{"id":"https://openalex.org/W2093752301","doi":"https://doi.org/10.1145/1989323.1989380","title":"Joint unsupervised structure discovery and information extraction","display_name":"Joint unsupervised structure discovery and information extraction","publication_year":2011,"publication_date":"2011-06-12","ids":{"openalex":"https://openalex.org/W2093752301","doi":"https://doi.org/10.1145/1989323.1989380","mag":"2093752301"},"language":"en","primary_location":{"id":"doi:10.1145/1989323.1989380","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989323.1989380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 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/A5046842171","display_name":"Eli Cortez","orcid":"https://orcid.org/0000-0003-4010-5854"},"institutions":[{"id":"https://openalex.org/I62885914","display_name":"Universidade Federal do Amazonas","ror":"https://ror.org/02263ky35","country_code":"BR","type":"education","lineage":["https://openalex.org/I62885914"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Eli Cortez","raw_affiliation_strings":["Universidade Federal do Amazonas, Manaus, Brazil","Universidade Federal do Amazonas, Manaus, Brazil#TAB#"],"affiliations":[{"raw_affiliation_string":"Universidade Federal do Amazonas, Manaus, Brazil","institution_ids":["https://openalex.org/I62885914"]},{"raw_affiliation_string":"Universidade Federal do Amazonas, Manaus, Brazil#TAB#","institution_ids":["https://openalex.org/I62885914"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086014975","display_name":"Daniel Oliveira","orcid":"https://orcid.org/0000-0002-1597-1622"},"institutions":[{"id":"https://openalex.org/I62885914","display_name":"Universidade Federal do Amazonas","ror":"https://ror.org/02263ky35","country_code":"BR","type":"education","lineage":["https://openalex.org/I62885914"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Daniel Oliveira","raw_affiliation_strings":["Universidade Federal do Amazonas, Manaus, Brazil","Universidade Federal do Amazonas, Manaus, Brazil#TAB#"],"affiliations":[{"raw_affiliation_string":"Universidade Federal do Amazonas, Manaus, Brazil","institution_ids":["https://openalex.org/I62885914"]},{"raw_affiliation_string":"Universidade Federal do Amazonas, Manaus, Brazil#TAB#","institution_ids":["https://openalex.org/I62885914"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015763962","display_name":"Altigran S. da Silva","orcid":null},"institutions":[{"id":"https://openalex.org/I62885914","display_name":"Universidade Federal do Amazonas","ror":"https://ror.org/02263ky35","country_code":"BR","type":"education","lineage":["https://openalex.org/I62885914"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Altigran S. da Silva","raw_affiliation_strings":["Universidade Federal do Amazonas, Manaus, Brazil","Universidade Federal do Amazonas, Manaus, Brazil#TAB#"],"affiliations":[{"raw_affiliation_string":"Universidade Federal do Amazonas, Manaus, Brazil","institution_ids":["https://openalex.org/I62885914"]},{"raw_affiliation_string":"Universidade Federal do Amazonas, Manaus, Brazil#TAB#","institution_ids":["https://openalex.org/I62885914"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015781017","display_name":"Edleno Silva de Moura","orcid":"https://orcid.org/0000-0002-7860-9575"},"institutions":[{"id":"https://openalex.org/I62885914","display_name":"Universidade Federal do Amazonas","ror":"https://ror.org/02263ky35","country_code":"BR","type":"education","lineage":["https://openalex.org/I62885914"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Edleno S. de Moura","raw_affiliation_strings":["Universidade Federal do Amazonas, Manaus, Brazil","Universidade Federal do Amazonas, Manaus, Brazil#TAB#"],"affiliations":[{"raw_affiliation_string":"Universidade Federal do Amazonas, Manaus, Brazil","institution_ids":["https://openalex.org/I62885914"]},{"raw_affiliation_string":"Universidade Federal do Amazonas, Manaus, Brazil#TAB#","institution_ids":["https://openalex.org/I62885914"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045978751","display_name":"Alberto H. F. Laender","orcid":"https://orcid.org/0000-0001-5032-2233"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Alberto H.F. Laender","raw_affiliation_strings":["Universidade Federal de Minas Gerais, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5046842171"],"corresponding_institution_ids":["https://openalex.org/I62885914"],"apc_list":null,"apc_paid":null,"fwci":8.8674,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.97391753,"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":"541","last_page":"552"},"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/T11719","display_name":"Data Quality and Management","score":0.9965000152587891,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9957000017166138,"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/computer-science","display_name":"Computer