Simon Bin

@article{demir2025ontolearn,
author = {Demir, Caglar and Baci, Alkid and Kouagou, N’Dah Jean and Sieger, Leonie Nora and Hein­dorf, Ste­fan and Bin, Simon and Bl{ü}baum, Lukas and Bigerl, Alexan­der and Ngo­mo, Axel-Cyrille Ngonga},
jour­nal = {Jour­nal of Machine Learn­ing Research},
key­words = {sys:relevantFor:infai},
pages = {1–6},
title = {Ontolearn—A Frame­work for Large-scale {OWL} Class Expres­sion Learn­ing in Python},
vol­ume = 26,
year = 2025
}

@inproceedings{Stadler2024fair,
address = {Her­sonis­sos, Greece},
author = {Stadler, Claus and Büh­mann, Lorenz and Bin, Simon},
book­ti­tle = {Pro­ceed­ings of the Fourth Work­shop on Meta­da­ta and Research (objects) Man­age­ment for Linked Open Sci­ence — DaMa­LOS 2024 co-locat­ed with Extend­ed Seman­tic Web Con­fer­ence (ESWC)},
edi­tor = {Cas­tro, Ley­la Jael and Reb­holz-Schuh­mann, Diet­rich and Dessì, Dani­lo and Schimm­ler, Son­ja},
key­words = {sys:relevantFor:infai},
month = {05},
pub­lish­er = {PUBLISSO},
title = {{FAIR} Data Pub­lish­ing with Apache Maven},
year = 2024
}

@inproceedings{bin2024geosparql,
abstract = {This paper explores the inte­gra­tion of geo-spa­tial data into RDF (Resource Descrip­tion Frame­work) using Apache Jena, a pop­u­lar Java-based frame­work for build­ing Seman­tic Web appli­ca­tions. We explain the basic rep­re­sen­ta­tion of geo-spa­tial data in RDF with a focus on both the new GeoSPAR­QL 1.1 stan­dard and Apache Jena. Our inves­ti­ga­tion cov­ers advanced tech­niques, such as trans­for­ma­tion of coor­di­nate ref­er­ence sys­tems, aggre­ga­tion of geo-spa­tial data, cre­ation of new geo-objects, and sim­pli­fi­ca­tion of poly­gons. Addi­tion­al­ly, we dis­cuss the usage of the H3 Grid as a Dis­crete Glob­al Grid Sys­tem (DGGS) for geo-spa­tial con­ver­sion. Fur­ther­more, we present per­for­mance opti­mi­sa­tions spe­cif­ic to Apache Jena, includ­ing per-graph geo-index­ing, improved geo-index seri­al­iza­tion for faster start­up times, and man­u­al opti­mi­sa­tion of geo-spa­tial queries. We con­clude with a com­par­i­son of dif­fer­ent geo-func­tions and out­line future direc­tions for enhanc­ing geo-spa­tial data man­age­ment in RDF.},
address = {Her­sonis­sos, Greece},
author = {Bin, Simon and Stadler, Claus and B{ü}hmann, Lorenz and Mar­tin, Michael},
book­ti­tle = {Pro­ceed­ings of the 6th Inter­na­tion­al Work­shop on Geospa­tial Linked Data 2024 co-locat­ed with 21st Extend­ed Seman­tic Web Con­fer­ence (ESWC 2024)},
edi­tor = {Hom­burg, Timo and Yaman, Beyza and Sherif, Mohamed Ahmed and Ngo­mo, Axel-Cyrille Ngonga},
key­words = {sys:relevantFor:infai},
month = {05},
series = {{CEUR} Work­shop Pro­ceed­ings},
title = {Get­ting prac­ti­cal with {G}eo{SPARQL} and {A}pache {J}ena},
vol­ume = 3743,
year = 2024
}

