{"id":"https://openalex.org/W1972837706","doi":"https://doi.org/10.1145/1816123.1816130","title":"Effective self-training author name disambiguation in scholarly digital libraries","display_name":"Effective self-training author name disambiguation in scholarly digital libraries","publication_year":2010,"publication_date":"2010-06-21","ids":{"openalex":"https://openalex.org/W1972837706","doi":"https://doi.org/10.1145/1816123.1816130","mag":"1972837706"},"language":"en","primary_location":{"id":"doi:10.1145/1816123.1816130","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1816123.1816130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th annual joint conference on Digital libraries","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/A5011076740","display_name":"Anderson A. Ferreira","orcid":"https://orcid.org/0000-0002-2487-6600"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Anderson A. Ferreira","raw_affiliation_strings":["Universidade Federal de Minas Gerais, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086714399","display_name":"Adriano Veloso","orcid":"https://orcid.org/0000-0002-9177-4954"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Adriano Veloso","raw_affiliation_strings":["Universidade Federal de Minas Gerais, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046370637","display_name":"Marcos Andr\u00e9 Gon\u00e7alves","orcid":"https://orcid.org/0000-0002-2075-3363"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Marcos Andr\u00e9 Gon\u00e7alves","raw_affiliation_strings":["Universidade Federal de Minas Gerais, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045978751","display_name":"Alberto H. F. Laender","orcid":"https://orcid.org/0000-0001-5032-2233"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Alberto H.F. Laender","raw_affiliation_strings":["Universidade Federal de Minas Gerais, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5011076740"],"corresponding_institution_ids":["https://openalex.org/I110200422"],"apc_list":null,"apc_paid":null,"fwci":10.0756,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.98083771,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"48"},"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/T10028","display_name":"Topic Modeling","score":0.9987999796867371,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8711620569229126},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.8029060363769531},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6626399755477905},{"id":"https://openalex.org/keywords/citation","display_name":"Citation","score":0.6511892080307007},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6254912614822388},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.572741687297821},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.516437828540802},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.510494589805603},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5026199817657471},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.46859779953956604},{"id":"https://openalex.org/keywords/associative-property","display_name":"Associative property","score":0.4592646360397339},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.44785481691360474},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4422440826892853},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43432819843292236},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.41429266333580017},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3712915778160095},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2641686797142029},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.09532138705253601},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08750033378601074}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8711620569229126},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.8029060363769531},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6626399755477905},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.6511892080307007},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6254912614822388},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.572741687297821},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.516437828540802},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.510494589805603},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5026199817657471},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.46859779953956604},{"id":"https://openalex.org/C159423971","wikidata":"https://www.wikidata.org/wiki/Q177251","display_name":"Associative property","level":2,"score":0.4592646360397339},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.44785481691360474},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4422440826892853},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43432819843292236},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.41429266333580017},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3712915778160095},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2641686797142029},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09532138705253601},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08750033378601074},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1816123.1816130","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1816123.1816130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th