{"id":"https://openalex.org/W2022760666","doi":"https://doi.org/10.1145/1142473.1142595","title":"Managing information extraction","display_name":"Managing information extraction","publication_year":2006,"publication_date":"2006-06-27","ids":{"openalex":"https://openalex.org/W2022760666","doi":"https://doi.org/10.1145/1142473.1142595","mag":"2022760666"},"language":"en","primary_location":{"id":"doi:10.1145/1142473.1142595","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1142473.1142595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 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/A5110256670","display_name":"AnHai Doan","orcid":null},"institutions":[{"id":"https://openalex.org/I2801919071","display_name":"University of Illinois System","ror":"https://ror.org/05e94g991","country_code":"US","type":"education","lineage":["https://openalex.org/I2801919071"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"AnHai Doan","raw_affiliation_strings":["University of Illinois"],"affiliations":[{"raw_affiliation_string":"University of Illinois","institution_ids":["https://openalex.org/I2801919071"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051301731","display_name":"Raghu Ramakrishnan","orcid":"https://orcid.org/0009-0007-5086-7664"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raghu Ramakrishnan","raw_affiliation_strings":["University of Wisconsin"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010223683","display_name":"Shivakumar Vaithyanathan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shivakumar Vaithyanathan","raw_affiliation_strings":["IBM Research at Almaden"],"affiliations":[{"raw_affiliation_string":"IBM Research at Almaden","institution_ids":["https://openalex.org/I4210085935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110256670"],"corresponding_institution_ids":["https://openalex.org/I2801919071"],"apc_list":null,"apc_paid":null,"fwci":13.2112,"has_fulltext":false,"cited_by_count":83,"citation_normalized_percentile":{"value":0.98960762,"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":"799","last_page":"800"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.968999981880188,"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":0.968999981880188,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9491000175476074,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.906000018119812,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8565675616264343},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.7182276248931885},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6082725524902344},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.5161272287368774},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4915388524532318},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.44843289256095886},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4262462556362152},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35699552297592163},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3246576488018036},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.32413387298583984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8565675616264343},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.7182276248931885},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6082725524902344},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.5161272287368774},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4915388524532318},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.44843289256095886},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4262462556362152},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35699552297592163},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3246576488018036},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32413387298583984},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1142473.1142595","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1142473.1142595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1601083748","https://openalex.org/W2134290612","https://openalex.org/W2016355461","https://openalex.org/W2386938185","https://openalex.org/W4225580798","https://openalex.org/W2068844411","https://openalex.org/W1986386500","https://openalex.org/W2793744252","https://openalex.org/W1516746680","https://openalex.org/W2072284316"],"abstract_inverted_index":{"This":[0],"tutorial":[1],"makes":[2],"the":[3,30,47,51,59,68,74,80,86,97],"case":[4],"for":[5,50,79],"developing":[6],"a":[7],"unified":[8],"framework":[9],"that":[10],"manages":[11],"information":[12,27,63],"extraction":[13,28,64,87,122],"from":[14],"unstructured":[15],"data":[16],"(focusing":[17],"in":[18,29,38,66,85],"particular":[19,67],"on":[20,26],"text).":[21],"We":[22,112],"first":[23],"survey":[24],"research":[25],"database,":[31],"AI,":[32],"NLP,":[33,121],"IR,":[34],"and":[35,57,72,77,82,109],"Web":[36],"communities":[37],"recent":[39],"years.":[40],"Then":[41],"we":[42,90],"discuss":[43],"why":[44],"this":[45],"is":[46],"right":[48],"time":[49],"database":[52],"community":[53],"to":[54,102],"actively":[55],"participate":[56],"address":[58],"problem":[60],"of":[61,70,118],"managing":[62],"(including":[65],"challenges":[69],"maintaining":[71],"querying":[73],"extracted":[75],"information,":[76],"accounting":[78],"imprecision":[81],"uncertainty":[83],"inherent":[84],"process).":[88],"Finally,":[89],"show":[91],"how":[92],"interested":[93],"researchers":[94],"can":[95],"take":[96],"next":[98],"step,":[99],"by":[100],"pointing":[101],"open":[103],"problems,":[104],"available":[105],"datasets,":[106],"applicable":[107],"standards,":[108],"software":[110],"tools.":[111],"do":[113],"not":[114],"assume":[115],"prior":[116],"knowledge":[117],"text":[119],"management,":[120],"techniques,":[123],"or":[124],"machine":[125],"learning.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"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":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
