{"id":"https://openalex.org/W6925379511","doi":"https://doi.org/10.18420/btw2023-19","title":"DPQL: The Data Profiling Query Language","display_name":"DPQL: The Data Profiling Query Language","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W6925379511","doi":"https://doi.org/10.18420/btw2023-19"},"language":"en","primary_location":{"id":"doi:10.18420/btw2023-19","is_oa":true,"landing_page_url":"https://doi.org/10.18420/btw2023-19","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.18420/btw2023-19","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Seeger, Marcian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seeger, Marcian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Schmidl, Sebastian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schmidl, Sebastian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Vielhauer, Alexander","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vielhauer, Alexander","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Papenbrock, Thorsten","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Papenbrock, Thorsten","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2929,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.55034504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12592","display_name":"Opinion Dynamics and Social Influence","score":0.07329999655485153,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12592","display_name":"Opinion Dynamics and Social Influence","score":0.07329999655485153,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11883","display_name":"Embodied and Extended Cognition","score":0.04809999838471413,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12469","display_name":"Chaos, Complexity, and Education","score":0.0478999987244606,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.847100019454956},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.4489000141620636},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.400299996137619},{"id":"https://openalex.org/keywords/data-type","display_name":"Data type","score":0.3594000041484833},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.32519999146461487},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.322299987077713}],"concepts":[{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.847100019454956},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8052999973297119},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4832000136375427},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.4489000141620636},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.400299996137619},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39640000462532043},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.3594000041484833},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C175801342","wikidata":"https://www.wikidata.org/wiki/Q1988917","display_name":"Data analysis","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.2581000030040741}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18420/btw2023-19","is_oa":true,"landing_page_url":"https://doi.org/10.18420/btw2023-19","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.18420/btw2023-19","is_oa":true,"landing_page_url":"https://doi.org/10.18420/btw2023-19","pdf_url":null,"source":{"id":"https://openalex.org/S7407052918","display_name":"Gesellschaft f\u00fcr Informatik (GI)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Abstract:":[0],"Data":[1,199],"profiling":[2,40,47,57,67,111,125,142,176,181,225,243,251,278],"describes":[3],"the":[4,43,52,84,101,147,162,170,191,219,223,254,295,299],"activity":[5],"of":[6,19,30,45,55,104,149,186,237,256,269,298,308],"extracting":[7],"implicit":[8],"metadata,":[9],"such":[10],"as":[11],"schema":[12],"descriptions,":[13],"data":[14,20,25,39,46,56,66,86,110,113,124,141,144,175,187,224,250,311],"types,":[15],"and":[16,37,189,197,221,234,240,253,276,288,302],"various":[17,184],"kinds":[18],"dependencies,":[21],"from":[22],"a":[23,173,194,260,267,277,304],"given":[24],"set.":[26],"The":[27,204],"considerable":[28],"amount":[29],"research":[31,58,309],"papers":[32],"about":[33],"novel":[34,174],"metadata":[35],"types":[36,185,239],"ever-faster":[38],"algorithms":[41,68,137],"emphasize":[42],"importance":[44],"in":[48,266,310],"practice.":[49],"Unfortunately,":[50],"though,":[51],"current":[53],"state":[54],"fails":[59],"to":[60,72,90,158,168,208],"address":[61],"practical":[62,102],"application":[63,148,262],"needs:":[64],"Typical":[65],"(i.":[69,77,82,92],"e.,":[70,78,83,93],"challenging":[71],"operate":[73],"structures)":[74],"discover":[75],"all":[76],"too":[79,94],"many)":[80],"minimal":[81],"wrong)":[85],"dependencies":[87,152,188,212],"within":[88],"minutes":[89],"hours":[91],"long).":[95],"Consequently,":[96],"if":[97],"we":[98,107,293],"look":[99],"at":[100],"success":[103],"our":[105],"research,":[106],"find":[108],"that":[109,178,247],"targets":[112,126,143],"cleaning,":[114],"but":[115,129,146,229],"most":[116],"cleaning":[117],"systems":[118],"still":[119],"use":[120],"only":[121,217],"hand-picked":[122],"dependencies;":[123],"query":[127,132,286],"optimization,":[128,287],"hardly":[130],"any":[131],"optimizer":[133],"uses":[134],"modern":[135,180,249],"discovery":[136],"for":[138,153,183,283],"dependency":[139,238],"extraction;":[140],"integration,":[145],"automatically":[150],"discovered":[151],"matching":[154],"purposes":[155],"is":[156],"yet":[157],"be":[159],"shown":[160],"-and":[161],"list":[163],"goes":[164],"on.":[165],"We":[166,245],"aim":[167],"solve":[169],"profiling-and-application-disconnect":[171],"with":[172,193,280],"engine":[177,279],"integrates":[179],"techniques":[182,252],"provides":[190],"applications":[192,207],"versatile,":[195],"intuitive,":[196],"declarative":[198],"Profiling":[200],"Query":[201],"Language":[202],"(DPQL).":[203],"DPQL":[205,300],"enables":[206,231],"specify":[209],"precisely":[210],"what":[211],"are":[213],"needed,":[214],"which":[215],"not":[216],"refines":[218],"results":[220,258],"makes":[222],"process":[226],"more":[227],"accessible":[228],"also":[230],"much":[232],"faster":[233],"(in":[235],"terms":[236],"selections)":[241],"holistic":[242],"runs.":[244],"expect":[246],"integrating":[248],"post-processing":[255],"their":[257],"under":[259],"single":[261],"endpoint":[263],"will":[264],"result":[265],"series":[268],"significant":[270],"algorithmic":[271],"advances,":[272],"new":[273,306],"pruning":[274],"concepts,":[275],"innovative":[281],"components":[282],"workload":[284],"auto-configuration,":[285],"parallelization.":[289],"With":[290],"this":[291],"paper,":[292],"present":[294],"first":[296],"version":[297],"syntax":[301],"introduce":[303],"fundamentally":[305],"line":[307],"profiling.":[312]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}
