{"id":"https://openalex.org/W1992994083","doi":"https://doi.org/10.1145/1807167.1807254","title":"ONDUX","display_name":"ONDUX","publication_year":2010,"publication_date":"2010-06-06","ids":{"openalex":"https://openalex.org/W1992994083","doi":"https://doi.org/10.1145/1807167.1807254","mag":"1992994083"},"language":"en","primary_location":{"id":"doi:10.1145/1807167.1807254","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807254","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":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":false,"raw_author_name":"Eli Cortez","raw_affiliation_strings":["Universidade Federal do Amazonas, Manaus, Brazil","Universidade Federal do Amazonas, Manaus, Brazil#TAB#"],"raw_orcid":null,"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#"],"raw_orcid":null,"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/A5046370637","display_name":"Marcos Andr\u00e9 Gon\u00e7alves","orcid":"https://orcid.org/0000-0002-2075-3363"},"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":"Marcos Andr\u00e9 Gon\u00e7alves","raw_affiliation_strings":["Universidade Federal de Minas Gerais, Belo Horizonte, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"last","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#"],"raw_orcid":null,"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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":15.6998,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.9878749,"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":"807","last_page":"818"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9986000061035156,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8191437721252441},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5920013189315796},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5706000924110413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.540494978427887},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.530898928642273},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.4844922721385956},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4713893532752991},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.46701911091804504},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46217837929725647},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4587550163269043},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4575570821762085},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43183523416519165},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.4310573935508728},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35296499729156494},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3305583596229553},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32021069526672363}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8191437721252441},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5920013189315796},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5706000924110413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.540494978427887},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.530898928642273},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4844922721385956},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4713893532752991},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.46701911091804504},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46217837929725647},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4587550163269043},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4575570821762085},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43183523416519165},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.4310573935508728},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35296499729156494},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3305583596229553},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32021069526672363},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1807167.1807254","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1807167.1807254","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"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7599999904632568}],"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/W1494141893","https://openalex.org/W1981791873","https://openalex.org/W2020539781","https://openalex.org/W2029873015","https://openalex.org/W2040217811","https://openalex.org/W2107008379","https://openalex.org/W2107726111","https://openalex.org/W2108126629","https://openalex.org/W2111071245","https://openalex.org/W2124410446","https://openalex.org/W2127484150","https://openalex.org/W2145948275","https://openalex.org/W2147880316","https://openalex.org/W2151406030","https://openalex.org/W2157026227","https://openalex.org/W2159080219","https://openalex.org/W2913389685","https://openalex.org/W4298193390","https://openalex.org/W6676007687","https://openalex.org/W6682452324"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2024136090","https://openalex.org/W3203657119","https://openalex.org/W4286952720"],"abstract_inverted_index":{"Information":[0,55],"extraction":[1,117],"by":[2,165],"text":[3],"segmentation":[4],"(IETS)":[5],"applies":[6],"to":[7,77,114,147,151],"cases":[8],"in":[9,17,22,42,80,160,177],"which":[10,178],"data":[11,76],"values":[12,132],"of":[13,86,101,107,118,130,156],"interest":[14],"are":[15],"organized":[16],"implicit":[18],"semi-structured":[19],"records":[20],"available":[21,73],"textual":[23,172],"sources":[24,173],"(e.g.":[25],"postal":[26],"addresses,":[27],"bibliographic":[28],"information,":[29],"ads).":[30],"It":[31],"is":[32,111,180],"an":[33],"important":[34],"practical":[35],"problem":[36],"that":[37,125],"has":[38],"been":[39],"frequently":[40],"addressed":[41],"the":[43,81,116,166],"recent":[44],"literature.":[45],"In":[46],"this":[47,108],"paper":[48],"we":[49,93,169],"introduce":[50],"ONDUX":[51,69,152,179],"(On":[52],"Demand":[53],"Unsupervised":[54],"Extraction),":[56],"a":[57,87,122,144,153,183],"new":[58],"unsupervised":[59,66],"probabilistic":[60],"approach":[61],"for":[62],"IETS.":[63],"As":[64],"other":[65,91],"IETS":[67,185],"approaches,":[68,92],"relies":[70],"on":[71,74,95],"information":[72],"pre-existing":[75],"associate":[78],"segments":[79],"input":[82],"string":[83],"with":[84,139,171,182],"attributes":[85,120],"given":[88],"domain.":[89],"Unlike":[90],"rely":[94],"very":[96],"effective":[97],"matching":[98,109],"strategies":[99],"instead":[100],"explicit":[102],"learning":[103],"strategies.":[104],"The":[105],"effectiveness":[106],"strategy":[110],"also":[112],"exploited":[113],"disambiguate":[115],"certain":[119],"through":[121],"reinforcement":[123],"step":[124],"explores":[126],"sequencing":[127],"and":[128,158],"positioning":[129],"attribute":[131],"directly":[133],"learned":[134],"on-demand":[135],"from":[136,174],"test":[137],"data,":[138],"no":[140],"previous":[141],"human-driven":[142],"training,":[143],"feature":[145],"unique":[146],"ONDUX.":[148],"This":[149],"assigns":[150],"high":[154],"degree":[155],"flexibility":[157],"results":[159],"superior":[161],"effectiveness,":[162],"as":[163],"demonstrated":[164],"experimental":[167],"evaluation":[168],"report":[170],"different":[175],"domains,":[176],"compared":[181],"state-of-art":[184],"approach.":[186]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2016-06-24T00:00:00"}