{"id":"https://openalex.org/W2951141188","doi":"https://doi.org/10.1609/aaai.v33i01.33019601","title":"Cleaning Noisy and Heterogeneous Metadata for Record Linking across Scholarly Big Datasets","display_name":"Cleaning Noisy and Heterogeneous Metadata for Record Linking across Scholarly Big Datasets","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2951141188","doi":"https://doi.org/10.1609/aaai.v33i01.33019601","mag":"2951141188"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33019601","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019601","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5022/4895","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5022/4895","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072607871","display_name":"Athar Sefid","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":"Athar Sefid","raw_affiliation_strings":["Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075242841","display_name":"Jian Wu","orcid":"https://orcid.org/0000-0003-0173-4463"},"institutions":[{"id":"https://openalex.org/I81365321","display_name":"Old Dominion University","ror":"https://ror.org/04zjtrb98","country_code":"US","type":"education","lineage":["https://openalex.org/I81365321"]},{"id":"https://openalex.org/I4210092569","display_name":"Dominion University College","ror":"https://ror.org/003kqe171","country_code":"GH","type":"education","lineage":["https://openalex.org/I4210092569"]}],"countries":["GH","US"],"is_corresponding":false,"raw_author_name":"Jian Wu","raw_affiliation_strings":["Old Dominion University","\u2021Old Dominion University"],"affiliations":[{"raw_affiliation_string":"Old Dominion University","institution_ids":["https://openalex.org/I4210092569","https://openalex.org/I81365321"]},{"raw_affiliation_string":"\u2021Old Dominion University","institution_ids":["https://openalex.org/I81365321"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086240210","display_name":"Allen C. Ge","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":"Allen C. Ge","raw_affiliation_strings":["Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101784136","display_name":"Zhao Jing","orcid":"https://orcid.org/0000-0003-4796-9532"},"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":"Jing Zhao","raw_affiliation_strings":["Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002822427","display_name":"Lu Liu","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":"Lu Liu","raw_affiliation_strings":["Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089085275","display_name":"Cornelia Caragea","orcid":"https://orcid.org/0000-0002-5664-2163"},"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":"Cornelia Caragea","raw_affiliation_strings":["Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009542542","display_name":"Prasenjit Mitra","orcid":"https://orcid.org/0000-0002-7530-9497"},"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":"Prasenjit Mitra","raw_affiliation_strings":["Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","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":["Pennsylvania State University"],"affiliations":[{"raw_affiliation_string":"Pennsylvania State University","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5072607871"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05639731,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","first_page":"9601","last_page":"9606"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9983000159263611,"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":0.9983000159263611,"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/T11937","display_name":"Research Data Management Practices","score":0.9815000295639038,"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/T14330","display_name":"Library Science and Information Systems","score":0.9567999839782715,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.9396520853042603},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8555358648300171},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7783318758010864},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.5921065807342529},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5311996340751648},{"id":"https://openalex.org/keywords/database-catalog","display_name":"Database catalog","score":0.41706582903862},{"id":"https://openalex.org/keywords/citation","display_name":"Citation","score":0.4107193648815155},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.31395214796066284}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9396520853042603},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8555358648300171},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7783318758010864},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.5921065807342529},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5311996340751648},{"id":"https://openalex.org/C65610166","wikidata":"https://www.wikidata.org/wiki/Q5227399","display_name":"Database