{"id":"https://openalex.org/W2964068340","doi":"https://doi.org/10.48550/arxiv.0909.1783","title":"The Case for a Structured Approach to Managing Unstructured Data","display_name":"The Case for a Structured Approach to Managing Unstructured Data","publication_year":2009,"publication_date":"2009-09-09","ids":{"openalex":"https://openalex.org/W2964068340","doi":"https://doi.org/10.48550/arxiv.0909.1783","mag":"2964068340"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:0909.1783","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/0909.1783","pdf_url":"https://arxiv.org/pdf/0909.1783","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/0909.1783","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110256670","display_name":"AnHai Doan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1304256225","display_name":"University of Wisconsin System","ror":"https://ror.org/03ydkyb10","country_code":"US","type":"education","lineage":["https://openalex.org/I1304256225"]},{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Doan, AnHai","raw_affiliation_strings":["Univ of Wisconsin","University of Wisconsin\u2013Madison, Madison, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ of Wisconsin","institution_ids":["https://openalex.org/I1304256225"]},{"raw_affiliation_string":"University of Wisconsin\u2013Madison, Madison, United States","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017678555","display_name":"Jeffrey F. Naughton","orcid":"https://orcid.org/0000-0002-3710-8096","observed_orcids":["https://orcid.org/0000-0002-3710-8096"]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Naughton, Jeff","raw_affiliation_strings":["Wisconsin","University of Wisconsin\u2013Madison, Madison, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wisconsin","institution_ids":[]},{"raw_affiliation_string":"University of Wisconsin\u2013Madison, Madison, United States","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003448893","display_name":"Akanksha Baid","orcid":"https://orcid.org/0009-0008-4307-9253","observed_orcids":["https://orcid.org/0009-0008-4307-9253"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baid, Akanksha","raw_affiliation_strings":["Wisconsin","IBM (United States), Armonk, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wisconsin","institution_ids":[]},{"raw_affiliation_string":"IBM (United States), Armonk, United States","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112065738","display_name":"Xiaoyong Chai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chai, Xiaoyong","raw_affiliation_strings":["Wisconsin","University of Wisconsin\u2013Madison, Madison, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wisconsin","institution_ids":[]},{"raw_affiliation_string":"University of Wisconsin\u2013Madison, Madison, United States","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405437","display_name":"Fei Chen","orcid":"https://orcid.org/0000-0003-3536-9898","observed_orcids":["https://orcid.org/0000-0003-3536-9898"]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Fei","raw_affiliation_strings":["Wisconsin","University of Wisconsin\u2013Madison, Madison, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wisconsin","institution_ids":[]},{"raw_affiliation_string":"University of Wisconsin\u2013Madison, Madison, United States","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108688659","display_name":"Ting Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Ting","raw_affiliation_strings":["Wisconsin","University of Wisconsin\u2013Madison, Madison, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wisconsin","institution_ids":[]},{"raw_affiliation_string":"University of Wisconsin\u2013Madison, Madison, United States","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chu, Eric","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chu, Eric","raw_affiliation_strings":["Wisconsin","University of Wisconsin\u2013Madison, Madison, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wisconsin","institution_ids":[]},{"raw_affiliation_string":"University of Wisconsin\u2013Madison, Madison, United States","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051215177","display_name":"Pedro DeRose","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DeRose, Pedro","raw_affiliation_strings":["Wisconsin","University of Wisconsin\u2013Madison, Madison, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wisconsin","institution_ids":[]},{"raw_affiliation_string":"University of Wisconsin\u2013Madison, Madison, United States","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110667925","display_name":"Byron J. Gao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I13511017","display_name":"Texas State University","ror":"https://ror.org/05h9q1g27","country_code":"US","type":"education","lineage":["https://openalex.org/I13511017"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gao, Byron","raw_affiliation_strings":["Wisconsin","Texas State University, San Marcos, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wisconsin","institution_ids":[]},{"raw_affiliation_string":"Texas State University, San Marcos, United States","institution_ids":["https://openalex.org/I13511017"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gokhale, Chaitanya","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gokhale, Chaitanya","raw_affiliation_strings":["Wisconsin","University of Wisconsin\u2013Madison, Madison, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wisconsin","institution_ids":[]},{"raw_affiliation_string":"University of Wisconsin\u2013Madison, Madison, United States","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100855262","display_name":"Jiansheng Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huang, Jiansheng","raw_affiliation_strings":["Wisconsin","University