{"id":"https://openalex.org/W2029182001","doi":"https://doi.org/10.14778/2367502.2367524","title":"Exploiting evidence from unstructured data to enhance master data management","display_name":"Exploiting evidence from unstructured data to enhance master data management","publication_year":2012,"publication_date":"2012-08-01","ids":{"openalex":"https://openalex.org/W2029182001","doi":"https://doi.org/10.14778/2367502.2367524","mag":"2029182001"},"language":"en","primary_location":{"id":"doi:10.14778/2367502.2367524","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2367502.2367524","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://sites.google.com/site/deepakp7/publications/vldb12.pdf?attredirects=0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109148692","display_name":"K. Narasimha Murthy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Karin Murthy","raw_affiliation_strings":["IBM Research - India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065031367","display_name":"Prasad Deshpande","orcid":"https://orcid.org/0000-0001-6389-533X"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prasad M. Deshpande","raw_affiliation_strings":["IBM Research - India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041736588","display_name":"Atreyee Dey","orcid":"https://orcid.org/0000-0001-6635-7094"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Atreyee Dey","raw_affiliation_strings":["IBM Research - India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013338700","display_name":"Ramanujam Halasipuram","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ramanujam Halasipuram","raw_affiliation_strings":["IBM Research - India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047987914","display_name":"Mukesh Mohania","orcid":"https://orcid.org/0000-0003-4429-1412"},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mukesh Mohania","raw_affiliation_strings":["IBM Research - India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113740386","display_name":"P Deepak","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"P. Deepak","raw_affiliation_strings":["IBM Research - India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research - India","institution_ids":["https://openalex.org/I4210103279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059438505","display_name":"Jennifer L. Reed","orcid":"https://orcid.org/0000-0001-7854-6220"},"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":"Jennifer Reed","raw_affiliation_strings":["IBM Software Group","IBM Software Group,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Software Group","institution_ids":[]},{"raw_affiliation_string":"IBM Software Group,","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054703740","display_name":"Scott Schumacher","orcid":null},"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":"Scott Schumacher","raw_affiliation_strings":["IBM Software Group","IBM Software Group,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Software Group","institution_ids":[]},{"raw_affiliation_string":"IBM Software Group,","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8423,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.90444799,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"5","issue":"12","first_page":"1862","last_page":"1873"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":1.0,"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":1.0,"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":0.9976999759674072,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9961000084877014,"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/unstructured-data","display_name":"Unstructured data","score":0.8670787811279297},{"id":"https://openalex.org/keywords/master-data","display_name":"Master data","score":0.786629855632782},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7464178204536438},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.704649806022644},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.47465139627456665},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.461098313331604},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.34004825353622437},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.2919228672981262},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.2743745446205139}],"concepts":[{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.8670787811279297},{"id":"https://openalex.org/C61871575","wikidata":"https://www.wikidata.org/wiki/Q384093","display_name":"Master data","level":2,"score":0.786629855632782},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7464178204536438},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.704649806022644},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.47465139627456665},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.461098313331604},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.34004825353622437},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2919228672981262},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2743745446205139},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.14778/2367502.2367524","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2367502.2367524","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:pure.qub.ac.uk/portal:publications/601e24da-a580-4efe-aaba-e75940a84aa8","is_oa":true,"landing_page_url":"https://pure.qub.ac.uk/en/publications/601e24da-a580-4efe-aaba-e75940a84aa8","pdf_url":"https://sites.google.com/site/deepakp7/publications/vldb12.pdf?attredirects=0","source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Murthy, K, Deshpande, P, Dey, A, Halasipuram, R, Mohania, M, Padmanabhan, D, Reed, J & Schumacher, S 2012, 'Exploiting evidence from unstructured data to enhance master data management', Proceedings of the VLDB Endowment, vol. 5, no. 12, pp. 1862-1873. < https://sites.google.com/site/deepakp7/publications/vldb12.pdf?attredirects=0 >","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.470.5740","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.470.5740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://vldb.org/pvldb/vol5/p1862_karinmurthy_vldb2012.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:pure.qub.ac.uk/portal:publications/601e24da-a580-4efe-aaba-e75940a84aa8","is_oa":true,"landing_page_url":"https://pure.qub.ac.uk/en/publications/601e24da-a580-4efe-aaba-e75940a84aa8","pdf_url":"https://sites.google.com/site/deepakp7/publications/vldb12.pdf?attredirects=0","source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Murthy, K, Deshpande, P, Dey, A, Halasipuram, R, Mohania, M, Padmanabhan, D, Reed, J & Schumacher, S 2012, 'Exploiting evidence from unstructured data to enhance master data management', Proceedings of the VLDB Endowment, vol. 5, no. 12, pp. 1862-1873. < https://sites.google.com/site/deepakp7/publications/vldb12.pdf?attredirects=0 >","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.41999998688697815},{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2029182001.pdf","grobid_xml":"https://content.openalex.org/works/W2029182001.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W1647671624","https://openalex.org/W1975842046","https://openalex.org/W2044520606","https://openalex.org/W2048468185","https://openalex.org/W2073471108","https://openalex.org/W2098720114","https://openalex.org/W2099370490","https://openalex.org/W2108126629","https://openalex.org/W2108991785","https://openalex.org/W2117062793","https://openalex.org/W2123241698","https://openalex.org/W2123561513","https://openalex.org/W2139379105","https://openalex.org/W2139660688","https://openalex.org/W2149997683","https://openalex.org/W2158188757","https://openalex.org/W2164806297","https://openalex.org/W2169940602","https://openalex.org/W2399675425","https://openalex.org/W2913389685","https://openalex.org/W6644237259","https://openalex.org/W6712897592"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2357241418","https://openalex.org/W2086064646","https://openalex.org/W2119135658","https://openalex.org/W2115485936","https://openalex.org/W2153015554","https://openalex.org/W3022131925","https://openalex.org/W2218797720","https://openalex.org/W2029182001","https://openalex.org/W2187434889"],"abstract_inverted_index":{"Master":[0,135],"data":[1,5,9,36,51,67,73,168],"management":[2],"(MDM)":[3],"integrates":[4],"from":[6,34,64,71,96,145,166],"multiple":[7],"structured":[8,66],"sources":[10,52,169],"and":[11,23,45,88,90,117,155],"builds":[12],"a":[13],"consolidated":[14],"360-degree":[15],"view":[16],"of":[17,103,163],"business":[18],"entities":[19,60,84],"such":[20,38],"as":[21,39,78,121],"customers":[22],"products.":[24],"Today's":[25],"MDM":[26,63,75,83,104,115,124,143],"systems":[27],"are":[28,85],"not":[29,99],"prepared":[30],"to":[31,62,81,132],"integrate":[32],"information":[33,56,70,94,165],"unstructured":[35,50,72,167],"sources,":[37],"news":[40],"reports,":[41],"emails,":[42],"call-center":[43],"transcripts,":[44],"chat":[46],"logs.":[47],"However,":[48],"those":[49],"may":[53],"contain":[54],"valuable":[55],"about":[57],"the":[58,65,91,101,161],"same":[59],"known":[61],"sources.":[68],"Integrating":[69],"into":[74,170],"is":[76],"challenging":[77],"textual":[79],"references":[80],"existing":[82],"often":[86],"incomplete":[87],"imprecise":[89],"additional":[92,146],"entity":[93,153],"extracted":[95],"text":[97],"should":[98],"impact":[100],"trustworthiness":[102],"data.":[105],"In":[106],"this":[107],"paper,":[108],"we":[109],"present":[110],"an":[111,130],"architecture":[112],"for":[113,126],"making":[114],"text-aware":[116],"showcase":[118],"its":[119],"implementation":[120],"IBM":[122,133],"Info-Sphere":[123],"Extension":[125],"Unstructured":[127],"Text":[128],"Correlation,":[129],"add-on":[131],"InfoSphere":[134],"Data":[136],"Management":[137],"Standard":[138],"Edition.":[139],"We":[140,158],"highlight":[141],"how":[142],"benefits":[144],"evidence":[147],"found":[148],"in":[149],"documents":[150],"when":[151],"doing":[152],"resolution":[154],"relationship":[156],"discovery.":[157],"experimentally":[159],"demonstrate":[160],"feasibility":[162],"integrating":[164],"MDM.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