@inproceedings{DBLP:conf/kgcw/StadlerB24,
abstract = {This is the report of the par­tic­i­pa­tion of the RDF­Pro­cess­ing­Toolk­it (RPT) in the KGCW2024 Chal­lenge at ESWC 2024. The RPT sys­tem process­es RML spec­i­fi­ca­tions by trans­lat­ing them into a series of extend­ed SPARQL CONSTRUCT queries. The nec­es­sary SPARQL exten­sions are pro­vid­ed as plu­g­ins for the Apache Jena frame­work. This year’s chal­lenge com­pris­es a per­for­mance and a con­for­mance track. For the per­for­mance track, a homo­ge­neous envi­ron­ment was kind­ly pro­vid­ed by the work­shop orga­niz­ers in order to facil­i­tate com­pa­ra­bil­i­ty of mea­sure­ments. In this track, we main­ly adapt­ed the set­up from our last year’s par­tic­i­pa­tion. For the con­for­mance track, we updat­ed our sys­tem with sup­port for the rml-core mod­ule of the upcom­ing RML revi­sion. We also report on the issues and short­com­ings we encoun­tered as a base for future improve­ments.},
address = {Her­sonis­sos, Greece},
author = {Stadler, Claus and Bin, Simon},
book­ti­tle = {Pro­ceed­ings of the 5th Inter­na­tion­al Work­shop on Knowl­edge Graph Con­struc­tion co-locat­ed with 21th Extend­ed Seman­tic Web Con­fer­ence {(ESWC} 2024)},
edi­tor = {Chaves{-}Fraga, David and Dimou, Anas­ta­sia and Iglesias{-}Molina, Ana and Ser­les, Umut­can and Ass­che, Dylan Van},
key­words = {sys:relevantFor:infai},
month = {05},
series = {{CEUR} Work­shop Pro­ceed­ings},
title = {{KGCW2024} Chal­lenge Report: {RDF}{P}rocessing{T}oolkit},
vol­ume = 3718,
year = 2024
}

@inproceedings{bin-2023–base-platform,
abstract = {We present an Open Source base plat­form for the Coy­Pu knowl­edge graph project in the resilience domain. We report on our expe­ri­ences with sev­er­al tools which are used to cre­ate, main­tain, serve, view and explore a mod­u­lar large-scale knowl­edge graph, as well as the adap­tions that were nec­es­sary to enable fric­tion­less inter­ac­tion from both per­for­mance and usabil­i­ty per­spec­tives. For this pur­pose, sev­er­al adjust­ments had to be made. We pro­vide a broad view of dif­fer­ent pro­grams which are of rel­e­vance to this domain. We demon­strate that while it is already pos­si­ble to achieve good results with free soft­ware, there are still sev­er­al pain points that need to be addressed. Res­o­lu­tion of these issues is often not only a mat­ter of con­fig­u­ra­tion but requires mod­i­fi­ca­tion of the source code as well.},
address = {Her­sonis­sos, Greece},
author = {Bin, Simon and Stadler, Claus and Radtke, Nor­man and Jung­hanns, Kurt and Grün­der-Fahrer, Sabine and Mar­tin, Michael},
book­ti­tle = {Pro­ceed­ings of the Inter­na­tion­al Work­shop on Linked Data-dri­ven Resilience Research 2023},
edi­tor = {Tramp, Sebas­t­ian and Usbeck, Ricar­do and Arndt, Natanael and Holze, Julia and Auer, Sören},
key­words = {sys:relevantFor:infai},
month = {05},
series = {{CEUR} Work­shop Pro­ceed­ings},
title = {Base Plat­form for Knowl­edge Graphs with Free Soft­ware},
vol­ume = 3401,
year = 2023
}

@inproceedings{stadler2023-kgcw-challenge,
abstract = {This is the report of our par­tic­i­pa­tion in the KGCW2023 Chal­lenge @ ESWC 2023 with our RDFProcessingToolkit/Sansa sys­tem which won the “fastest” tool award. The chal­lenge was about the con­struc­tion of RDF knowl­edge graphs from RML spec­i­fi­ca­tions with vary­ing com­plex­i­ty in regard to the mix of input for­mats, char­ac­ter­is­tics of the data and the need­ed join oper­a­tions. We detail how we inte­grat­ed our tool into the pro­vid­ed bench­mark frame­work. There­by we also report on the issues and short­com­ings we encoun­tered as a base for future improve­ments. Fur­ther­more, we pro­vide an analy­sis of the data mea­sured with the bench­mark frame­work.},
address = {Her­sonis­sos, Greece},
author = {Bin, Simon and Stadler, Claus and Büh­mann, Lorenz},
book­ti­tle = {4th Inter­na­tion­al Work­shop on Knowl­edge Graph Con­struc­tion @ ESWC 2023},
key­words = {sys:relevantFor:infai},
num­ber = 3471,
series = {CEUR work­shop pro­ceed­ings},
title = {{KGCW}2023 Chal­lenge Report {RDF}{P}rocessing{T}oolkit / Sansa},
year = 2023
}

