{"id":"https://openalex.org/W2096006132","doi":"https://doi.org/10.1109/dest.2013.6611347","title":"Unstructured data extraction in distributed NoSQL","display_name":"Unstructured data extraction in distributed NoSQL","publication_year":2013,"publication_date":"2013-07-01","ids":{"openalex":"https://openalex.org/W2096006132","doi":"https://doi.org/10.1109/dest.2013.6611347","mag":"2096006132"},"language":"en","primary_location":{"id":"doi:10.1109/dest.2013.6611347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dest.2013.6611347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 7th IEEE International Conference on Digital Ecosystems and Technologies (DEST)","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/A5082276800","display_name":"Richard K. Lomotey","orcid":"https://orcid.org/0000-0002-5215-7806"},"institutions":[{"id":"https://openalex.org/I32625721","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63","country_code":"CA","type":"education","lineage":["https://openalex.org/I32625721"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Richard K. Lomotey","raw_affiliation_strings":["Department of Computer Science, University of Saskatchewan, Saskatoon, SAS, Canada","Department of Computer Science, University of Saskatchewan, Saskatoon, Sk, Canada#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Saskatchewan, Saskatoon, SAS, Canada","institution_ids":["https://openalex.org/I32625721"]},{"raw_affiliation_string":"Department of Computer Science, University of Saskatchewan, Saskatoon, Sk, Canada#TAB#","institution_ids":["https://openalex.org/I32625721"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046273010","display_name":"Ralph Deters","orcid":"https://orcid.org/0000-0001-6703-5839"},"institutions":[{"id":"https://openalex.org/I32625721","display_name":"University of Saskatchewan","ror":"https://ror.org/010x8gc63","country_code":"CA","type":"education","lineage":["https://openalex.org/I32625721"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ralph Deters","raw_affiliation_strings":["Department of Computer Science, University of Saskatchewan, Saskatoon, SAS, Canada","Department of Computer Science, University of Saskatchewan, Saskatoon, Sk, Canada#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Saskatchewan, Saskatoon, SAS, Canada","institution_ids":["https://openalex.org/I32625721"]},{"raw_affiliation_string":"Department of Computer Science, University of Saskatchewan, Saskatoon, Sk, Canada#TAB#","institution_ids":["https://openalex.org/I32625721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.11004947,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"160","last_page":"165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9991999864578247,"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"}},"topics":[{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9991999864578247,"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/T11106","display_name":"Data Management and Algorithms","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9980999827384949,"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/nosql","display_name":"NoSQL","score":0.9326026439666748},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8542541861534119},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.6801497936248779},{"id":"https://openalex.org/keywords/usable","display_name":"USable","score":0.5841840505599976},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.5461439490318298},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.48925185203552246},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4531328082084656},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.44702789187431335},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.43855202198028564},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4024824798107147},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.38179880380630493},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21084293723106384},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1993761658668518}],"concepts":[{"id":"https://openalex.org/C2779599972","wikidata":"https://www.wikidata.org/wiki/Q82231","display_name":"NoSQL","level":3,"score":0.9326026439666748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8542541861534119},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.6801497936248779},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.5841840505599976},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.5461439490318298},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.48925185203552246},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4531328082084656},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.44702789187431335},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.43855202198028564},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4024824798107147},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.38179880380630493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21084293723106384},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1993761658668518}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dest.2013.6611347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dest.2013.6611347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 7th IEEE International Conference on Digital Ecosystems and Technologies (DEST)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W28669376","https://openalex.org/W112729621","https://openalex.org/W1486198364","https://openalex.org/W1490467896","https://openalex.org/W1601717103","https://openalex.org/W1884216778","https://openalex.org/W1920895891","https://openalex.org/W1982769922","https://openalex.org/W2012325806","https://openalex.org/W2021502500","https://openalex.org/W2023628824","https://openalex.org/W2030910246","https://openalex.org/W2064799701","https://openalex.org/W2069140227","https://openalex.org/W2090645789","https://openalex.org/W2111934954","https://openalex.org/W2131728141","https://openalex.org/W2160822901","https://openalex.org/W2183978789","https://openalex.org/W2394309960","https://openalex.org/W2912486915","https://openalex.org/W4240420807","https://openalex.org/W6604608902","https://openalex.org/W6629265943","https://openalex.org/W6635896488","https://openalex.org/W6640164538","https://openalex.org/W6673094781"],"related_works":["https://openalex.org/W2799973158","https://openalex.org/W2419153746","https://openalex.org/W3089119258","https://openalex.org/W2923327995","https://openalex.org/W2518340158","https://openalex.org/W3168508953","https://openalex.org/W2386245213","https://openalex.org/W2019158987","https://openalex.org/W1996324618","https://openalex.org/W1516746680"],"abstract_inverted_index":{"While":[0],"\u201cBig":[1],"data\u201d":[2],"has":[3,73],"brought":[4],"good":[5],"tidings":[6],"in":[7,25,100],"terms":[8,63],"of":[9,93],"easy":[10],"accessibility":[11],"to":[12,61,88,107],"voluminous":[13],"data,":[14],"we":[15,47,81],"are":[16,37],"faced":[17],"with":[18],"challenges":[19],"too.":[20],"The":[21],"existing":[22],"Knowledge":[23],"Discovery":[24],"Database":[26],"(KDD)":[27],"processes":[28],"which":[29,53],"have":[30],"been":[31],"proposed":[32],"for":[33],"schema-oriented":[34],"data":[35,43,66],"sources":[36,67],"no":[38],"longer":[39],"applicable":[40],"since":[41],"todays":[42],"is":[44,104],"unstructured.":[45],"Previously,":[46],"deployed":[48,78],"a":[49],"tool":[50,99],"called":[51],"TouchR":[52],"relies":[54],"on":[55,75,90,112],"the":[56,76,91,94,98,108,113],"Hidden":[57],"Markov":[58],"Model":[59],"(HMM)":[60],"extract":[62],"from":[64],"unstructured":[65],"(specifically,":[68],"NoSQL":[69],"databases).":[70],"This":[71],"paper":[72],"advanced":[74],"initially":[77],"version":[79],"where":[80],"introduced":[82],"re-usable":[83],"dictionary":[84],"and":[85],"association":[86],"rules":[87],"improve":[89],"quality":[92],"extracted":[95],"terms.":[96],"Also,":[97],"its":[101],"present":[102],"stage":[103],"more":[105],"adaptable":[106],"user":[109],"search":[110],"based":[111],"most":[114],"frequently":[115],"searched":[116],"term.":[117]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}