{"id":"https://openalex.org/W2134755874","doi":"https://doi.org/10.1145/1807167.1807211","title":"Automatically incorporating new sources in keyword search-based data integration","display_name":"Automatically incorporating new sources in keyword search-based data integration","publication_year":2010,"publication_date":"2010-06-06","ids":{"openalex":"https://openalex.org/W2134755874","doi":"https://doi.org/10.1145/1807167.1807211","mag":"2134755874"},"language":"en","primary_location":{"id":"doi:10.1145/1807167.1807211","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.upenn.edu/bitstreams/b389bc10-80d7-48b1-bcaf-600180d6881b/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033696194","display_name":"Partha Talukdar","orcid":"https://orcid.org/0000-0001-8825-589X"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Partha Pratim Talukdar","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063822723","display_name":"Zachary G. Ives","orcid":"https://orcid.org/0000-0001-7527-2957"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zachary G. Ives","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044708805","display_name":"Fernando Pereira","orcid":"https://orcid.org/0000-0001-6100-947X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fernando Pereira","raw_affiliation_strings":["Google, Inc., Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5033696194"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":11.1716,"has_fulltext":true,"cited_by_count":53,"citation_normalized_percentile":{"value":0.98401477,"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":"387","last_page":"398"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9994000196456909,"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":0.9994000196456909,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9984999895095825,"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":0.7408974170684814},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.7337967753410339},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6361196041107178},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5658847689628601},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4747883677482605},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.46314144134521484},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.33938127756118774},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2620463967323303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.07552370429039001}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7408974170684814},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.7337967753410339},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6361196041107178},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5658847689628601},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4747883677482605},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.46314144134521484},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33938127756118774},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2620463967323303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.07552370429039001},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1807167.1807211","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2010 ACM SIGMOD International Conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.upenn.edu:cis_papers-1661","is_oa":true,"landing_page_url":"https://repository.upenn.edu/cis_papers/622","pdf_url":"https://repository.upenn.edu/bitstreams/b389bc10-80d7-48b1-bcaf-600180d6881b/download","source":{"id":"https://openalex.org/S4306402083","display_name":"ScholarlyCommons (University of Pennsylvania)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79576946","host_organization_name":"University of Pennsylvania","host_organization_lineage":["https://openalex.org/I79576946"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Departmental Papers (CIS)","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.182.1356","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.182.1356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.talukdar.net/papers/auto-integrate_sigmod2010.pdf","raw_type":"text"},{"id":"pmh:oai:repository.upenn.edu:20.500.14332/6687","is_oa":false,"landing_page_url":"https://repository.upenn.edu/handle/20.500.14332/6687","pdf_url":null,"source":{"id":"https://openalex.org/S4377196331","display_name":"Scholarly Commons (University of Pennsylvania)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79576946","host_organization_name":"University of Pennsylvania","host_organization_lineage":["https://openalex.org/I79576946"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"published","raw_type":"Presentation"}],"best_oa_location":{"id":"pmh:oai:repository.upenn.edu:cis_papers-1661","is_oa":true,"landing_page_url":"https://repository.upenn.edu/cis_papers/622","pdf_url":"https://repository.upenn.edu/bitstreams/b389bc10-80d7-48b1-bcaf-600180d6881b/download","source":{"id":"https://openalex.org/S4306402083","display_name":"ScholarlyCommons (University of Pennsylvania)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79576946","host_organization_name":"University of Pennsylvania","host_organization_lineage":["https://openalex.org/I79576946"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Departmental Papers (CIS)","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2134755874.pdf","grobid_xml":"https://content.openalex.org/works/W2134755874.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1539585011","https://openalex.org/W1552297528","https://openalex.org/W1597031998","https://openalex.org/W1981585544","https://openalex.org/W2007352552","https://openalex.org/W2008620264","https://openalex.org/W2008896880","https://openalex.org/W2038281398","https://openalex.org/W2051582400","https://openalex.org/W2056021151","https://openalex.org/W2057052429","https://openalex.org/W2059268928","https://openalex.org/W2066636486","https://openalex.org/W2069897123","https://openalex.org/W2084538728","https://openalex.org/W2098388305","https://openalex.org/W2099797738","https://openalex.org/W2108223890","https://openalex.org/W2108572131","https://openalex.org/W2116469285","https://openalex.org/W2116544254","https://openalex.org/W2122483056","https://openalex.org/W2123390832","https://openalex.org/W2123853152","https://openalex.org/W2130878769","https://openalex.org/W2139135093","https://openalex.org/W2139823104","https://openalex.org/W2148738951","https://openalex.org/W2150365753","https://openalex.org/W2153508518","https://openalex.org/W2156454791","https://openalex.org/W2156543375","https://openalex.org/W2157110051","https://openalex.org/W2160218441","https://openalex.org/W2169624745","https://openalex.org/W2171874178","https://openalex.org/W3009009611","https://openalex.org/W3148472308","https://openalex.org/W4232413872","https://openalex.org/W6635649160","https://openalex.org/W6652609139","https://openalex.org/W6680506379","https://openalex.org/W6682435157"],"related_works":["https://openalex.org/W2149537132","https://openalex.org/W2018871932","https://openalex.org/W641279757","https://openalex.org/W370975646","https://openalex.org/W1670566515","https://openalex.org/W4242022592","https://openalex.org/W596972243","https://openalex.org/W4313230280","https://openalex.org/W2126703991","https://openalex.org/W2610897791"],"abstract_inverted_index":{"Scientific":[0,13],"data":[1,10,24,52,84,89],"offers":[2],"some":[3],"of":[4,20,41,64,79,91],"the":[5,39,42,51,76,80,94],"most":[6],"interesting":[7],"challenges":[8],"in":[9,62],"integration":[11],"today.":[12],"fields":[14],"evolve":[15],"rapidly":[16],"and":[17,22,32],"accumulate":[18],"masses":[19],"observational":[21],"experimental":[23],"that":[25,74],"needs":[26],"to":[27,35,93],"be":[28,46,57],"annotated,":[29],"revised,":[30],"interlinked,":[31],"made":[33],"available":[34],"other":[36],"scientists.":[37],"From":[38],"perspective":[40],"user,":[43],"this":[44],"can":[45],"a":[47,72],"major":[48],"headache":[49],"as":[50],"they":[53],"seek":[54],"may":[55],"initially":[56],"spread":[58],"across":[59],"many":[60],"databases":[61],"need":[63],"integration.":[65],"Worse,":[66],"even":[67],"if":[68],"users":[69],"are":[70],"given":[71],"solution":[73],"integrates":[75],"current":[77],"state":[78],"source":[81],"databases,":[82],"new":[83,88],"sources":[85],"appear":[86],"with":[87],"items":[90],"interest":[92],"user.":[95]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":8},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