@inproceedings{stadler-c-2022–geospacial,
abstract = {In the con­text of cri­sis infor­mat­ics, the inte­gra­tion and exploita­tion of high vol­umes of het­ero­ge­neous data from mul­ti­ple sources is one of the big chances as well as chal­lenges up to now. Seman­tic Web tech­nolo­gies have proven a valu­able means to inte­grate and rep­re­sent knowl­edge on the basis of domain con­cepts which improves inter­op­er­abil­i­ty and inter­pretabil­i­ty of infor­ma­tion resources and allows deriv­ing more knowl­edge via seman­tic rela­tions and rea­son­ing. In this paper, we inves­ti­gate the poten­tial of rep­re­sent­ing and pro­cess­ing geospa­tial infor­ma­tion with­in the seman­tic par­a­digm. We show, on the tech­ni­cal lev­el, how exist­ing open source means can be used and sup­ple­ment­ed as to effi­cient­ly han­dle geo­graph­ic infor­ma­tion and to con­vey exem­plary results high­ly rel­e­vant in con­text of cri­sis man­age­ment appli­ca­tions. When giv­en seman­tic resources get enriched with geospa­tial infor­ma­tion, new infor­ma­tion can be retrieved com­bin­ing the con­cepts of mul­ti-poly­gons and geo-coor­di­nates and using the pow­er of GeoSPAR­QL queries. Cus­tom SPARQL exten­sion func­tions and data types for JSON, XML and CSV as well as for dialects such as Geo­J­SON and GML allow for suc­cinct inte­gra­tion of het­ero­ge­neous data. We imple­ment­ed these fea­tures for the Apache Jena Seman­tic Web frame­work by lever­ag­ing its plu­g­in sys­tems. Fur­ther­more, sig­nif­i­cant improve­ments w.r.t. GeoSPAR­QL query per­for­mance have been con­tributed to the frame­work.},
address = {Leipzig, Ger­many},
author = {Stadler, Claus and Bin, Simon and Büh­mann, Lorenz and Radtke, Nor­man and Jung­hanns, Kurt and Grün­der-Fahrer, Sabine and Mar­tin, Michael},
book­ti­tle = {Pro­ceed­ings of the Inter­na­tion­al Work­shop on Data-dri­ven Resilience Research 2022},
edi­tor = {Arndt, Natanael and Grün­der-Fahrer, Sabine and Holze, Julia and Mar­tin, Michael and Tramp, Sebas­t­ian},
key­words = {sys:relevantFor:infai},
month = {07},
series = {{CEUR} Work­shop Pro­ceed­ings},
title = {Seman­tifi­ca­tion of Geospa­tial Infor­ma­tion for Enriched Knowl­edge Rep­re­sen­ta­tion in Con­text of Cri­sis Infor­mat­ics},
vol­ume = 3376,
year = 2022
}

@article{WestphalGCBB022,
author = {West­phal, Patrick and Gruben­mann, Tobias and Col­larana, Diego and Bin, Simon and Büh­mann, Lorenz and Lehmann, Jens},
jour­nal = {Knowl. Based Syst.},
key­words = {sys:relevantFor:infai},
title = {Spa­tial con­cept learn­ing and infer­ence on geospa­tial poly­gon data},
vol­ume = 241,
year = 2022
}

