{"id":"https://openalex.org/W2425367731","doi":"https://doi.org/10.1145/2932194.2932198","title":"Web table column categorisation and profiling","display_name":"Web table column categorisation and profiling","publication_year":2016,"publication_date":"2016-06-17","ids":{"openalex":"https://openalex.org/W2425367731","doi":"https://doi.org/10.1145/2932194.2932198","mag":"2425367731"},"language":"en","primary_location":{"id":"doi:10.1145/2932194.2932198","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2932194.2932198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th International Workshop on Web and Databases","raw_type":"proceedings-article"},"type":"conference-paper","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/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":["University of Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of 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":["University of Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177802217"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9975000023841858,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9855999946594238,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8313651084899902},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5680124163627625},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5549314618110657},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47971171140670776},{"id":"https://openalex.org/keywords/binary-relation","display_name":"Binary relation","score":0.46801838278770447},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.43993791937828064},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4189044237136841},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.353958398103714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2998564839363098},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.28491610288619995},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10796013474464417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8313651084899902},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5680124163627625},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5549314618110657},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47971171140670776},{"id":"https://openalex.org/C65180967","wikidata":"https://www.wikidata.org/wiki/Q130901","display_name":"Binary relation","level":2,"score":0.46801838278770447},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.43993791937828064},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4189044237136841},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.353958398103714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2998564839363098},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.28491610288619995},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10796013474464417},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2932194.2932198","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2932194.2932198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th International Workshop on Web and Databases","raw_type":"proceedings-article"},{"id":"pmh:oai:ub-madoc.bib.uni-mannheim.de:40987","is_oa":false,"landing_page_url":"http://delivery.acm.org/10.1145/2940000/2932198/a4-lehmberg.pdf?ip=134.155.63.203&id=2932198&acc=ACTIVE%20SERVICE&key=2BA2C432AB83DA15%2E33B98ACB330D6FA0%2E4D4702B0C3E38B35%2E4D4702B0C3E38B35&CFID=659325678&CFTOKEN=32825157&__acm__=1472033506_ac45cd983470ea31ac82d13aafebb770","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W102383941","https://openalex.org/W1552847225","https://openalex.org/W1969621019","https://openalex.org/W1996505782","https://openalex.org/W2016753842","https://openalex.org/W2020022499","https://openalex.org/W2092364718","https://openalex.org/W2094625154","https://openalex.org/W2104042955","https://openalex.org/W2108223890","https://openalex.org/W2138556038","https://openalex.org/W2140116426","https://openalex.org/W2151803977","https://openalex.org/W2241277057","https://openalex.org/W2325923789","https://openalex.org/W2338381085","https://openalex.org/W2340354588","https://openalex.org/W2439326083"],"related_works":["https://openalex.org/W4394360958","https://openalex.org/W2948670949","https://openalex.org/W4288047943","https://openalex.org/W4394193569","https://openalex.org/W2156982617","https://openalex.org/W2535940710","https://openalex.org/W2116258248","https://openalex.org/W2950632968","https://openalex.org/W4297958055","https://openalex.org/W2408706506"],"abstract_inverted_index":{"Relational":[0],"tables":[1,38,71,110,143,186,204],"collected":[2],"from":[3,187,193],"HTML":[4],"pages":[5],"(\"web":[6],"tables\")":[7],"are":[8,144,205],"used":[9],"for":[10,29,96,208],"a":[11,47,51,60,73,93,148,170],"variety":[12],"of":[13,25,42,59,64,76,105,137,151,172,184,212],"tasks":[14,31],"including":[15],"table":[16,98],"extension,":[17],"knowledge":[18],"base":[19],"completion,":[20],"and":[21,114,153,192],"data":[22,35],"transformation.":[23],"Most":[24],"the":[26,34,37,40,85,102,112,182,188,199,209],"existing":[27],"algorithms":[28,119],"these":[30,124],"assume":[32],"that":[33,69,107,131,201],"in":[36,109],"has":[39],"form":[41],"binary":[43],"relations,":[44],"i.e.,":[45],"relates":[46],"single":[48,202],"entity":[49],"to":[50,54,117,161,164,197],"value":[52],"or":[53],"another":[55],"entity.":[56],"Our":[57],"exploration":[58],"large":[61,74],"public":[62],"corpus":[63],"web":[65,70,97,142,190,195,203],"tables,":[66],"however,":[67],"shows":[68],"contain":[72,147],"fraction":[75],"non-binary":[77],"relations":[78,106,138],"which":[79,100,120,174],"will":[80],"likely":[81],"be":[82,162],"misinterpreted":[83],"by":[84,180],"state-of-the-art":[86],"algorithms.":[87],"In":[88,159],"this":[89,166],"paper,":[90],"we":[91,168],"propose":[92,169],"categorisation":[94],"scheme":[95],"columns":[99],"distinguishes":[101],"different":[103,125,135,194],"types":[104,136],"appear":[108],"on":[111],"Web":[113],"may":[115],"help":[116],"design":[118],"better":[121],"deal":[122],"with":[123],"types.":[126],"Designing":[127],"an":[128],"automated":[129],"classifier":[130],"can":[132],"distinguish":[133],"between":[134],"is":[139],"non-trivial,":[140],"because":[141],"relatively":[145],"small,":[146],"high":[149],"level":[150],"noise,":[152],"often":[154],"miss":[155],"partial":[156],"key":[157],"values.":[158],"order":[160],"able":[163],"perform":[165],"distinction,":[167],"set":[171],"features":[173],"goes":[175],"beyond":[176],"probabilistic":[177],"functional":[178,213],"dependencies":[179],"using":[181],"union":[183],"multiple":[185],"same":[189],"site":[191],"sites":[196],"overcome":[198],"problem":[200],"too":[206],"small":[207],"reliable":[210],"calculation":[211],"dependencies.":[214]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
