{"id":"https://openalex.org/W2148539344","doi":"https://doi.org/10.1145/1141753.1141817","title":"Learning metadata from the evidence in an on-line citation matching scheme","display_name":"Learning metadata from the evidence in an on-line citation matching scheme","publication_year":2006,"publication_date":"2006-06-11","ids":{"openalex":"https://openalex.org/W2148539344","doi":"https://doi.org/10.1145/1141753.1141817","mag":"2148539344"},"language":"en","primary_location":{"id":"doi:10.1145/1141753.1141817","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141753.1141817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM/IEEE-CS 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":null,"display_name":"Isaac G. Councill","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Isaac G. Councill","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078578035","display_name":"Huajing Li","orcid":"https://orcid.org/0000-0003-4207-8351"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huajing Li","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102106448","display_name":"Ziming Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziming Zhuang","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103340284","display_name":"Sandip Debnath","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sandip Debnath","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022614137","display_name":"Levent Bolelli","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Levent Bolelli","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111961814","display_name":"Wang Chien Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang Chien Lee","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033253809","display_name":"Anand Sivasubramaniam","orcid":"https://orcid.org/0000-0001-6173-687X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anand Sivasubramaniam","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":2.1866,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.88259905,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"276","last_page":"285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9955999851226807,"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/T10028","display_name":"Topic Modeling","score":0.9937999844551086,"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":0.8156560659408569},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.7948472499847412},{"id":"https://openalex.org/keywords/citation","display_name":"Citation","score":0.794734001159668},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7494776248931885},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5463453531265259},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.5162642002105713},{"id":"https://openalex.org/keywords/citation-analysis","display_name":"Citation analysis","score":0.5112712383270264},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.49864983558654785},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.48502129316329956},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.41893136501312256},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34609097242355347},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32748177647590637},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.32431626319885254},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13001295924186707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8156560659408569},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.7948472499847412},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.794734001159668},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7494776248931885},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5463453531265259},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.5162642002105713},{"id":"https://openalex.org/C105345328","wikidata":"https://www.wikidata.org/wiki/Q206276","display_name":"Citation analysis","level":3,"score":0.5112712383270264},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.49864983558654785},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.48502129316329956},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.41893136501312256},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34609097242355347},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32748177647590637},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32431626319885254},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13001295924186707},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1141753.1141817","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141753.1141817","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.75.7870","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.7870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.personal.psu.edu/zxz127/docs/Councill_JCDL06.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.91.9487","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.91.9487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://clgiles.ist.psu.edu/papers/jcdl2006-learning-metadata.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1483664051","https://openalex.org/W1774330103","https://openalex.org/W1809800090","https://openalex.org/W1922293195","https://openalex.org/W1964685327","https://openalex.org/W1974940083","https://openalex.org/W1980925709","https://openalex.org/W1984058101","https://openalex.org/W2035745790","https://openalex.org/W2036216970","https://openalex.org/W2056826404","https://openalex.org/W2099105514","https://openalex.org/W2119965724","https://openalex.org/W2124949857","https://openalex.org/W2144564434","https://openalex.org/W2154498027","https://openalex.org/W2159080219","https://openalex.org/W2159481891","https://openalex.org/W2168190036"],"related_works":["https://openalex.org/W1552553528","https://openalex.org/W2183628870","https://openalex.org/W3023161639","https://openalex.org/W2008531296","https://openalex.org/W2782431616","https://openalex.org/W2394393789","https://openalex.org/W2374379029","https://openalex.org/W1503116306","https://openalex.org/W4299935056","https://openalex.org/W4385414095"],"abstract_inverted_index":{"Citation":[0,125],"matching,":[1],"or":[2],"the":[3,12,103,164,173],"automatic":[4,22],"grouping":[5],"of":[6,78,105,176],"bibliographic":[7,45],"references":[8],"that":[9,55,171],"refer":[10],"to":[11,98,122,136,162,186],"same":[13],"document,":[14],"is":[15,160],"a":[16,106,116,138,145,169],"data":[17],"management":[18],"problem":[19],"faced":[20],"by":[21],"digital":[23,61],"libraries":[24,62],"for":[25,40,149,168],"scientific":[26],"literature":[27],"such":[28],"as":[29,85],"CiteSeer":[30],"and":[31,70,147,153,182],"Google":[32],"Scholar.":[33],"Although":[34],"several":[35],"solutions":[36,48],"have":[37],"been":[38],"offered":[39],"citation":[41,64,79,83,108,113,151,166],"matching":[42,152],"in":[43,93,134],"large":[44],"databases,":[46],"these":[47],"typically":[49],"require":[50],"expensive":[51],"batch":[52],"clustering":[53],"operations":[54],"must":[56,127],"be":[57,96,128],"run":[58],"offline.":[59],"Large":[60],"containing":[63],"information":[65,91,126,132,178],"can":[66,95],"reduce":[67],"maintenance":[68],"costs":[69],"provide":[71,137],"new":[72,86],"services":[73],"through":[74],"efficient":[75],"online":[76,150],"processing":[77],"data,":[80],"resolving":[81],"document":[82,100,140,170],"relationships":[84],"records":[87],"become":[88],"available.":[89],"Additionally,":[90],"found":[92],"citations":[94],"used":[97],"supplement":[99],"metadata,":[101],"requiring":[102],"generation":[104],"canonical":[107,154],"record":[109,167],"from":[110,120,179],"merging":[111],"variant":[112],"subfields":[114],"into":[115],"unified":[117],"\"best":[118],"guess\"":[119],"which":[121],"draw":[123],"information.":[124],"merged":[129],"with":[130],"other":[131],"sources":[133,181],"order":[135],"complete":[139],"record.":[141],"This":[142],"paper":[143],"outlines":[144],"system":[146,184],"algorithms":[148],"metadata":[155],"generation.":[156],"A":[157],"Bayesian":[158],"framework":[159],"employed":[161],"build":[163],"ideal":[165],"carries":[172],"added":[174],"advantages":[175],"fusing":[177],"disparate":[180],"increasing":[183],"resilience":[185],"erroneous":[187],"data.":[188]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