science","score":0.8282461166381836},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.693099856376648},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5571333765983582},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5300682783126831},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5286992788314819},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.5265253782272339},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.520382285118103},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4890947937965393},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.48089170455932617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41692161560058594},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.06473422050476074}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8282461166381836},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.693099856376648},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5571333765983582},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5300682783126831},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5286992788314819},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.5265253782272339},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.520382285118103},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4890947937965393},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.48089170455932617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41692161560058594},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.06473422050476074},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1989323.1989380","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1989323.1989380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 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":21,"referenced_works":["https://openalex.org/W236085609","https://openalex.org/W1981791873","https://openalex.org/W1992994083","https://openalex.org/W1995875735","https://openalex.org/W2020539781","https://openalex.org/W2029873015","https://openalex.org/W2035015991","https://openalex.org/W2041404167","https://openalex.org/W2048468185","https://openalex.org/W2059756710","https://openalex.org/W2067416210","https://openalex.org/W2108126629","https://openalex.org/W2124410446","https://openalex.org/W2128836931","https://openalex.org/W2145948275","https://openalex.org/W2147880316","https://openalex.org/W2151406030","https://openalex.org/W2159080219","https://openalex.org/W2162340487","https://openalex.org/W2913389685","https://openalex.org/W2978725006"],"related_works":["https://openalex.org/W1996130883","https://openalex.org/W2748574964","https://openalex.org/W2888483922","https://openalex.org/W2016355461","https://openalex.org/W2386938185","https://openalex.org/W2068844411","https://openalex.org/W1986386500","https://openalex.org/W2793744252","https://openalex.org/W1516746680","https://openalex.org/W2072284316"],"abstract_inverted_index":{"In":[0],"this":[1,127],"paper":[2],"we":[3,158],"present":[4],"JUDIE":[5,65,160],"(Joint":[6],"Unsupervised":[7],"Structure":[8,88],"Discovery":[9,89],"and":[10,36,144,166,192],"Information":[11,46],"Extraction),":[12],"a":[13,62,86,93],"new":[14],"method":[15],"for":[16,111],"automatically":[17],"extracting":[18,193],"semi-structured":[19],"data":[20,53],"records":[21,54,108,191],"in":[22,44,129,155],"the":[23,49,52,58,70,118,130,183,187,190],"form":[24],"of":[25,51,68,72,95,114,136,185,189],"continuous":[26],"text":[27],"(e.g.,":[28],"bibliographic":[29],"citations,":[30],"postal":[31],"addresses,":[32],"classified":[33],"ads,":[34],"etc.)":[35],"having":[37],"no":[38],"explicit":[39],"delimiters":[40],"between":[41],"them.":[42,196],"While":[43],"state-of-the-art":[45,162],"Extraction":[47],"methods":[48,165],"structure":[50,71,145,188],"is":[55,66,83,175],"manually":[56],"supplied":[57],"by":[59,85,109,134],"user":[60,80,172],"as":[61],"training":[63],"step,":[64],"capable":[67],"detecting":[69],"each":[73],"individual":[74,107],"record":[75],"being":[76],"extracted":[77],"without":[78,170],"any":[79,171],"assistance.":[81],"This":[82],"accomplished":[84],"novel":[87],"algorithm":[90,128],"that,":[91,168],"given":[92,119],"sequence":[94],"labels":[96,105],"representing":[97],"attributes":[98],"assigned":[99],"to":[100,125,177],"potential":[101],"values,":[102],"groups":[103],"these":[104],"into":[106],"looking":[110],"frequent":[112],"patterns":[113],"label":[115],"repetitions":[116],"among":[117],"sequence.":[120],"We":[121],"also":[122],"show":[123],"how":[124],"integrate":[126],"information":[131,142,163,194],"extraction":[132,143,164],"process":[133],"means":[135],"successive":[137],"refinement":[138],"steps":[139],"that":[140],"alternate":[141],"discovery.":[146],"Through":[147],"an":[148],"extensively":[149],"experimental":[150],"evaluation":[151],"with":[152,161],"different":[153],"datasets":[154],"distinct":[156],"domains,":[157],"compare":[159],"conclude":[167],"even":[169],"intervention,":[173],"it":[174],"able":[176],"achieve":[178],"high":[179],"quality":[180],"results":[181],"on":[182],"tasks":[184],"discovering":[186],"from":[195]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}