{"id":"https://openalex.org/W2074126326","doi":"https://doi.org/10.1145/2213836.2213912","title":"Automatic web-scale information extraction","display_name":"Automatic web-scale information extraction","publication_year":2012,"publication_date":"2012-05-20","ids":{"openalex":"https://openalex.org/W2074126326","doi":"https://doi.org/10.1145/2213836.2213912","mag":"2074126326"},"language":"en","primary_location":{"id":"doi:10.1145/2213836.2213912","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2213836.2213912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 ACM SIGMOD International Conference on Management of Data","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/A5029571794","display_name":"Philip Bohannon","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":"Philip Bohannon","raw_affiliation_strings":["Yahoo! Research, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Santa Clara, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081323769","display_name":"Nilesh Dalvi","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":"Nilesh Dalvi","raw_affiliation_strings":["Yahoo! Research, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Santa Clara, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047362769","display_name":"Yuval Filmus","orcid":"https://orcid.org/0000-0002-1739-0872"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yuval Filmus","raw_affiliation_strings":["University of Toronto, Toronto, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, Toronto, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021757437","display_name":"Nori Jacoby","orcid":"https://orcid.org/0000-0003-2868-0100"},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nori Jacoby","raw_affiliation_strings":["Yahoo!, Tel Aviv, Israel","Yahoo, Tel Aviv, Israel#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo!, Tel Aviv, Israel","institution_ids":[]},{"raw_affiliation_string":"Yahoo, Tel Aviv, Israel#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109221570","display_name":"Sathiya Keerthi","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":"Sathiya Keerthi","raw_affiliation_strings":["Yahoo! Research, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Santa Clara, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064186354","display_name":"Alok Kirpal","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":"Alok Kirpal","raw_affiliation_strings":["Yahoo! Research, Santa Clara, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Santa Clara, USA","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5029571794"],"corresponding_institution_ids":["https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":12.0793,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.98272856,"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":"609","last_page":"612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9976999759674072,"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":0.9970999956130981,"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":0.7220016717910767},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5729696750640869},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5186495184898376},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5153772234916687},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.425820916891098},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3507288098335266},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.08437421917915344},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.05755069851875305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7220016717910767},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5729696750640869},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5186495184898376},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5153772234916687},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.425820916891098},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3507288098335266},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.08437421917915344},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.05755069851875305},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2213836.2213912","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2213836.2213912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 ACM SIGMOD International Conference on Management of Data","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":20,"referenced_works":["https://openalex.org/W136639676","https://openalex.org/W1493490255","https://openalex.org/W1553019137","https://openalex.org/W1602270052","https://openalex.org/W2023673418","https://openalex.org/W2049711652","https://openalex.org/W2065568440","https://openalex.org/W2079594573","https://openalex.org/W2080132606","https://openalex.org/W2108223890","https://openalex.org/W2115461474","https://openalex.org/W2124943418","https://openalex.org/W2135767707","https://openalex.org/W2137313854","https://openalex.org/W2145007893","https://openalex.org/W2951333348","https://openalex.org/W3015882749","https://openalex.org/W4256361765","https://openalex.org/W6629638141","https://openalex.org/W6633154970"],"related_works":["https://openalex.org/W1788528807","https://openalex.org/W1975174578","https://openalex.org/W104581431","https://openalex.org/W2725657302","https://openalex.org/W2469626427","https://openalex.org/W1561729373","https://openalex.org/W2393978999","https://openalex.org/W1548492051","https://openalex.org/W2153799433","https://openalex.org/W1545545132"],"abstract_inverted_index":{"In":[0],"this":[1],"demonstration,":[2],"we":[3,8,30],"showcase":[4],"the":[5,37,45],"technologies":[6],"that":[7],"are":[9],"building":[10],"at":[11],"Yahoo!":[12],"for":[13],"Web-scale":[14],"Information":[15],"Extraction.":[16],"Given":[17],"any":[18],"new":[19],"Website,":[20],"containing":[21],"semi-structured":[22],"information":[23,43],"about":[24],"a":[25],"pre-specified":[26],"set":[27],"of":[28],"schemas,":[29],"show":[31],"how":[32],"to":[33],"populate":[34],"objects":[35],"in":[36],"corresponding":[38],"schema":[39],"by":[40],"automatically":[41],"extracting":[42],"from":[44],"Website.":[46]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}