{"id":"https://openalex.org/W2138556038","doi":"https://doi.org/10.1145/1935826.1935904","title":"Web-scale table census and classification","display_name":"Web-scale table census and classification","publication_year":2011,"publication_date":"2011-02-01","ids":{"openalex":"https://openalex.org/W2138556038","doi":"https://doi.org/10.1145/1935826.1935904","mag":"2138556038"},"language":"en","primary_location":{"id":"doi:10.1145/1935826.1935904","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth ACM international conference on Web search and data mining","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/A5066954331","display_name":"Eric Crestan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Crestan","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, CA, USA","Yahoo! Labs., Sunnyvale, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Labs., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041476585","display_name":"Patrick Pantel","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Pantel","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6582,"has_fulltext":false,"cited_by_count":79,"citation_normalized_percentile":{"value":0.8484757,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"545","last_page":"554"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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":0.9994000196456909,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9940000176429749,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.98089998960495,"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":0.8042076230049133},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6306859850883484},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6306638121604919},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.6184213161468506},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.54322749376297},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5068870186805725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3930116295814514},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35913586616516113},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3220779299736023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8042076230049133},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6306859850883484},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6306638121604919},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.6184213161468506},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.54322749376297},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5068870186805725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3930116295814514},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35913586616516113},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3220779299736023},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":1,"locations":[{"id":"doi:10.1145/1935826.1935904","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1935826.1935904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fourth ACM international conference on Web search and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W179050280","https://openalex.org/W1554237613","https://openalex.org/W1595439448","https://openalex.org/W1678356000","https://openalex.org/W1988217119","https://openalex.org/W2078206655","https://openalex.org/W2102189859","https://openalex.org/W2108223890","https://openalex.org/W2122695568","https://openalex.org/W2124576009","https://openalex.org/W2135767707","https://openalex.org/W2140602286","https://openalex.org/W2161292215","https://openalex.org/W2171743956","https://openalex.org/W6680646450"],"related_works":["https://openalex.org/W2329500892","https://openalex.org/W28991112","https://openalex.org/W2370726991","https://openalex.org/W2369710579","https://openalex.org/W2545348020","https://openalex.org/W4327728159","https://openalex.org/W2912751582","https://openalex.org/W2130893381","https://openalex.org/W1990856605","https://openalex.org/W3120436346"],"abstract_inverted_index":{"We":[0,43,68,90],"report":[1],"on":[2,11],"a":[3,16,47,73,78,92],"census":[4],"of":[5,8,61,80],"the":[6,12,21,59,81,98],"types":[7],"HTML":[9,52,63],"tables":[10,64],"Web":[13],"according":[14],"to":[15,58],"fine-grained":[17],"classification":[18,54,84],"taxonomy":[19],"describing":[20],"semantics":[22],"that":[23,83],"they":[24],"express.":[25],"For":[26],"each":[27,103],"relational":[28],"table":[29,53,104],"type,":[30],"we":[31],"describe":[32],"open":[33],"challenges":[34],"for":[35,50,102],"extracting":[36],"from":[37],"them":[38],"semantic":[39],"triples,":[40],"i.e.,":[41],"knowledge.":[42],"also":[44],"present":[45,91],"TabEx,":[46],"supervised":[48],"framework":[49],"web-scale":[51],"and":[55,96],"apply":[56],"it":[57],"task":[60],"classifying":[62],"into":[65],"our":[66],"taxonomy.":[67],"show":[69],"empirical":[70],"evidence,":[71],"through":[72],"large-scale":[74],"experimental":[75],"analysis":[76,95],"over":[77],"crawl":[79],"Web,":[82],"accuracy":[85],"significantly":[86],"outperforms":[87],"several":[88],"baselines.":[89],"detailed":[93],"feature":[94],"outline":[97],"most":[99],"salient":[100],"features":[101],"type.":[105]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}