{"id":"https://openalex.org/W1934084512","doi":"https://doi.org/10.14778/2809974.2809991","title":"Incremental knowledge base construction using DeepDive","display_name":"Incremental knowledge base construction using DeepDive","publication_year":2015,"publication_date":"2015-07-01","ids":{"openalex":"https://openalex.org/W1934084512","doi":"https://doi.org/10.14778/2809974.2809991","mag":"1934084512","pmid":"https://pubmed.ncbi.nlm.nih.gov/27144081"},"language":"en","primary_location":{"id":"doi:10.14778/2809974.2809991","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2809974.2809991","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","pubmed"],"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/A5101727253","display_name":"Jaeho Shin","orcid":"https://orcid.org/0000-0001-5280-3356"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jaeho Shin","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033975637","display_name":"Sen Wu","orcid":"https://orcid.org/0000-0002-6133-4122"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sen Wu","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778975","display_name":"Feiran Wang","orcid":"https://orcid.org/0000-0003-4568-9158"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Feiran Wang","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041869459","display_name":"Christopher De","orcid":"https://orcid.org/0000-0002-3610-2696"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher De Sa","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100383721","display_name":"Ce Zhang","orcid":"https://orcid.org/0000-0001-6789-0130"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]},{"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":"Ce Zhang","raw_affiliation_strings":["Stanford University and University of Wisconsin-Madison"],"affiliations":[{"raw_affiliation_string":"Stanford University and University of Wisconsin-Madison","institution_ids":["https://openalex.org/I135310074","https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103852640","display_name":"Christopher R\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher R\u00e9","raw_affiliation_strings":["Stanford University"],"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101727253"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":44.5424,"has_fulltext":false,"cited_by_count":235,"citation_normalized_percentile":{"value":0.99906642,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"8","issue":"11","first_page":"1310","last_page":"1321"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9962999820709229,"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":0.9962999820709229,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9918000102043152,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9767000079154968,"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/inference","display_name":"Inference","score":0.8010464906692505},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7830888032913208},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.6094374656677246},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5741683840751648},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5206108093261719},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.45260727405548096},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4395756125450134},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43295779824256897},{"id":"https://openalex.org/keywords/inference-engine","display_name":"Inference engine","score":0.4325272738933563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42803680896759033},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35631150007247925},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09334823489189148}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.8010464906692505},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7830888032913208},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.6094374656677246},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5741683840751648},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5206108093261719},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.45260727405548096},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4395756125450134},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43295779824256897},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.4325272738933563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42803680896759033},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35631150007247925},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09334823489189148},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.14778/2809974.2809991","is_oa":false,"landing_page_url":"https://doi.org/10.14778/2809974.2809991","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":"pmid:27144081","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/27144081","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment. International Conference on Very Large Data