volume = {2},
	 year = {2009}
}

@inbook{umbrkarn2013aa,
	 author = {Umbrich, Jürgen and Karnstedt, Marcel and Sattler, Kai-Uwe and Polleres, Axel},
	 chapter = {Index-Based Source Selection and Optimization},
	 date-modified = {2015-06-26 17:16:12 +0000},
	 editor = {Hose, Katja and Schenk, Ralf and Harth, Andreas},
	 owner = {umbrichj},
	 timestamp = {2013.08.29},
	 title = {{L}inked {D}ata Management},
	 year = {2013}
}

@inproceedings{umbrmrze2015aa,
	 author = {Umbrich, Jürgen and Mrzelj, Nina and Axel, Polleres},
	 booktitle = {Managing the Evolution and Preservation of the Data Web - First Diachron Workshop at ESWC 2015},
	 date-added = {2015-04-24 09:25:39 +0000},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 keyword = {workshop},
	 title = {Towards capturing and preserving changes on the Web of Data},
	 year = {2015}
}

@inproceedings{fernpoll2015aa,
	 author = {Fernandec Garcia, Javier David and Polleres, Axel and Umbrich, Jürgen},
	 booktitle = {In DIACHRON workshop (co-located with ESWC)},
	 date-added = {2015-04-24 10:52:36 +0000},
	 date-modified = {2015-06-26 16:58:44 +0000},
	 keyword = {workshop},
	 title = {Towards Efficient Archiving of Dynamic Linked Open Data},
	 year = {2015}
}

@inbook{pollhoga2013aa,
	 author = {Polleres, Axel and Hogan, Aidan and Delbru, Renaud and Umbrich, Jürgen},
	 chapter = {{RDFS} & {OWL} Reasoning for {L}inked {D}ata},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 editor = {Rudolph, Sebastian},
	 owner = {umbrichj},
	 pages = {91-149},
	 publisher = {Springer},
	 timestamp = {2013.08.29},
	 title = {Reasoning {W}eb Summer School},
	 year = {2013}
}

@inproceedings{di-cfern2015aa,
	 author = {Di Ciccio, Claudio and Fernandez Garcia, Javier David and Umbrich, Jürgen},
	 booktitle = {ODQ2015: Open Data Quality: from Theory to Practice Workshop},
	 date-added = {2015-04-24 11:01:04 +0000},
	 date-modified = {2016-06-16 06:16:57 +0000},
	 keyword = {workshop},
	 title = {Improving The Usability Of Open Data Portals From A Business Process Perspective},
	 year = {2015}
}

@incollection{rakhumbr2013aa,
	 author = {Rakhmawati, Nur Aini and Umbrich, Jürgen and Karnstedt, Marcel and Hasnain, Ali and Hausenblas, Michael},
	 bdsk-url-1 = {http://arxiv.org/pdf/1306.1723v1.pdf},
	 bibsource = {DBLP, http://dblp.uni-trier.de},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 ee = {http://arxiv.org/abs/1306.1723},
	 journal = {CoRR},
	 keyword = {other},
	 link = {http://arxiv.org/pdf/1306.1723v1.pdf},
	 title = {Querying over Federated {SPARQL} Endpoints - A State of the Art Survey},
	 volume = {abs/1306.1723},
	 year = {2013}
}

@incollection{umbrglas2009aa,
	 abstract = {Publishing and consuming content on the {W}eb of Data often requires
considerable expertise in the underlying technolo- gies, as the expected
services to achieve this are either not packaged in a simple and
accessible manner, or are simply lacking. In this poster, we address
selected issues by briefly introducing the following essential {W}eb
of Data services de- signed to lower the entry-barrier for {W}eb developers:
(i) a multi-ping service, (ii) a meta search service, and (iii) a
universal discovery service.},
	 author = {Umbrich, Jürgen and Glaser, Hugh and Hastrup, Tuuka and Millard, Ian and Hausenblas, Michael},
	 bdsk-url-1 = {http://eprints.ecs.soton.ac.uk/18160/},
	 booktitle = {Posters{&}Demos at International Semantic Web Conference (ISWC)},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 keyword = {demo},
	 link = {http://eprints.ecs.soton.ac.uk/18160/},
	 month = {oct},
	 owner = {UmbrichJ},
	 publisher = {Springer},
	 timestamp = {2013.07.09},
	 title = {{W}eb of Data Plumbing - Lowering the Barriers to Entry},
	 year = {2009}
}

@inbook{harthoga2013aa,
	 author = {Harth, Andreas and Hogan, Aidan and Umbrich, Jürgen and Kinsella, Sheila and Polleres, Axel and Decker, Stefan},
	 chapter = {Searching and Browsing {L}inked {D}ata with {SWSE}},
	 date-modified = {2015-06-01 13:31:07 +0000},
	 editor = {Roberto De Virgilio, Francesco Guerra, Yannis Velegrakis},
	 owner = {umbrichj},
	 publisher = {Springer},
	 timestamp = {2013.08.29},
	 title = {Semantic Search over the {W}eb},
	 year = {2013}
}

@phdthesis{umbr2012aa,
	 author = {Umbrich, Jürgen},
	 date-modified = {2016-06-16 06:14:30 +0000},
	 owner = {umbrichj},
	 school = {Digitial Enterprise Research Institute, National University Ireland, Galway},
	 timestamp = {2013.09.15},
	 title = {A Hybrid Framework for Querying {L}inked {D}ata Dynamically},
	 year = {2012}
}