annual joint conference on Digital libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.182.4937","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.182.4937","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dcc.ufmg.br/%7Eadrianov/papers/JCDL10/jcdl10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W156710820","https://openalex.org/W278081246","https://openalex.org/W1490467549","https://openalex.org/W1496319844","https://openalex.org/W1536860849","https://openalex.org/W1547705211","https://openalex.org/W1585742040","https://openalex.org/W1592086497","https://openalex.org/W1592339834","https://openalex.org/W1599013591","https://openalex.org/W1660390307","https://openalex.org/W1673310716","https://openalex.org/W1766412966","https://openalex.org/W1846215264","https://openalex.org/W1964879903","https://openalex.org/W1974832471","https://openalex.org/W1982149803","https://openalex.org/W1982678692","https://openalex.org/W1990976049","https://openalex.org/W1991184411","https://openalex.org/W1999431036","https://openalex.org/W2007172042","https://openalex.org/W2021995095","https://openalex.org/W2026499502","https://openalex.org/W2039599657","https://openalex.org/W2050612897","https://openalex.org/W2056826404","https://openalex.org/W2065068924","https://openalex.org/W2078517869","https://openalex.org/W2080099271","https://openalex.org/W2090987348","https://openalex.org/W2098162425","https://openalex.org/W2116690618","https://openalex.org/W2118938540","https://openalex.org/W2119821739","https://openalex.org/W2148019918","https://openalex.org/W2153635508","https://openalex.org/W2162337786","https://openalex.org/W2166559705","https://openalex.org/W3017034856","https://openalex.org/W3120421331","https://openalex.org/W4240579122","https://openalex.org/W4243229161","https://openalex.org/W6635685934","https://openalex.org/W6637101025"],"related_works":["https://openalex.org/W1496222301","https://openalex.org/W3207760230","https://openalex.org/W1590307681","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2358353312","https://openalex.org/W2353836703","https://openalex.org/W41015297","https://openalex.org/W4280645561","https://openalex.org/W1671936420"],"abstract_inverted_index":{"Name":[0,116],"ambiguity":[1],"in":[2,21,33,55,65,171,191,224],"the":[3,15,42,47,74,95,98,128,149,174,185],"context":[4],"of":[5,17,61,76,80,97,130,173,188],"bibliographic":[6],"citation":[7,145,193,216],"records":[8,146,217],"is":[9,163,219],"a":[10,56,108,140,158,192],"hard":[11],"problem":[12],"that":[13,29,118,143,162,203,212],"affects":[14],"quality":[16],"services":[18],"and":[19,24,58,82,199,218,223],"content":[20],"digital":[22],"libraries":[23],"similar":[25],"systems.":[26,102],"Supervised":[27],"methods":[28,211],"exploit":[30,213],"training":[31,70,176,235],"examples":[32,81,91,138],"order":[34,66],"to":[35,67,165],"distinguish":[36],"ambiguous":[37],"author":[38,195],"names":[39],"are":[40,92,94],"among":[41,151],"most":[43],"effective":[44,85,221],"solutions":[45],"for":[46,100],"problem,":[48],"but":[49],"they":[50],"require":[51],"skilled":[52],"human":[53],"annotators":[54],"laborious":[57],"continuous":[59],"process":[60],"manually":[62,232],"labeling":[63,133,233],"citations":[64],"provide":[68],"enough":[69],"examples.":[71,177],"Thus,":[72],"addressing":[73],"issues":[75],"(i)":[77],"automatic":[78],"acquisition":[79],"(ii)":[83],"highly":[84],"disambiguation":[86,111,160,210],"even":[87],"when":[88],"only":[89],"few":[90],"available,":[93],"need":[96,129],"hour":[99],"such":[101],"In":[103],"this":[104],"paper,":[105],"we":[106],"propose":[107],"novel":[109],"two-step":[110],"method,":[112],"SAND":[113],"(Self-training":[114],"Associative":[115],"Disambiguator),":[117],"deals":[119],"with":[120,180],"these":[121],"two":[122],"issues.":[123],"The":[124,154],"first":[125],"step":[126,156],"eliminates":[127],"any":[131,172,234],"manual":[132],"effort":[134],"by":[135],"automatically":[136],"acquiring":[137],"using":[139,184],"clustering":[141],"method":[142,161,206],"groups":[144],"based":[147],"on":[148],"similarity":[150],"coauthor":[152],"names.":[153],"second":[155],"uses":[157],"supervised":[159,229],"able":[164],"detect":[166],"unseen":[167],"authors":[168],"not":[169],"included":[170],"given":[175],"Experiments":[178],"conducted":[179],"standard":[181],"public":[182],"collections,":[183],"minimum":[186],"set":[187],"attributes":[189],"present":[190],"(i.e.,":[194],"names,":[196],"work":[197],"title":[198],"publication":[200],"venue),":[201],"demonstrated":[202],"our":[204],"proposed":[205],"outperforms":[207],"representative":[208],"unsupervised":[209],"similarities":[214],"between":[215],"as":[220],"as,":[222],"some":[225],"cases":[226],"superior":[227],"to,":[228],"ones,":[230],"without":[231],"example.":[236]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}