Bases","raw_type":null},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.927.9523","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.927.9523","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://i.stanford.edu/hazy/papers/inc.pdf","raw_type":"text"},{"id":"pmh:oai:europepmc.org:3822607","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/4852149","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":94,"referenced_works":["https://openalex.org/W104683736","https://openalex.org/W130710483","https://openalex.org/W144096106","https://openalex.org/W343945789","https://openalex.org/W1435924991","https://openalex.org/W1484863582","https://openalex.org/W1489949474","https://openalex.org/W1493490255","https://openalex.org/W1500829410","https://openalex.org/W1509562192","https://openalex.org/W1512387364","https://openalex.org/W1515300998","https://openalex.org/W1562880585","https://openalex.org/W1565102206","https://openalex.org/W1599188306","https://openalex.org/W1600293573","https://openalex.org/W1604644367","https://openalex.org/W1788418780","https://openalex.org/W1900340173","https://openalex.org/W1951794832","https://openalex.org/W1954715867","https://openalex.org/W1962705364","https://openalex.org/W1963853643","https://openalex.org/W1965685479","https://openalex.org/W1985093013","https://openalex.org/W1997945384","https://openalex.org/W2006149654","https://openalex.org/W2009591769","https://openalex.org/W2012670464","https://openalex.org/W2019041908","https://openalex.org/W2024710200","https://openalex.org/W2036287059","https://openalex.org/W2045495924","https://openalex.org/W2052569640","https://openalex.org/W2064466058","https://openalex.org/W2068737686","https://openalex.org/W2079785597","https://openalex.org/W2081210343","https://openalex.org/W2093808275","https://openalex.org/W2099419573","https://openalex.org/W2101108755","https://openalex.org/W2102267996","https://openalex.org/W2107598941","https://openalex.org/W2115461474","https://openalex.org/W2118038484","https://openalex.org/W2120143966","https://openalex.org/W2120340025","https://openalex.org/W2120615054","https://openalex.org/W2125972432","https://openalex.org/W2128851024","https://openalex.org/W2129207602","https://openalex.org/W2129629757","https://openalex.org/W2132679783","https://openalex.org/W2133134975","https://openalex.org/W2133338734","https://openalex.org/W2135194391","https://openalex.org/W2135209143","https://openalex.org/W2135779000","https://openalex.org/W2135912864","https://openalex.org/W2138204945","https://openalex.org/W2144416276","https://openalex.org/W2144810465","https://openalex.org/W2145453687","https://openalex.org/W2150588363","https://openalex.org/W2151128232","https://openalex.org/W2151608460","https://openalex.org/W2162621793","https://openalex.org/W2167571757","https://openalex.org/W2171278097","https://openalex.org/W2181502022","https://openalex.org/W2184860929","https://openalex.org/W2250545651","https://openalex.org/W2251419334","https://openalex.org/W2251812060","https://openalex.org/W2251960799","https://openalex.org/W2338322935","https://openalex.org/W2396924315","https://openalex.org/W2401642934","https://openalex.org/W2466758040","https://openalex.org/W2568452962","https://openalex.org/W2913201029","https://openalex.org/W2964244261","https://openalex.org/W3098547670","https://openalex.org/W4230201548","https://openalex.org/W4292691288","https://openalex.org/W4293052541","https://openalex.org/W6629408398","https://openalex.org/W6630321736","https://openalex.org/W6680029872","https://openalex.org/W6680083739","https://openalex.org/W6685275506","https://openalex.org/W6712028060","https://openalex.org/W6841455387","https://openalex.org/W7075682605"],"related_works":["https://openalex.org/W2057057690","https://openalex.org/W2368184788","https://openalex.org/W2358964818","https://openalex.org/W2359535128","https://openalex.org/W2395929705","https://openalex.org/W2381332051","https://openalex.org/W4375958074","https://openalex.org/W2372304001","https://openalex.org/W2376097826","https://openalex.org/W1498088200"],"abstract_inverted_index":{"Populating":[0],"a":[1,7,44,114],"database":[2,48],"with":[3,30,148],"unstructured":[4],"information":[5],"is":[6,75],"long-standing":[8],"problem":[9,27],"in":[10],"industry":[11],"and":[12,20,33,49,58,77,100,112,124],"research":[13],"that":[14,46,71,133],"encompasses":[15],"problems":[16],"of":[17,109,121,146],"extraction,":[18],"cleaning,":[19],"integration.":[21],"Recent":[22],"names":[23],"used":[24],"for":[25,86,93],"this":[26,39],"include":[28],"dealing":[29],"dark":[31],"data":[32],"knowledge":[34],"base":[35],"construction":[36],"(KBC).":[37],"In":[38],"work,":[40],"we":[41,59,78,125],"describe":[42],"DeepDive,":[43],"system":[45],"combines":[47],"machine":[50],"learning":[51],"ideas":[52],"to":[53,62,81,143],"help":[54],"develop":[55,79,113],"KBC":[56,65,73,87,130,138],"systems,":[57,131],"present":[60],"techniques":[61,80],"make":[63],"the":[64,72,106],"process":[66,74],"more":[67],"efficient.":[68],"We":[69,89,103],"observe":[70],"iterative,":[76],"incrementally":[82],"produce":[83],"inference":[84,139],"results":[85],"systems.":[88],"propose":[90],"two":[91,144],"methods":[92,111],"incremental":[94],"inference,":[95],"based":[96],"respectively":[97],"on":[98,128,151],"sampling":[99],"variational":[101],"techniques.":[102],"also":[104],"study":[105],"tradeoff":[107],"space":[108],"these":[110,122],"simple":[115],"rule-based":[116],"optimizer.":[117],"DeepDive":[118],"includes":[119],"all":[120],"contributions,":[123],"evaluate":[126],"Deep-Dive":[127],"five":[129],"showing":[132],"it":[134],"can":[135],"speed":[136],"up":[137,142],"tasks":[140],"by":[141],"orders":[145],"magnitude":[147],"negligible":[149],"impact":[150],"quality.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":51},{"year":2018,"cited_by_count":36},{"year":2017,"cited_by_count":32},{"year":2016,"cited_by_count":30},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}