{"id":"https://openalex.org/W4386117809","doi":"https://doi.org/10.14778/3611479.3611535","title":"Effective Entity Augmentation by Querying External Data Sources","display_name":"Effective Entity Augmentation by Querying External Data Sources","publication_year":2023,"publication_date":"2023-07-01","ids":{"openalex":"https://openalex.org/W4386117809","doi":"https://doi.org/10.14778/3611479.3611535"},"language":"en","primary_location":{"id":"doi:10.14778/3611479.3611535","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3611479.3611535","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://pdxscholar.library.pdx.edu/compsci_fac/332","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060456300","display_name":"Christopher Bu\u00df","orcid":null},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Buss","raw_affiliation_strings":["Oregon State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon State University","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092090212","display_name":"Jasmin Mousavi","orcid":null},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jasmin Mousavi","raw_affiliation_strings":["Oregon State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon State University","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050558907","display_name":"M. V. Tokarev","orcid":"https://orcid.org/0000-0003-0749-3357"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mikhail Tokarev","raw_affiliation_strings":["Oregon State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon State University","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008664449","display_name":"Arash Termehchy","orcid":"https://orcid.org/0009-0007-2213-6303"},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arash Termehchy","raw_affiliation_strings":["Oregon State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon State University","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014301644","display_name":"David Maier","orcid":"https://orcid.org/0000-0003-4790-5619"},"institutions":[{"id":"https://openalex.org/I126345244","display_name":"Portland State University","ror":"https://ror.org/00yn2fy02","country_code":"US","type":"education","lineage":["https://openalex.org/I126345244"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Maier","raw_affiliation_strings":["Portland State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Portland State University","institution_ids":["https://openalex.org/I126345244"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019904004","display_name":"Stefan Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefan Lee","raw_affiliation_strings":["Oregon State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon State University","institution_ids":["https://openalex.org/I131249849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6666,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.726825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"16","issue":"11","first_page":"3404","last_page":"3417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994999766349792,"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":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.8730284571647644},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.6864379644393921},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6685479283332825},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4480955898761749},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3379625380039215},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3359820246696472}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8730284571647644},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.6864379644393921},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6685479283332825},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4480955898761749},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3379625380039215},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3359820246696472},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/3611479.3611535","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3611479.3611535","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:pdxscholar.library.pdx.edu:compsci_fac-1338","is_oa":true,"landing_page_url":"https://pdxscholar.library.pdx.edu/compsci_fac/332","pdf_url":null,"source":{"id":"https://openalex.org/S4377196300","display_name":"PDXScholar  (Portland State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126345244","host_organization_name":"Portland State University","host_organization_lineage":["https://openalex.org/I126345244"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Faculty Publications and Presentations","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:pdxscholar.library.pdx.edu:compsci_fac-1338","is_oa":true,"landing_page_url":"https://pdxscholar.library.pdx.edu/compsci_fac/332","pdf_url":null,"source":{"id":"https://openalex.org/S4377196300","display_name":"PDXScholar  (Portland State University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126345244","host_organization_name":"Portland State University","host_organization_lineage":["https://openalex.org/I126345244"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Faculty Publications and Presentations","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1556285385","https://openalex.org/W1779170294","https://openalex.org/W1870305865","https://openalex.org/W1996505782","https://openalex.org/W2038721957","https://openalex.org/W2061503185","https://openalex.org/W2062941476","https://openalex.org/W2065398649","https://openalex.org/W2144684817","https://openalex.org/W2148738951","https://openalex.org/W2148942721","https://openalex.org/W2208783499","https://openalex.org/W2767681556","https://openalex.org/W2767891136","https://openalex.org/W2795089200","https://openalex.org/W2798601084","https://openalex.org/W2945883855","https://openalex.org/W2948163032","https://openalex.org/W2949047719","https://openalex.org/W2984651502","https://openalex.org/W3139909695","https://openalex.org/W3168854329","https://openalex.org/W3175808861","https://openalex.org/W4206275166","https://openalex.org/W4210896998","https://openalex.org/W4213009331","https://openalex.org/W4234859835","https://openalex.org/W4310945327","https://openalex.org/W6602962767"],"related_works":["https://openalex.org/W4245395944","https://openalex.org/W2143551613","https://openalex.org/W1979740464","https://openalex.org/W2138823233","https://openalex.org/W2143345456","https://openalex.org/W2023236823","https://openalex.org/W1789991335","https://openalex.org/W2562731034","https://openalex.org/W2101053337","https://openalex.org/W1546993490"],"abstract_inverted_index":{"Users":[0],"often":[1],"want":[2],"to":[3,32,89,91,101,110,126,129,143,163,179,183,187,207],"augment":[4],"and":[5,77,122,148],"enrich":[6],"entities":[7],"in":[8,74,134,152,190],"their":[9],"datasets":[10,68],"with":[11,170],"relevant":[12,40,109,131,186,209],"information":[13,41,73,108,116,166,185,210],"from":[14,167,193],"external":[15,20,168,194],"data":[16,51,83,195],"sources.":[17,196],"As":[18],"many":[19,50,136],"sources":[21,52,169],"are":[22],"accessible":[23],"only":[24,56],"via":[25],"keyword-search":[26],"interfaces,":[27],"a":[28,35,57,103,160,191],"user":[29],"usually":[30],"has":[31],"manually":[33],"formulate":[34,102,127],"keyword":[36],"query":[37,104],"that":[38,105,201],"extract":[39],"for":[42,115,141],"each":[43,188],"entity.":[44,112],"This":[45],"approach":[46,162,203],"is":[47,99,139],"challenging":[48],"as":[49,155],"contain":[53,63],"numerous":[54],"tuples,":[55],"small":[58],"fraction":[59],"of":[60],"which":[61],"may":[62,69,85],"entity-relevant":[64,165],"information.":[65,132],"Furthermore,":[66],"different":[67,79,82,87],"represent":[70],"the":[71,92],"same":[72,93],"distinct":[75],"forms":[76],"under":[78],"terms":[80],"(e.g.,":[81],"source":[84],"use":[86],"names":[88],"refer":[90],"person).":[94],"In":[95],"such":[96],"cases,":[97],"it":[98,138],"difficult":[100],"precisely":[106],"retrieves":[107],"an":[111],"Current":[113],"methods":[114],"enrichment":[117],"mainly":[118],"rely":[119],"on":[120],"lengthy":[121],"resource-intensive":[123],"manual":[124],"effort":[125],"queries":[128],"discover":[130],"However,":[133],"increasingly":[135],"settings,":[137],"important":[140],"users":[142],"get":[144],"initial":[145],"answers":[146],"quickly":[147],"without":[149],"substantial":[150],"investment":[151],"resources":[153],"(such":[154],"human":[156],"attention).":[157],"We":[158],"propose":[159],"progressive":[161],"discovering":[164],"minimal":[171],"expert":[172],"intervention.":[173],"It":[174],"leverages":[175],"end":[176],"users'":[177],"feedback":[178],"progressively":[180],"learn":[181],"how":[182],"retrieve":[184],"entity":[189],"dataset":[192],"Our":[197],"empirical":[198],"evaluation":[199],"shows":[200],"our":[202],"learns":[204],"accurate":[205],"strategies":[206],"deliver":[208],"quickly.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}