{"id":"https://openalex.org/W147286453","doi":null,"title":"Navigating Extracted Data with Schema Discovery.","display_name":"Navigating Extracted Data with Schema Discovery.","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W147286453","mag":"147286453"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.104.7631","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.104.7631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://gemo.futurs.inria.fr/events/WebDB2007/Papers/p47.pdf","raw_type":"text"},"volume":null,"type":"article","indexed_in":[],"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/A5039133265","display_name":"Michael Cafarella","orcid":"https://orcid.org/0000-0001-6122-0590","observed_orcids":["https://orcid.org/0000-0001-6122-0590"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Cafarella","raw_affiliation_strings":["University of Washington"],"raw_orcid":"https://orcid.org/0000-0001-6122-0590","affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048204602","display_name":"Dan Mircea Suciu","orcid":"https://orcid.org/0000-0002-4144-0868","observed_orcids":["https://orcid.org/0000-0002-4144-0868"]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Suciu","raw_affiliation_strings":["University of Washington"],"raw_orcid":"https://orcid.org/0000-0002-4144-0868","affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110184338","display_name":"Oren Etzioni","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oren Etzioni","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":8.0424,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.97086726,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.25609999895095825,"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":0.25609999895095825,"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":0.24040000140666962,"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":0.11720000207424164,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/open-information-extraction","display_name":"open information extraction","score":0.984000027179718},{"id":"https://openalex.org/keywords/schema-discovery","display_name":"schema discovery","score":0.8980000019073486},{"id":"https://openalex.org/keywords/relational-database-schema","display_name":"relational database schema","score":0.9240000247955322},{"id":"https://openalex.org/keywords/query-composition","display_name":"query composition","score":0.8230000138282776},{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.3400000035762787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8286798000335693},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.7784223556518555},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6766065359115601},{"id":"https://openalex.org/C150012506","wikidata":"https://www.wikidata.org/wiki/Q6031185","display_name":"Information schema","level":5,"score":0.633930504322052},{"id":"https://openalex.org/C30775581","wikidata":"https://www.wikidata.org/wiki/Q632285","display_name":"Database schema","level":3,"score":0.48981162905693054},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4894603490829468},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.48616310954093933},{"id":"https://openalex.org/C56310702","wikidata":"https://www.wikidata.org/wiki/Q2269281","display_name":"Semi-structured model","level":4,"score":0.4746152460575104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44216835498809814},{"id":"https://openalex.org/C135598885","wikidata":"https://www.wikidata.org/wiki/Q1366302","display_name":"Row","level":2,"score":0.440141886472702},{"id":"https://openalex.org/C148840519","wikidata":"https://www.wikidata.org/wiki/Q1049878","display_name":"Database design","level":2,"score":0.15915066003799438},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.15828028321266174}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.104.7631","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.104.7631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://gemo.futurs.inria.fr/events/WebDB2007/Papers/p47.pdf","raw_type":"text"},{"id":"mag:147286453","doi":null,"is_oa":false,"landing_page_url":"http://ai.cs.washington.edu/www/media/papers/tmp116iOQ.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306420358","display_name":"International Workshop on the Web and Databases","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Workshop on the Web and Databases","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1484413656","https://openalex.org/W1489949474","https://openalex.org/W1493490255","https://openalex.org/W1553019137","https://openalex.org/W1616576116","https://openalex.org/W1787194749","https://openalex.org/W2008896880","https://openalex.org/W2085016361","https://openalex.org/W2102381086","https://openalex.org/W2103436317","https://openalex.org/W2103931177","https://openalex.org/W2115461474","https://openalex.org/W2116493296","https://openalex.org/W2150365753","https://openalex.org/W2150721933","https://openalex.org/W2160196229","https://openalex.org/W2166559705","https://openalex.org/W2294859229","https://openalex.org/W3004540582"],"related_works":["https://openalex.org/W7215035753","https://openalex.org/W1493490255","https://openalex.org/W4389209386","https://openalex.org/W1970187983","https://openalex.org/W7098012212","https://openalex.org/W2182941413","https://openalex.org/W2273897543","https://openalex.org/W3151990698","https://openalex.org/W2174011386","https://openalex.org/W238570764"],"abstract_inverted_index":{"Open":[0],"Information":[1],"Extraction":[2],"(OIE)":[3],"is":[4,54,72],"a":[5,46,64,78,83,95,139],"recently-introduced":[6],"type":[7],"of":[8,16,48,66,172],"information":[9],"extraction":[10,31],"that":[11,70,98,163,179],"extracts":[12],"small":[13],"individual":[14],"pieces":[15],"data":[17,29,185],"from":[18,45],"input":[19,158],"text":[20],"without":[21],"any":[22],"domainspecific":[23],"guidance":[24],"such":[25,74],"as":[26,75,157],"special":[27],"training":[28],"or":[30,81,123,186],"rules.":[32],"For":[33],"example,":[34],"an":[35,131],"OIE":[36,53],"system":[37],"might":[38],"discover":[39],"the":[40,88,91,100,104,118,144],"triple":[41],"Frenzy,":[42],"year,":[43],"1972":[44],"set":[47],"documents":[49,173],"about":[50],"movies.":[51],"Because":[52],"domain-independent,":[55],"it":[56],"promises":[57],"to":[58,90,159],"help":[59],"users":[60],"when":[61,76],"they":[62],"have":[63,113,149],"corpus":[65],"structured":[67],"data,":[68],"but":[69,116],"structure":[71,89],"unknown,":[73],"browsing":[77],"novel":[79],"domain":[80],"formulating":[82],"query.":[84],"We":[85,161],"can":[86,154],"describe":[87],"user":[92],"by":[93],"displaying":[94],"relational":[96,141],"schema":[97,110,134,142],"fits":[99],"extracted":[101,114,145,191],"data.":[102,146,192],"Unfortunately,":[103],"extractions":[105],"do":[106],"not":[107,117],"carry":[108],"full":[109],"information:":[111],"we":[112,128],"values,":[115],"correct":[119],"relations,":[120],"their":[121,124],"rows,":[122],"columns.":[125],"In":[126],"response":[127],"propose":[129],"TGen,":[130],"algorithm":[132],"for":[133,143,182,187],"discovery,":[135],"which":[136,153],"automatically":[137],"derives":[138],"high-quality":[140],"Different":[147],"applications":[148],"different":[150],"schema-design":[151],"requirements,":[152],"be":[155],"encoded":[156],"TGen.":[160],"show":[162],"our":[164],"data-mining":[165],"approach":[166],"runs":[167],"in":[168,177],"minutes":[169],"on":[170],"millions":[171],"while":[174],"still":[175],"resulting":[176],"schemas":[178],"are":[180],"useful":[181],"exploring":[183],"unfamiliar":[184],"composing":[188],"queries":[189],"over":[190],"1.":[193]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}