{"id":"https://openalex.org/W4225592814","doi":"https://doi.org/10.1007/978-3-030-78307-5_2","title":"Supporting Semantic Data Enrichment at Scale","display_name":"Supporting Semantic Data Enrichment at Scale","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4225592814","doi":"https://doi.org/10.1007/978-3-030-78307-5_2"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-78307-5_2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-78307-5_2","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-030-78307-5_2.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Technologies and Applications for Big Data Value","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-030-78307-5_2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079768184","display_name":"Michele Ciavotta","orcid":"https://orcid.org/0000-0002-2480-966X"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Michele Ciavotta","raw_affiliation_strings":["Department of Informatics, Systems and Communication, University of Milan\u2013Bicocca, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Systems and Communication, University of Milan\u2013Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067221673","display_name":"Vincenzo Cutrona","orcid":"https://orcid.org/0000-0001-7830-7596"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Vincenzo Cutrona","raw_affiliation_strings":["Department of Informatics, Systems and Communication, University of Milan\u2013Bicocca, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Systems and Communication, University of Milan\u2013Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049354209","display_name":"Flavio De Paoli","orcid":"https://orcid.org/0000-0002-5047-7371"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Flavio De Paoli","raw_affiliation_strings":["Department of Informatics, Systems and Communication, University of Milan\u2013Bicocca, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Systems and Communication, University of Milan\u2013Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064116719","display_name":"Nikolay Nikolov","orcid":"https://orcid.org/0000-0003-3266-0751"},"institutions":[{"id":"https://openalex.org/I173888879","display_name":"SINTEF","ror":"https://ror.org/01f677e56","country_code":"NO","type":"facility","lineage":["https://openalex.org/I173888879"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Nikolay Nikolov","raw_affiliation_strings":["Department of Software and Service Innovation, SINTEF AS, Oslo, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Software and Service Innovation, SINTEF AS, Oslo, Norway","institution_ids":["https://openalex.org/I173888879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065845420","display_name":"Matteo Palmonari","orcid":"https://orcid.org/0000-0002-1801-5118"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Matteo Palmonari","raw_affiliation_strings":["Department of Informatics, Systems and Communication, University of Milan\u2013Bicocca, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Systems and Communication, University of Milan\u2013Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016864296","display_name":"Dumitru Roman","orcid":"https://orcid.org/0000-0001-6397-3705"},"institutions":[{"id":"https://openalex.org/I173888879","display_name":"SINTEF","ror":"https://ror.org/01f677e56","country_code":"NO","type":"facility","lineage":["https://openalex.org/I173888879"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Dumitru Roman","raw_affiliation_strings":["Department of Software and Service Innovation, SINTEF AS, Oslo, Norway"],"affiliations":[{"raw_affiliation_string":"Department of Software and Service Innovation, SINTEF AS, Oslo, Norway","institution_ids":["https://openalex.org/I173888879"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5079768184"],"corresponding_institution_ids":["https://openalex.org/I66752286"],"apc_list":null,"apc_paid":null,"fwci":10.0097,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.98455919,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"39"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9962999820709229,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8258172869682312},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6730254888534546},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.628122091293335},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.569660484790802},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5582712292671204},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5131500363349915},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48881813883781433},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4614924192428589},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4497976005077362},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43507322669029236},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4332420527935028},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.42536303400993347},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.41473355889320374},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.37505197525024414},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36513829231262207},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1475067138671875},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.09286156296730042},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06863361597061157}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8258172869682312},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6730254888534546},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