@inproceedings{wenige2020kindex,
author = {Wenige, Lisa and Stadler, Claus and Bin, Simon and Büh­mann, Lorenz and Jung­hanns, Kurt and Mar­tin, Michael},
book­ti­tle = {LASCAR Work­shop at the Extend­ed Seman­tic Web Con­fer­ence (ESWC)},
key­words = {sys:relevantFor:infai},
title = {Auto­mat­ic Sub­ject Index­ing with Knowl­edge Graphs},
year = 2020
}

@article{stadler2020facete,
abstract = {In this work, we present a schema-agnos­tic faceted brows­ing bench­mark gen­er­a­tion frame­work for RDF data and SPARQL engines. Faceted search is a tech­nique that allows nar­row­ing down sets of infor­ma­tion items by apply­ing con­straints over their prop­er­ties, where­as facets cor­re­spond to prop­er­ties of these items. While our work can be used to realise real-world faceted search user inter­faces, our focus lies on the con­struc­tion and bench­mark­ing of faceted search queries over knowl­edge graphs. The RDF mod­el exhibits sev­er­al traits that seem­ing­ly make it a nat­ur­al foun­da­tion for faceted search: all infor­ma­tion items are rep­re­sent­ed as RDF resources, prop­er­ty val­ues typ­i­cal­ly already cor­re­spond to mean­ing­ful seman­tic clas­si­fi­ca­tions, and with SPARQL there is a stan­dard lan­guage for uni­form­ly query­ing instance and schema infor­ma­tion. How­ev­er, although faceted search is ubiq­ui­tous today, it is typ­i­cal­ly not per­formed on the RDF mod­el direct­ly. Two major sources of con­cern are the com­plex­i­ty of query gen­er­a­tion and the query per­for­mance. To over­come the for­mer, our frame­work comes with an inter­me­di­ate domain-spe­cif­ic lan­guage. There­by our approach is SPAR­QL-dri­ven which means that every faceted search infor­ma­tion need is inten­sion­al­ly expressed as a sin­gle SPARQL query. In regard to the lat­ter, we inves­ti­gate the pos­si­bil­i­ties and lim­its of real-time SPAR­QL-dri­ven faceted search on con­tem­po­rary triple stores. We report on our find­ings by eval­u­at­ing sys­tems per­for­mance and cor­rect­ness char­ac­ter­is­tics when exe­cut­ing a bench­mark gen­er­at­ed using our gen­er­a­tion frame­work. All com­po­nents, name­ly the bench­mark gen­er­a­tor, the bench­mark run­ners and the under­ly­ing faceted search frame­work, are pub­lished freely avail­able as open source.},
author = {Stadler, Claus and Bin, Simon and Wenige, Lisa and Büh­mann, Lorenz and Lehmann, Jens},
jour­nal = {Jour­nal of Web Seman­tics},
key­words = {sys:relevantFor:infai},
pages = 100614,
title = {Schema-agnos­tic SPAR­QL-dri­ven faceted search bench­mark gen­er­a­tion},
year = 2020
}

@article{smlbench,
author = {West­phal, Patrick and Büh­mann, Lorenz and Bin, Simon and Jabeen, Haji­ra and Lehmann, Jens},
jour­nal = {Seman­tic Web Jour­nal},
key­words = {sys:relevantFor:infai},
title = {SML-Bench – A Bench­mark­ing Frame­work for Struc­tured Machine Learn­ing},
year = 2018
}

@inproceedings{www2018dllearner,
author = {Buehmann, Lorenz and Lehmann, Jens and West­phal, Patrick and Bin, Simon},
book­ti­tle = {The Web Conf (WWW) 2018 Jour­nals Track},
key­words = {sys:relevantFor:infai},
title = {DL-Learn­er – Struc­tured Machine Learn­ing on Seman­tic Web Data},
year = 2018
}

@inproceedings{iermilov-2017-sansa-iswc-demo,
author = {Ermilov, Ivan and Lehmann, Jens and Sejdiu, Gez­im and Büh­mann, Lorenz and West­phal, Patrick and Stadler, Claus and Bin, Simon and Chakraborty, Nilesh and Pet­z­ka, Hen­ning and Saleem, Muham­mad and Ngonga, Axel-Cyrille Ngo­mo and Jabeen, Haji­ra},
book­ti­tle = {Pro­ceed­ings of 16th Inter­na­tion­al Seman­tic Web Con­fer­ence, Poster \& Demos},
key­words = {buehmann},
title = {The Tale of Sansa Spark},
year = 2017
}

