{"id":"https://openalex.org/W2887266854","doi":"https://doi.org/10.3233/sw-180301","title":"STEM: Stacked threshold-based entity matching for knowledge base generation","display_name":"STEM: Stacked threshold-based entity matching for knowledge base generation","publication_year":2018,"publication_date":"2018-08-10","ids":{"openalex":"https://openalex.org/W2887266854","doi":"https://doi.org/10.3233/sw-180301","mag":"2887266854"},"language":"en","primary_location":{"id":"doi:10.3233/sw-180301","is_oa":false,"landing_page_url":"https://doi.org/10.3233/sw-180301","pdf_url":null,"source":{"id":"https://openalex.org/S4210177235","display_name":"Semantic Web","issn_l":"1570-0844","issn":["1570-0844","2210-4968"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Semantic Web","raw_type":"journal-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/A5045705674","display_name":"Enrico Palumbo","orcid":"https://orcid.org/0000-0003-3898-7480"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]},{"id":"https://openalex.org/I2800599128","display_name":"Istituto Superiore Mario Boella","ror":"https://ror.org/05y6jfx28","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2800599128","https://openalex.org/I4210155299"]},{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["FR","IT"],"is_corresponding":true,"raw_author_name":"Enrico Palumbo","raw_affiliation_strings":["EURECOM, Sophia Antipolis, France","Istituto Superiore Mario Boella, Turin, Italy","Politecnico di Torino, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EURECOM, Sophia Antipolis, France","institution_ids":["https://openalex.org/I1902872"]},{"raw_affiliation_string":"Istituto Superiore Mario Boella, Turin, Italy","institution_ids":["https://openalex.org/I2800599128"]},{"raw_affiliation_string":"Politecnico di Torino, Turin, Italy","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088463134","display_name":"Giuseppe Rizzo","orcid":"https://orcid.org/0000-0003-0083-813X"},"institutions":[{"id":"https://openalex.org/I2800599128","display_name":"Istituto Superiore Mario Boella","ror":"https://ror.org/05y6jfx28","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2800599128","https://openalex.org/I4210155299"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giuseppe Rizzo","raw_affiliation_strings":["Istituto Superiore Mario Boella, Turin, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istituto Superiore Mario Boella, Turin, Italy","institution_ids":["https://openalex.org/I2800599128"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022574838","display_name":"Rapha\u00ebl Troncy","orcid":"https://orcid.org/0000-0003-0457-1436"},"institutions":[{"id":"https://openalex.org/I1902872","display_name":"EURECOM","ror":"https://ror.org/00sse7z02","country_code":"FR","type":"education","lineage":["https://openalex.org/I1902872","https://openalex.org/I205703379"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Rapha\u00ebl Troncy","raw_affiliation_strings":["EURECOM, Sophia Antipolis, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EURECOM, Sophia Antipolis, France","institution_ids":["https://openalex.org/I1902872"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045705674"],"corresponding_institution_ids":["https://openalex.org/I177477856","https://openalex.org/I1902872","https://openalex.org/I2800599128"],"apc_list":null,"apc_paid":null,"fwci":0.2123,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.59823149,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"10","issue":"1","first_page":"117","last_page":"137"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.980400025844574,"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/T10028","display_name":"Topic Modeling","score":0.9783999919891357,"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":0.6968159079551697},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.6422528028488159},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5867103934288025},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5549802184104919},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.543969452381134},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5340591669082642},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.520430862903595},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48840564489364624},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47882989048957825},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46556970477104187},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.46435976028442383},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.4368324875831604},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4306516647338867},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.4104645550251007},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19434842467308044},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11529406905174255},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11358505487442017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6968159079551697},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.6422528028488159},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5867103934288025},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5549802184104919},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.543969452381134},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5340591669082642},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.520430862903595},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48840564489364624},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47882989048957825},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46556970477104187},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.46435976028442383},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.4368324875831604},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4306516647338867},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.4104645550251007},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19434842467308044},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11529406905174255},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11358505487442017},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/sw-180301","is_oa":false,"landing_page_url":"https://doi.org/10.3233/sw-180301","pdf_url":null,"source":{"id":"https://openalex.org/S4210177235","display_name":"Semantic