{"id":"https://openalex.org/W3012588391","doi":"https://doi.org/10.1145/3366423.3380039","title":"Natural Key Discovery in Wikipedia Tables","display_name":"Natural Key Discovery in Wikipedia Tables","publication_year":2020,"publication_date":"2020-04-20","ids":{"openalex":"https://openalex.org/W3012588391","doi":"https://doi.org/10.1145/3366423.3380039","mag":"3012588391"},"language":"en","primary_location":{"id":"doi:10.1145/3366423.3380039","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380039","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Web Conference 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3366423.3380039","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011231340","display_name":"Leon Bornemann","orcid":"https://orcid.org/0000-0001-9939-4932"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Leon Bornemann","raw_affiliation_strings":["Hasso Plattner Institute"],"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042896292","display_name":"Tobias Bleifu\u00df","orcid":"https://orcid.org/0009-0006-9517-7707"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Bleifu\u00df","raw_affiliation_strings":["Hasso Plattner Institute"],"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078774287","display_name":"Dmitri V. Kalashnikov","orcid":"https://orcid.org/0009-0002-4180-1384"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dmitri V. Kalashnikov","raw_affiliation_strings":["AT&amp;T Labs - Research"],"affiliations":[{"raw_affiliation_string":"AT&amp;T Labs - Research","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053028480","display_name":"Felix Naumann","orcid":"https://orcid.org/0000-0002-4483-1389"},"institutions":[{"id":"https://openalex.org/I143288331","display_name":"Hasso Plattner Institute","ror":"https://ror.org/058rn5r42","country_code":"DE","type":"facility","lineage":["https://openalex.org/I143288331","https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Felix Naumann","raw_affiliation_strings":["Hasso Plattner Institute"],"affiliations":[{"raw_affiliation_string":"Hasso Plattner Institute","institution_ids":["https://openalex.org/I143288331"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088315797","display_name":"Divesh Srivastava","orcid":"https://orcid.org/0000-0002-7609-9217"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Divesh Srivastava","raw_affiliation_strings":["AT&amp;T Labs-Research"],"affiliations":[{"raw_affiliation_string":"AT&amp;T Labs-Research","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5011231340"],"corresponding_institution_ids":["https://openalex.org/I143288331"],"apc_list":null,"apc_paid":null,"fwci":1.4582,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85554353,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2789","last_page":"2795"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","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"}},"topics":[{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","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"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9947999715805054,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9945999979972839,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.8808118104934692},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8253476619720459},{"id":"https://openalex.org/keywords/encyclopedia","display_name":"Encyclopedia","score":0.7886570692062378},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.7748591899871826},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6894669532775879},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.6731557846069336},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5229883193969727},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4985952377319336},{"id":"https://openalex.org/keywords/relational-database","display_name":"Relational database","score":0.46061065793037415},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4236631691455841},{"id":"https://openalex.org/keywords/table-of-contents","display_name":"Table of contents","score":0.41522416472435},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.19901305437088013}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8808118104934692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8253476619720459},{"id":"https://openalex.org/C148863701","wikidata":"https://www.wikidata.org/wiki/Q5292","display_name":"Encyclopedia","level":2,"score":0.7886570692062378},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.7748591899871826},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6894669532775879},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.6731557846069336},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5229883193969727},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4985952377319336},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.46061065793037415},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4236631691455841},{"id":"https://openalex.org/C68476402","wikidata":"https://www.wikidata.org/wiki/Q1456936","display_name":"Table of contents","level":2,"score":0.41522416472435},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.19901305437088013},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C161191863","wikidata":"https://www.wikidata.org/wiki/Q199655","display_name":"Library science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3366423.3380039","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380039","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Web Conference 2020","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3366423.3380039","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3366423.3380039","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of The Web Conference 2020","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6600000262260437,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W95495802","https://openalex.org/W1721994796","https://openalex.org/W1870305865","https://openalex.org/W1873084716","https://openalex.org/W1969621019","https://openalex.org/W1976022204","https://openalex.org/W1988217119","https://openalex.org/W1996505782","https://openalex.org/W2020022499","https://openalex.org/W2027420911","https://openalex.org/W2066806792","https://openalex.org/W2112129552","https://openalex.org/W2140602286","https://openalex.org/W2159186077","https://openalex.org/W2168846860","https://openalex.org/W2203920328","https://openalex.org/W2244913846","https://openalex.org/W2394595640","https://openalex.org/W2402694377","https://openalex.org/W2529049456","https://openalex.org/W2604250586","https://openalex.org/W2741470040","https://openalex.org/W2762307198","https://openalex.org/W2889133671","https://openalex.org/W2903025523","https://openalex.org/W2946370960","https://openalex.org/W2952611840","https://openalex.org/W2963174348"],"related_works":["https://openalex.org/W2348562996","https://openalex.org/W4387776128","https://openalex.org/W3010321750","https://openalex.org/W4394774294","https://openalex.org/W3159833212","https://openalex.org/W4244686159","https://openalex.org/W3011873497","https://openalex.org/W3007654203","https://openalex.org/W4256318226","https://openalex.org/W4253980046"],"abstract_inverted_index":{"Wikipedia":[0],"is":[1,12,45,69],"the":[2,38],"largest":[3],"encyclopedia":[4],"to":[5,25,35,63,83],"date.":[6],"Scattered":[7],"among":[8],"its":[9],"articles,":[10],"there":[11],"an":[13,64],"enormous":[14],"number":[15],"of":[16,50,60],"tables":[17],"that":[18],"contain":[19],"structured,":[20],"relational":[21],"information.":[22],"In":[23],"contrast":[24],"database":[26],"tables,":[27],"these":[28],"webtables":[29],"lack":[30],"metadata,":[31,51],"making":[32],"it":[33],"difficult":[34],"automatically":[36],"interpret":[37],"knowledge":[39],"they":[40],"harbor.":[41],"The":[42],"natural":[43,67],"key":[44,57],"a":[46,55],"particularly":[47],"important":[48],"piece":[49],"which":[52],"acts":[53],"as":[54,75],"primary":[56],"and":[58],"consists":[59],"attributes":[61],"inherent":[62],"entity.":[65],"Determining":[66],"keys":[68],"crucial":[70],"for":[71],"many":[72],"tasks,":[73],"such":[74],"information":[76],"integration,":[77],"table":[78],"augmentation,":[79],"or":[80],"tracking":[81],"changes":[82],"entities":[84],"over":[85],"time.":[86]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
