{"id":"https://openalex.org/W2020022499","doi":"https://doi.org/10.1145/2797115.2797118","title":"Matching HTML Tables to DBpedia","display_name":"Matching HTML Tables to DBpedia","publication_year":2015,"publication_date":"2015-07-13","ids":{"openalex":"https://openalex.org/W2020022499","doi":"https://doi.org/10.1145/2797115.2797118","mag":"2020022499"},"language":"en","primary_location":{"id":"doi:10.1145/2797115.2797118","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2797115.2797118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Conference on Web Intelligence, Mining and Semantics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068732489","display_name":"Dominique Ritze","orcid":null},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Dominique Ritze","raw_affiliation_strings":["Data and Web Science Group, University of Mannheim, Mannheim, Germany"],"affiliations":[{"raw_affiliation_string":"Data and Web Science Group, University of Mannheim, Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017822280","display_name":"Oliver Lehmberg","orcid":null},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Oliver Lehmberg","raw_affiliation_strings":["Data and Web Science Group, University of Mannheim, Mannheim, Germany"],"affiliations":[{"raw_affiliation_string":"Data and Web Science Group, University of Mannheim, Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076876024","display_name":"Christian Bizer","orcid":"https://orcid.org/0000-0003-2367-0237"},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Bizer","raw_affiliation_strings":["Data and Web Science Group, University of Mannheim, Mannheim, Germany"],"affiliations":[{"raw_affiliation_string":"Data and Web Science Group, University of Mannheim, Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068732489"],"corresponding_institution_ids":["https://openalex.org/I177802217"],"apc_list":null,"apc_paid":null,"fwci":37.8133,"has_fulltext":false,"cited_by_count":158,"citation_normalized_percentile":{"value":0.99708412,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11719","display_name":"Data Quality and Management","score":0.9976999759674072,"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/T10028","display_name":"Topic Modeling","score":0.996999979019165,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.8188062310218811},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6970797777175903},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.6843167543411255},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5764032006263733},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.5291301012039185},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.4962497353553772},{"id":"https://openalex.org/keywords/schema-matching","display_name":"Schema matching","score":0.47914665937423706},{"id":"https://openalex.org/keywords/row","display_name":"Row","score":0.45859968662261963},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3356451392173767},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3164348602294922},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2803053855895996},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.14886882901191711},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1217258870601654}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8188062310218811},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6970797777175903},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.6843167543411255},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5764032006263733},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.5291301012039185},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.4962497353553772},{"id":"https://openalex.org/C2777327318","wikidata":"https://www.wikidata.org/wiki/Q1408390","display_name":"Schema matching","level":3,"score":0.47914665937423706},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.45859968662261963},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3356451392173767},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3164348602294922},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2803053855895996},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.14886882901191711},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1217258870601654},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2797115.2797118","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2797115.2797118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th International Conference on Web Intelligence, Mining and Semantics","raw_type":"proceedings-article"},{"id":"pmh:oai:ub-madoc.bib.uni-mannheim.de:39487","is_oa":false,"landing_page_url":"http://ub-madoc.bib.uni-mannheim.de/39487/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196315","display_name":"MADOC (University of Mannheim)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177802217","host_organization_name":"University of Mannheim","host_organization_lineage":["https://openalex.org/I177802217"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W20290297","https://openalex.org/W64481094","https://openalex.org/W77414827","https://openalex.org/W1495062271","https://openalex.org/W1552847225","https://openalex.org/W1597082186","https://openalex.org/W1945264926","https://openalex.org/W1969621019","https://openalex.org/W1996505782","https://openalex.org/W2016753842","https://openalex.org/W2022166150","https://openalex.org/W2035274534","https://openalex.org/W2092364718","https://openalex.org/W2108223890","https://openalex.org/W2111869785","https://openalex.org/W2133134975","https://openalex.org/W2151803977","https://openalex.org/W2157311147","https://openalex.org/W2163041183","https://openalex.org/W2182907248","https://openalex.org/W6602554808"],"related_works":["https://openalex.org/W4281971614","https://openalex.org/W2471940468","https://openalex.org/W147534183","https://openalex.org/W4226075635","https://openalex.org/W1528218860","https://openalex.org/W2406112091","https://openalex.org/W2125859764","https://openalex.org/W2014400548","https://openalex.org/W2029826694","https://openalex.org/W2016247499"],"abstract_inverted_index":{"Millions":[0],"of":[1,75,96,106,166,187,191,220,227,235],"HTML":[2,56,97,131,196],"tables":[3,18,57,197],"containing":[4],"structured":[5],"data":[6,50],"can":[7],"be":[8,60,81],"found":[9],"on":[10,130],"the":[11,37,55,63,76,86,94,116,122,137,144,150,164,184,206],"Web.":[12],"With":[13],"their":[14],"wide":[15],"coverage,":[16],"these":[17],"are":[19,153],"potentially":[20],"very":[21],"useful":[22],"for":[23,44,51,90,183],"filling":[24],"missing":[25],"values":[26],"and":[27,72,92,110,121,176,194,229],"extending":[28],"cross-domain":[29,200],"knowledge":[30,52,64,77,100,124,134,145,201],"bases":[31],"such":[32],"as":[33,147,149],"DBpedia,":[34],"YAGO,":[35],"or":[36],"Google":[38],"Knowledge":[39],"Graph.":[40],"As":[41],"a":[42,218,225,233],"prerequisite":[43],"being":[45],"able":[46],"to":[47,59,80,99,133,162],"use":[48,185],"table":[49,70,98,132],"base":[53,78,101,135],"extension,":[54],"need":[58,79],"matched":[61],"with":[62,217,224,232],"base,":[65,146],"meaning":[66],"that":[67,211],"correspondences":[68,114,216,223,231],"between":[69,115],"rows/columns":[71],"entities/schema":[73],"elements":[74],"found.":[82],"This":[83],"paper":[84],"presents":[85],"T2D":[87,104,207],"gold":[88,151,157,208],"standard":[89,152,158,209],"measuring":[91],"comparing":[93],"performance":[95,165],"matching":[102,171,188],"systems.":[103],"consists":[105],"8":[107],"700":[108],"schema-level":[109],"26":[111],"100":[112],"entity-level":[113],"WebDataCommons":[117],"Web":[118,138],"Tables":[119,139],"Corpus":[120,140],"DBpedia":[123],"base.":[125],"In":[126],"contrast":[127],"related":[128],"work":[129],"matching,":[136],"(147":[141],"million":[142],"tables),":[143],"well":[148],"publicly":[154],"available.":[155],"The":[156,203],"is":[159,181],"used":[160],"afterward":[161],"evaluate":[163],"T2K":[167,179,212],"Match,":[168],"an":[169],"iterative":[170],"method":[172],"which":[173],"combines":[174],"schema":[175],"instance":[177],"matching.":[178],"Match":[180,213],"designed":[182],"case":[186],"large":[189,199],"quantities":[190],"mostly":[192],"small":[193],"narrow":[195],"against":[198],"bases.":[202],"evaluation":[204],"using":[205],"shows":[210],"discovers":[214],"table-to-class":[215],"precision":[219,226,234],"94%,":[221],"row-to-entity":[222],"90%,":[228],"column-to-property":[230],"77%.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":27},{"year":2019,"cited_by_count":27},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}