.628122091293335},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.569660484790802},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5582712292671204},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5131500363349915},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48881813883781433},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4614924192428589},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4497976005077362},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43507322669029236},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4332420527935028},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.42536303400993347},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41473355889320374},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.37505197525024414},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36513829231262207},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1475067138671875},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.09286156296730042},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06863361597061157},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-030-78307-5_2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-78307-5_2","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-030-78307-5_2.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Technologies and Applications for Big Data Value","raw_type":"book-chapter"},{"id":"pmh:oai:boa.unimib.it:10281/372742","is_oa":true,"landing_page_url":"http://hdl.handle.net/10281/372742","pdf_url":null,"source":{"id":"https://openalex.org/S4306401259","display_name":"BOA (University of Milano-Bicocca)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66752286","host_organization_name":"University of Milano-Bicocca","host_organization_lineage":["https://openalex.org/I66752286"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":{"id":"doi:10.1007/978-3-030-78307-5_2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-78307-5_2","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-030-78307-5_2.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Technologies and Applications for Big Data Value","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G265104915","display_name":null,"funder_award_id":"EC H2020","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G5980781711","display_name":null,"funder_award_id":"780247","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4225592814.pdf","grobid_xml":"https://content.openalex.org/works/W4225592814.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1993830291","https://openalex.org/W2020022499","https://openalex.org/W2111869785","https://openalex.org/W2275216626","https://openalex.org/W2295276225","https://openalex.org/W2368635037","https://openalex.org/W2398363389","https://openalex.org/W2493970676","https://openalex.org/W2518514431","https://openalex.org/W2546510339","https://openalex.org/W2581324571","https://openalex.org/W2782725803","https://openalex.org/W2792215712","https://openalex.org/W2891222064","https://openalex.org/W2892354435","https://openalex.org/W2913152377","https://openalex.org/W2946369706","https://openalex.org/W2977421310","https://openalex.org/W2980791946","https://openalex.org/W3013698559","https://openalex.org/W3081758821","https://openalex.org/W3110634154","https://openalex.org/W4247564058","https://openalex.org/W4255235742","https://openalex.org/W6679046037","https://openalex.org/W7057339168"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W4244478748","https://openalex.org/W4233347783","https://openalex.org/W2910064364","https://openalex.org/W4255224757"],"abstract_inverted_index":{"Abstract":[0],"Data":[1,104],"enrichment":[2,33,85,99],"is":[3,16],"a":[4,14,50,62,73,102],"critical":[5],"task":[6],"in":[7,12,65,90,140],"the":[8,32,123,126,144,150],"data":[9,37,84,98],"preparation":[10],"process":[11,34,93,128],"which":[13,141],"dataset":[15],"extended":[17],"with":[18,157],"additional":[19],"information":[20],"from":[21,137],"various":[22],"sources":[23],"to":[24,49,121],"perform":[25],"analyses":[26],"or":[27],"add":[28],"meaningful":[29],"context.":[30],"Facilitating":[31],"design":[35],"for":[36],"workers":[38],"and":[39,79,86,117,146],"supporting":[40],"its":[41],"execution":[42],"on":[43,129],"large":[44,130],"datasets":[45,156],"are":[46],"only":[47],"supported":[48],"limited":[51],"extent":[52],"by":[53],"existing":[54],"solutions.":[55],"Harnessing":[56],"semantics":[57],"at":[58],"scale":[59],"can":[60,106],"be":[61,107],"crucial":[63],"factor":[64],"effectively":[66],"addressing":[67],"this":[68,92],"challenge.":[69],"This":[70],"chapter":[71],"presents":[72],"comprehensive":[74],"approach":[75],"covering":[76],"both":[77],"design-":[78],"run-time":[80,147],"aspects":[81],"of":[82,101,125,149],"tabular":[83,110,131],"discusses":[87],"our":[88],"experience":[89],"making":[91],"scalable.":[94],"We":[95],"illustrate":[96],"how":[97],"steps":[100],"Big":[103],"pipeline":[105],"implemented":[108],"via":[109],"transformations":[111],"exploiting":[112],"semantic":[113],"table":[114],"annotation":[115],"methods":[116],"discuss":[118],"techniques":[119],"devised":[120],"support":[122],"enactment":[124],"resulting":[127],"datasets.":[132],"Furthermore,":[133],"we":[134,142],"present":[135],"results":[136],"experimental":[138],"evaluations":[139],"tested":[143],"scalability":[145],"efficiency":[148],"proposed":[151],"cloud-based":[152],"approach,":[153],"enriching":[154],"massive":[155],"promising":[158],"performance.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}