@inproceedings{lehmann-2017-sansa-iswc,
author = {Lehmann, Jens and Sejdiu, Gez­im and Büh­mann, Lorenz and West­phal, Patrick and Stadler, Claus and Ermilov, Ivan and Bin, Simon and Chakraborty, Nilesh and Saleem, Muham­mad and Ngonga, Axel-Cyrille Ngo­mo and Jabeen, Haji­ra},
book­ti­tle = {Pro­ceed­ings of 16th Inter­na­tion­al Seman­tic Web Con­fer­ence — Resources Track (ISWC’2017)},
key­words = {buehmann},
pages = {147–155},
pub­lish­er = {Springer},
title = {Dis­trib­uted Seman­tic Ana­lyt­ics using the SANSA Stack},
year = 2017
}

@inproceedings{bin-2017-sake,
author = {Bin, Simon and West­phal, Patrick and Lehmann, Jens and Ngonga, Axel-Cyrille Ngo­mo},
book­ti­tle = {IEEE Big Data Con­fer­ence 2017},
key­words = {sys:relevantFor:infai},
title = {Imple­ment­ing Scal­able Struc­tured Machine Learn­ing for Big Data in the SAKE Project},
year = 2017
}

@inproceedings{sparqllearner,
author = {Bin, Simon and B{ü}hmann, Lorenz and Lehmann, Jens and {Ngonga Ngo­mo}, Axel-Cyrille},
book­ti­tle = {ECAI 2016 — Pro­ceed­ings of the 22nd Euro­pean Con­fer­ence on Arti­fi­cial Intel­li­gence},
edi­tor = {Kamin­ka, Gal A. and Fox, Maria and Bou­quet, Pao­lo and H{ü}llermeier, Eyke and Dignum, Vir­ginia and Dignum, Frank and van Harme­len, Frank},
key­words = {buehmann},
pages = {1551–1552},
pub­lish­er = {IOS Press},
series = {Fron­tiers in Arti­fi­cial Intel­li­gence and Appli­ca­tions},
title = {Towards {SPARQL}-Based Induc­tion for Large-Scale {RDF} Data sets},
vol­ume = 285,
year = 2016
}

@incollection{volke2014visual,
author = {Volke, Sebas­t­ian and Bin, Simon and Zeckz­er, Dirk and Mid­den­dorf, Mar­tin and Scheuer­mann, Gerik},
book­ti­tle = {Recent Advances in the The­o­ry and Appli­ca­tion of Fit­ness Land­scapes},
edi­tor = {Richter, Hen­drik and Engel­brecht, Andries},
key­words = {land­scape},
pages = {487–507},
pub­lish­er = {Springer Berlin Hei­del­berg},
series = {Emer­gence, Com­plex­i­ty and Com­pu­ta­tion},
title = {Visu­al Analy­sis of Dis­crete Par­ti­cle Swarm Opti­miza­tion Using Fit­ness Land­scapes},
vol­ume = 6,
year = 2014
}

@incollection{bin2014comparing,
author = {Bin, Simon and Volke, Sebas­t­ian and Scheuer­mann, Gerik and Mid­den­dorf, Mar­tin},
book­ti­tle = {The­o­ry and Prac­tice of Nat­ur­al Com­put­ing},
edi­tor = {Dediu, Adri­an-Horia and Lozano, Manuel and Mart{\’\i}n‑Vide, Car­los},
key­words = {land­scape},
pages = {47–58},
pub­lish­er = {Springer Inter­na­tion­al Pub­lish­ing},
series = {Lec­ture Notes in Com­put­er Sci­ence},
title = {Com­par­ing the Opti­miza­tion Behav­iour of Heuris­tics with Topol­o­gy Based Visu­al­iza­tion},
vol­ume = 8890,
year = 2014
}