{"id":"https://openalex.org/W2199337656","doi":"https://doi.org/10.1109/bigdata.2015.7363868","title":"A pipeline for extracting and deduplicating domain-specific knowledge bases","display_name":"A pipeline for extracting and deduplicating domain-specific knowledge bases","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2199337656","doi":"https://doi.org/10.1109/bigdata.2015.7363868","mag":"2199337656"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7363868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363868","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5074197492","display_name":"Mayank Kejriwal","orcid":"https://orcid.org/0000-0001-5988-8305"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mayank Kejriwal","raw_affiliation_strings":["The University of Texas at Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100688198","display_name":"Qiaoling Liu","orcid":"https://orcid.org/0000-0001-5909-6885"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiaoling Liu","raw_affiliation_strings":["CareerBuilder LLC, Norcross, GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CareerBuilder LLC, Norcross, GA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088467827","display_name":"Ferosh Jacob","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ferosh Jacob","raw_affiliation_strings":["CareerBuilder LLC, Norcross, GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CareerBuilder LLC, Norcross, GA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101668745","display_name":"Faizan Javed","orcid":"https://orcid.org/0000-0002-9362-2081"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Faizan Javed","raw_affiliation_strings":["CareerBuilder LLC, Norcross, GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CareerBuilder LLC, Norcross, GA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1144","last_page":"1153"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9958999752998352,"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":0.9958999752998352,"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/pipeline","display_name":"Pipeline (software)","score":0.8394574522972107},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8182482719421387},{"id":"https://openalex.org/keywords/data-deduplication","display_name":"Data deduplication","score":0.7216438055038452},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6677204966545105},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6561181545257568},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6199050545692444},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.5728940367698669},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.5310894250869751},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4833680987358093},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4582783877849579},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.440257728099823},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.42928239703178406},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4165729880332947},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3849279582500458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2871858775615692},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07726255059242249},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0691177248954773}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.8394574522972107},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8182482719421387},{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.7216438055038452},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6677204966545105},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6561181545257568},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6199050545692444},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.5728940367698669},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.5310894250869751},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4833680987358093},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4582783877849579},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.440257728099823},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.42928239703178406},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4165729880332947},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3849279582500458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2871858775615692},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07726255059242249},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0691177248954773},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2015.7363868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363868","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W102708294","https://openalex.org/W273955616","https://openalex.org/W631580934","https://openalex.org/W1513159584","https://openalex.org/W1547612978","https://openalex.org/W1680622244","https://openalex.org/W1886771451","https://openalex.org/W1964189668","https://openalex.org/W1977518804","https://openalex.org/W2016753842","https://openalex.org/W2024770506","https://openalex.org/W2031250218","https://openalex.org/W2049770245","https://openalex.org/W2094728533","https://openalex.org/W2099846738","https://openalex.org/W2108991785","https://openalex.org/W2122604280","https://openalex.org/W2122865749","https://openalex.org/W2141278204","https://openalex.org/W2152502401","https://openalex.org/W2154536059","https://openalex.org/W2164456230","https://openalex.org/W2210478268","https://openalex.org/W2293638404","https://openalex.org/W2949591734","https://openalex.org/W3126729787","https://openalex.org/W3146259567","https://openalex.org/W4242744113","https://openalex.org/W4254788633","https://openalex.org/W4366078666","https://openalex.org/W6610017368","https://openalex.org/W6697186641"],"related_works":["https://openalex.org/W2938937533","https://openalex.org/W2562283313","https://openalex.org/W1426690399","https://openalex.org/W3000763654","https://openalex.org/W2615258478","https://openalex.org/W3184782866","https://openalex.org/W2399436049","https://openalex.org/W2122539184","https://openalex.org/W2573530796","https://openalex.org/W2046488454","https://openalex.org/W2894938771","https://openalex.org/W2033062623","https://openalex.org/W3198567163","https://openalex.org/W3119497443","https://openalex.org/W2328260270","https://openalex.org/W62397842","https://openalex.org/W3041159669","https://openalex.org/W142581890","https://openalex.org/W131511973","https://openalex.org/W3044148358"],"abstract_inverted_index":{"Building":[0],"a":[1,85,93,112,128],"knowledge":[2],"base":[3],"(KB)":[4],"describing":[5,95],"domain-specific":[6,57],"entities":[7,100],"is":[8],"an":[9,123],"important":[10],"problem":[11],"in":[12,53],"industry,":[13],"examples":[14],"including":[15,36],"KBs":[16],"built":[17],"over":[18,133],"companies":[19],"(e.g.":[20],"Dun":[21],"&":[22],"Bradstreet),":[23],"skills":[24],"(LinkedIn,":[25],"CareerBuilder)":[26],"and":[27,44,66,80,109,111,116,143],"people":[28],"(inome).":[29],"The":[30,60],"task":[31],"involves":[32,48],"several":[33],"engineering":[34],"challenges,":[35],"devising":[37],"effective":[38],"procedures":[39],"for":[40,91],"data":[41,58,106],"extraction,":[42],"aggregation":[43],"deduplication.":[45],"Data":[46],"extraction":[47],"processing":[49],"multiple":[50],"information":[51],"sources":[52,107],"order":[54],"to":[55,72,121],"extract":[56],"instances.":[59],"extracted":[61,141],"instances":[62,70,120],"must":[63,77],"be":[64,78],"aggregated":[65],"deduplicated;":[67],"that":[68],"is,":[69],"referring":[71],"the":[73,119,140],"same":[74],"underlying":[75],"entity":[76],"identified":[79],"merged.":[81],"This":[82],"paper":[83],"describes":[84],"pipeline":[86],"developed":[87],"at":[88],"CareerBuilder":[89],"LLC":[90],"building":[92],"KB":[94],"employers,":[96],"by":[97],"first":[98],"extracting":[99],"from":[101,139],"both":[102],"global,":[103],"publicly":[104],"available":[105],"(Wikipedia":[108],"Freebase)":[110],"proprietary":[113],"source":[114],"(Infogroup),":[115],"then":[117],"deduplicating":[118],"yield":[122],"employer-specific":[124],"KB.":[125],"We":[126],"conduct":[127],"range":[129],"of":[130],"pilot":[131],"experiments":[132],"three":[134],"independently":[135],"labeled":[136],"datasets":[137],"sampled":[138],"KB,":[142],"comment":[144],"on":[145],"some":[146],"lessons":[147],"learned.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}