Web","issn_l":"1570-0844","issn":["1570-0844","2210-4968"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Semantic Web","raw_type":"journal-article"},{"id":"pmh:oai:fr.eurecom:5477","is_oa":false,"landing_page_url":"http://www.eurecom.fr/publication/5477","pdf_url":null,"source":{"id":"https://openalex.org/S4377196942","display_name":"Graduate School and Research Center in Digital Science (EURECOM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1902872","host_organization_name":"EURECOM","host_organization_lineage":["https://openalex.org/I1902872"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Semantic Web 1 (2016) 1-5, IOS Press","raw_type":"Journal"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W509898","https://openalex.org/W28412257","https://openalex.org/W46659105","https://openalex.org/W51908901","https://openalex.org/W61518770","https://openalex.org/W140982117","https://openalex.org/W179179905","https://openalex.org/W192652968","https://openalex.org/W1491268609","https://openalex.org/W1491357092","https://openalex.org/W1503398984","https://openalex.org/W1538632262","https://openalex.org/W1550206324","https://openalex.org/W1568705965","https://openalex.org/W1599547597","https://openalex.org/W1659724737","https://openalex.org/W1924689489","https://openalex.org/W1979954747","https://openalex.org/W1982804187","https://openalex.org/W1998475090","https://openalex.org/W2024594469","https://openalex.org/W2030959072","https://openalex.org/W2046020929","https://openalex.org/W2067566391","https://openalex.org/W2070229309","https://openalex.org/W2073471108","https://openalex.org/W2085099553","https://openalex.org/W2085302848","https://openalex.org/W2086405793","https://openalex.org/W2092126505","https://openalex.org/W2092708731","https://openalex.org/W2104511295","https://openalex.org/W2111625757","https://openalex.org/W2117030594","https://openalex.org/W2123561513","https://openalex.org/W2140527686","https://openalex.org/W2141634619","https://openalex.org/W2142787640","https://openalex.org/W2153635508","https://openalex.org/W2159392930","https://openalex.org/W2160536005","https://openalex.org/W2161600801","https://openalex.org/W2164456230","https://openalex.org/W2170902582","https://openalex.org/W2239873446","https://openalex.org/W2407521136","https://openalex.org/W2471839838","https://openalex.org/W2521135474","https://openalex.org/W2526010169","https://openalex.org/W2546945975","https://openalex.org/W2577695005","https://openalex.org/W2615447451","https://openalex.org/W2615504032","https://openalex.org/W3177743715","https://openalex.org/W3215186461","https://openalex.org/W4205223485","https://openalex.org/W4241410814","https://openalex.org/W4245861846","https://openalex.org/W6632943017","https://openalex.org/W6689934819","https://openalex.org/W6728903214","https://openalex.org/W6816152598"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W1978893398","https://openalex.org/W2201908702","https://openalex.org/W4381094582","https://openalex.org/W2369625323","https://openalex.org/W2364579609","https://openalex.org/W1977906818","https://openalex.org/W2385713529","https://openalex.org/W2599749361","https://openalex.org/W2387801216"],"abstract_inverted_index":{"One":[0],"of":[1,9,15,21,44,54,79,85,120,154,168,187,210,238,245],"the":[2,7,13,34,42,52,55,62,74,77,80,86,147,150,155,160,165,169,185,208,211,236,239,243,246],"major":[3],"issues":[4],"encountered":[5],"in":[6,242],"generation":[8,244],"knowledge":[10,249],"bases":[11],"is":[12,33,39,143,181],"integration":[14],"data":[16,23,31,190,226],"coming":[17],"from":[18],"a":[19,45,59,65,71,110,131,135,194,231],"collection":[20],"heterogeneous":[22],"sources.":[24],"A":[25],"key":[26],"essential":[27],"task":[28],"when":[29],"integrating":[30],"instances":[32,119],"entity":[35,56],"matching.":[36],"Entity":[37],"matching":[38],"based":[40],"on":[41,51,184,223],"definition":[43],"similarity":[46,63,202],"measure":[47],"among":[48],"entities":[49],"and":[50,76,92,95,102,126,152,163,180],"classification":[53],"pair":[57],"as":[58,82,130],"match":[60],"if":[61],"exceeds":[64],"certain":[66],"threshold.":[67],"This":[68],"parameter":[69],"introduces":[70],"trade-off":[72,148],"between":[73,149],"precision":[75,91,151],"recall":[78,101,153],"algorithm,":[81,156],"higher":[83,90,100],"values":[84,97],"threshold":[87],"lead":[88,98],"to":[89,99,123,145,193,206],"lower":[93,96,103],"recall,":[94],"precision.":[104],"In":[105,204],"this":[106,141,175],"paper,":[107],"we":[108,213,229],"propose":[109],"stacking":[111],"approach":[112,142,177,197,241],"for":[113,134],"threshold-based":[114,221],"classifiers.":[115],"It":[116],"runs":[117],"several":[118],"classifiers":[121,222],"corresponding":[122],"different":[124,220,225],"thresholds":[125],"use":[127,233],"their":[128],"predictions":[129],"feature":[132],"vector":[133],"supervised":[136,195],"learner.":[137],"We":[138,171],"show":[139,173,230],"that":[140,174,198],"able":[144],"break":[146],"increasing":[157],"both":[158],"at":[159],"same":[161],"time":[162],"enhancing":[164],"overall":[166],"performance":[167],"algorithm.":[170],"also":[172],"hybrid":[176],"performs":[178],"better":[179],"less":[182],"dependent":[183],"amount":[186],"available":[188],"training":[189],"with":[191],"respect":[192],"learning":[196],"directly":[199],"uses":[200],"properties\u2019":[201],"values.":[203],"order":[205],"test":[207],"generality":[209],"claim,":[212],"have":[214],"run":[215],"experimental":[216],"tests":[217],"using":[218],"two":[219,224],"sets.":[227],"Finally,":[228],"concrete":[232],"case":[234],"describing":[235],"implementation":[237],"proposed":[240],"3cixty":[247],"Nice":[248],"base.":[250]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}