{"id":"https://openalex.org/W2001793573","doi":"https://doi.org/10.1145/1772690.1772814","title":"Web-scale knowledge extraction from semi-structured tables","display_name":"Web-scale knowledge extraction from semi-structured tables","publication_year":2010,"publication_date":"2010-04-26","ids":{"openalex":"https://openalex.org/W2001793573","doi":"https://doi.org/10.1145/1772690.1772814","mag":"2001793573"},"language":"en","primary_location":{"id":"doi:10.1145/1772690.1772814","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1772690.1772814","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 conference on World wide web","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/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":true,"raw_author_name":"Eric Crestan","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, CA, USA","Yahoo! Labs., Sunnyvale, CA, USA"],"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/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":"Patrick Pantel","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, CA, USA","Yahoo! Labs., Sunnyvale, CA, USA"],"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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5066954331"],"corresponding_institution_ids":["https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":5.5496,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.95813706,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1081","last_page":"1082"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9847000241279602,"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/T11719","display_name":"Data Quality and Management","score":0.98089998960495,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8276102542877197},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.7544207572937012},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6241675615310669},{"id":"https://openalex.org/keywords/decision-table","display_name":"Decision table","score":0.5152385830879211},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.501307487487793},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.4726095497608185},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4587571620941162},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.4275619685649872},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40930747985839844},{"id":"https://openalex.org/keywords/rough-set","display_name":"Rough set","score":0.1697412133216858},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06976145505905151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8276102542877197},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.7544207572937012},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6241675615310669},{"id":"https://openalex.org/C172967692","wikidata":"https://www.wikidata.org/wiki/Q747762","display_name":"Decision table","level":3,"score":0.5152385830879211},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.501307487487793},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.4726095497608185},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4587571620941162},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.4275619685649872},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40930747985839844},{"id":"https://openalex.org/C111012933","wikidata":"https://www.wikidata.org/wiki/Q3137210","display_name":"Rough set","level":2,"score":0.1697412133216858},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06976145505905151},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1772690.1772814","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1772690.1772814","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 conference on World wide web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1678356000","https://openalex.org/W1988217119","https://openalex.org/W2078206655","https://openalex.org/W2102189859","https://openalex.org/W2108223890","https://openalex.org/W2171743956"],"related_works":["https://openalex.org/W2047835521","https://openalex.org/W64552174","https://openalex.org/W2361933495","https://openalex.org/W2360959806","https://openalex.org/W2370063844","https://openalex.org/W2375755112","https://openalex.org/W2025955965","https://openalex.org/W4286964398","https://openalex.org/W3201074950","https://openalex.org/W2033543900"],"abstract_inverted_index":{"A":[0],"wealth":[1],"of":[2,9,38,46,80,94],"knowledge":[3],"is":[4,85],"encoded":[5],"in":[6,70,88,104],"the":[7,12,36,47,78,81,89,101],"form":[8],"tables":[10,30,57],"on":[11],"World":[13],"Wide":[14],"Web.":[15],"We":[16,34,61],"propose":[17,50],"a":[18,22,43,64,67],"classification":[19],"algorithm":[20],"and":[21,31,49],"rich":[23],"feature":[24],"set":[25],"for":[26,53],"automatically":[27],"recognizing":[28],"layout":[29],"attribute/value":[32,56],"tables.":[33],"report":[35],"frequencies":[37],"these":[39],"table":[40,82,90],"types":[41],"over":[42],"large":[44],"analysis":[45],"Web":[48,96],"open":[51],"challenges":[52],"extracting":[54,71],"from":[55],"semantic":[58,72],"triples":[59],"(knowledge).":[60],"then":[62],"describe":[63],"solution":[65],"to":[66],"key":[68],"problem":[69],"triples:":[73],"protagonist":[74,103],"detection,":[75],"i.e.,":[76],"finding":[77],"subject":[79],"that":[83],"often":[84],"not":[86],"present":[87],"itself.":[91],"In":[92],"79%":[93],"our":[95,98],"tables,":[97],"method":[99],"finds":[100],"correct":[102],"its":[105],"top":[106],"three":[107],"returned":[108],"candidates.":[109]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":5},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}