of Wisconsin\u2013Madison, Madison, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wisconsin","institution_ids":[]},{"raw_affiliation_string":"University of Wisconsin\u2013Madison, Madison, United States","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110502431","display_name":"Warren Shen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shen, Warren","raw_affiliation_strings":["Wisconsin","University of Wisconsin\u2013Madison, Madison, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wisconsin","institution_ids":[]},{"raw_affiliation_string":"University of Wisconsin\u2013Madison, Madison, United States","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077225988","display_name":"Ba-Quy Vuong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vuong, Ba-Quy","raw_affiliation_strings":["Wisconsin","University of Wisconsin\u2013Madison, Madison, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wisconsin","institution_ids":[]},{"raw_affiliation_string":"University of Wisconsin\u2013Madison, Madison, United States","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.8589000105857849,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.8589000105857849,"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":0.020600000396370888,"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":0.017000000923871994,"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/unstructured-data-management","display_name":"unstructured data management","score":0.8809999823570251},{"id":"https://openalex.org/keywords/data-management","display_name":"data management","score":0.703000009059906},{"id":"https://openalex.org/keywords/structured-approach","display_name":"structured approach","score":0.5440000295639038}],"concepts":[{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.7921667098999023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7389143705368042},{"id":"https://openalex.org/C40077939","wikidata":"https://www.wikidata.org/wiki/Q2336004","display_name":"Semi-structured data","level":3,"score":0.6659945845603943},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5951219797134399},{"id":"https://openalex.org/C5655090","wikidata":"https://www.wikidata.org/wiki/Q192588","display_name":"Relational database","level":2,"score":0.5570211410522461},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.5535955429077148},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5176723003387451},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5017111301422119},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.28797152638435364},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2017447054386139},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.13192281126976013},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:arXiv.org:0909.1783","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/0909.1783","pdf_url":"https://arxiv.org/pdf/0909.1783","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.145.1857","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.145.1857","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-db.cs.wisc.edu/cidr/cidr2009/Paper_110.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.381.1331","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.381.1331","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://pages.cs.wisc.edu/~whshen/papers/cidr09.pdf","raw_type":"text"},{"id":"doi:10.48550/arxiv.0909.1783","doi":"https://doi.org/10.48550/arxiv.0909.1783","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.0909.1783","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2964068340","doi":null,"is_oa":false,"landing_page_url":"http://pages.cs.wisc.edu/~fchen/papers/cidr09.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418070","display_name":"Conference on Innovative Data Systems Research","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":"Conference on Innovative Data Systems Research","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:0909.1783","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/0909.1783","pdf_url":"https://arxiv.org/pdf/0909.1783","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2540700336","https://openalex.org/W3161552744","https://openalex.org/W2066855269","https://openalex.org/W1530703495","https://openalex.org/W4323975459","https://openalex.org/W7096707178","https://openalex.org/W2335232344","https://openalex.org/W1527746910","https://openalex.org/W2089513683","https://openalex.org/W2503261746"],"abstract_inverted_index":{"The":[0],"challenge":[1],"of":[2,97,104,111],"managing":[3,17,78,87,101],"unstructured":[4,88],"data":[5,10],"represents":[6],"perhaps":[7],"the":[8,31,74,94,109],"largest":[9],"management":[11],"opportunity":[12,27],"for":[13],"our":[14,112],"community":[15],"since":[16],"relational":[18,79],"data.":[19,89],"And":[20],"yet":[21],"we":[22,61,64,81],"are":[23],"risking":[24],"letting":[25],"this":[26,59,70,98],"go":[28],"by,":[29],"ceding":[30],"playing":[32],"field":[33],"to":[34,49,67,86,100,108],"other":[35,102],"players,":[36],"ranging":[37],"from":[38],"communities":[39],"such":[40,52],"as":[41,53],"AI,":[42],"KDD,":[43],"IR,":[44],"Web,":[45,48],"and":[46,56,107],"Semantic":[47],"industrial":[50],"players":[51],"Google,":[54],"Yahoo,":[55],"Microsoft.":[57],"In":[58],"essay":[60],"explore":[62],"what":[63],"can":[65],"do":[66],"improve":[68],"upon":[69],"situation.":[71],"Drawing":[72],"on":[73],"lessons":[75],"learned":[76],"while":[77],"data,":[80,106],"outline":[82],"a":[83],"structured":[84],"approach":[85,99],"We":[90],"conclude":[91],"by":[92],"discussing":[93],"potential":[95],"implications":[96],"kinds":[103],"non-relational":[105],"identify":[110],"field.":[113]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2019-07-30T00:00:00"}