catalog","level":4,"score":0.41706582903862},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.4107193648815155},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.31395214796066284},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1609/aaai.v33i01.33019601","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019601","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5022/4895","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1906.08470","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.08470","pdf_url":"https://arxiv.org/pdf/1906.08470","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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"},{"id":"mag:2951141188","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1906.08470.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1906.08470","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.08470","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33019601","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33019601","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5022/4895","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2951141188.pdf","grobid_xml":"https://content.openalex.org/works/W2951141188.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W926830766","https://openalex.org/W1559499673","https://openalex.org/W1969890816","https://openalex.org/W1992464666","https://openalex.org/W2012833704","https://openalex.org/W2079659743","https://openalex.org/W2085030399","https://openalex.org/W2168190036","https://openalex.org/W2253675773","https://openalex.org/W2295508865","https://openalex.org/W2555393643","https://openalex.org/W2604792366","https://openalex.org/W2604887361","https://openalex.org/W2759340467","https://openalex.org/W2777092996","https://openalex.org/W2787905620","https://openalex.org/W6642556363","https://openalex.org/W6670307327","https://openalex.org/W6691667650","https://openalex.org/W6697460127"],"related_works":["https://openalex.org/W2964694902","https://openalex.org/W2777092996","https://openalex.org/W3159409148","https://openalex.org/W2547426272","https://openalex.org/W3207741004","https://openalex.org/W2076677427","https://openalex.org/W1513581231","https://openalex.org/W1869053546","https://openalex.org/W2894841400","https://openalex.org/W3174867802","https://openalex.org/W3016988636","https://openalex.org/W2787847379","https://openalex.org/W2808058165","https://openalex.org/W2767496934","https://openalex.org/W1992438279","https://openalex.org/W2963946295","https://openalex.org/W3121496113","https://openalex.org/W2076915037","https://openalex.org/W2575555199","https://openalex.org/W2017047449"],"abstract_inverted_index":{"Automatically":[0],"extracted":[1,116],"metadata":[2,26,79,120,135,180],"from":[3,97,117],"scholarly":[4,74,186],"documents":[5],"in":[6,174],"PDF":[7],"formats":[8],"is":[9,27,36,49],"usually":[10],"noisy":[11,78],"and":[12,18,54,136,167,181],"heterogeneous,":[13],"often":[14],"containing":[15],"incomplete":[16],"fields":[17],"erroneous":[19],"values.":[20],"One":[21],"common":[22],"way":[23],"of":[24,134,160,164],"cleaning":[25],"to":[28,37,72,92,129,156,178,184],"use":[29,110],"a":[30,69,81],"bibliographic":[31],"reference":[32,82,99],"dataset.":[33,83,151],"The":[34,45,84,107,122,132],"challenge":[35],"match":[38,73,130,157],"records":[39,183],"between":[40],"corpora":[41],"with":[42,77],"high":[43,139],"precision.":[44],"existing":[46],"solution":[47],"which":[48,113],"based":[50],"on":[51,57,147],"information":[52,128],"retrieval":[53],"string":[55],"similarity":[56],"titles":[58,64],"works":[59],"well":[60],"only":[61],"if":[62],"the":[63,88,94,98,144,148,158,175],"are":[65],"cleaned.":[66],"We":[67,152],"introduce":[68],"system":[70,123,155,177],"designed":[71],"document":[75],"entities":[76],"against":[80,162],"blocking":[85],"function":[86],"uses":[87],"classic":[89],"BM25":[90],"algorithm":[91],"find":[93],"matching":[95],"candidates":[96],"data":[100],"that":[101,141],"has":[102],"been":[103],"indexed":[104],"by":[105],"ElasticSearch.":[106],"core":[108],"components":[109],"supervised":[111],"methods":[112],"combine":[114],"features":[115],"all":[118],"available":[119,126],"fields.":[121],"also":[124],"leverages":[125],"citation":[127,137],"entities.":[131],"combination":[133],"achieves":[138],"accuracy":[140],"significantly":[142],"outperforms":[143],"baseline":[145],"method":[146,170],"same":[149],"test":[150],"apply":[153],"this":[154],"database":[159],"CiteSeerX":[161,176],"Web":[163],"Science,":[165],"PubMed,":[166],"DBLP.":[168],"This":[169],"will":[171],"be":[172],"deployed":[173],"clean":[179],"link":[182],"other":[185],"big":[187],"datasets.":[188]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
