{"id":"https://openalex.org/W2188509728","doi":null,"title":"Large-scale author coreference via hierarchical entity representations","display_name":"Large-scale author coreference via hierarchical entity representations","publication_year":2013,"publication_date":"2013-05-08","ids":{"openalex":"https://openalex.org/W2188509728","mag":"2188509728"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.363.1703","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.363.1703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://openreview.net/file/9ce576d1-d9f8-45ee-bf4c-e91f5b39d5ae.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5058514754","display_name":"Michael Wick","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Wick","raw_affiliation_strings":["University of Massachusetts, Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068953995","display_name":"Ari Kobren","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ari Kobren","raw_affiliation_strings":["University of Massachusetts, Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107835063","display_name":"Andrew McCallum","orcid":"https://orcid.org/0000-0003-2843-6992","observed_orcids":["https://orcid.org/0000-0003-2843-6992"]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew McCallum","raw_affiliation_strings":["University of Massachusetts, Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts, Amherst","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":1.24,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.86361096,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.8618000149726868,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.8618000149726868,"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/T10102","display_name":"scientometrics and bibliometrics research","score":0.06759999692440033,"subfield":{"id":"https://openalex.org/subfields/3309","display_name":"Library and Information Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14330","display_name":"Library Science and Information Systems","score":0.025100000202655792,"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/author-name-disambiguation","display_name":"author name disambiguation","score":0.7839999794960022},{"id":"https://openalex.org/keywords/markov-chain-monte-carlo-inference","display_name":"Markov chain Monte Carlo inference","score":0.9169999957084656},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.6629999876022339},{"id":"https://openalex.org/keywords/bibliographic-databases","display_name":"bibliographic databases","score":0.8769999742507935},{"id":"https://openalex.org/keywords/web-of-science","display_name":"Web of Science","score":0.7739999890327454}],"concepts":[{"id":"https://openalex.org/C28076734","wikidata":"https://www.wikidata.org/wiki/Q63087","display_name":"Coreference","level":3,"score":0.9365708827972412},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8187255859375},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6930655241012573},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6178761124610901},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.5982053875923157},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5616055727005005},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5578728318214417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46917158365249634},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4359990954399109},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42848092317581177},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4280610978603363},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40731751918792725},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34348517656326294},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.28784680366516113},{"id":"https://openalex.org/C138268822","wikidata":"https://www.wikidata.org/wiki/Q1051925","display_name":"Resolution (logic)","level":2,"score":0.23783603310585022},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.13858535885810852},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.363.1703","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.363.1703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://openreview.net/file/9ce576d1-d9f8-45ee-bf4c-e91f5b39d5ae.pdf","raw_type":"text"},{"id":"mag:2188509728","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=TTFCKqmXtgaYf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W17582134","https://openalex.org/W47392883","https://openalex.org/W191584165","https://openalex.org/W1496319844","https://openalex.org/W1581262234","https://openalex.org/W1789782362","https://openalex.org/W1880262756","https://openalex.org/W2024770506","https://openalex.org/W2036216970","https://openalex.org/W2050273484","https://openalex.org/W2080527295","https://openalex.org/W2099982145","https://openalex.org/W2109215439","https://openalex.org/W2113310984","https://openalex.org/W2131193521","https://openalex.org/W2133236963","https://openalex.org/W2147706904","https://openalex.org/W2164455818"],"related_works":["https://openalex.org/W7097982668","https://openalex.org/W2099982145","https://openalex.org/W2109215439","https://openalex.org/W2597258728","https://openalex.org/W2167140078","https://openalex.org/W7095793581","https://openalex.org/W2274487744","https://openalex.org/W2808117207","https://openalex.org/W2777996367","https://openalex.org/W2145124624"],"abstract_inverted_index":{"Large-scale":[0],"author":[1,33,67,89,135],"coreference,":[2],"the":[3,19,45,85],"problem":[4],"of":[5,32,87,139],"ascribing":[6],"research":[7],"papers":[8],"to":[9,37,47,104,130,132],"real-world":[10],"authors":[11],"in":[12,137],"bibliographic":[13],"databases,":[14],"is":[15,102],"critical":[16],"for":[17,65],"mining":[18],"scientific":[20],"community.":[21],"However,":[22],"traditional":[23],"pairwise":[24],"approaches,":[25,42],"which":[26,43,101],"measure":[27],"coreference":[28,68,108],"similarity":[29],"between":[30],"pairs":[31],"mentions,":[34],"scale":[35,131],"poorly":[36],"large":[38],"databases;":[39],"and":[40,120],"streaming":[41],"lack":[44],"ability":[46],"retroactively":[48,105],"correct":[49,106],"errors,":[50],"can":[51],"suffer":[52],"from":[53],"chronically":[54],"low":[55],"accuracy.":[56],"In":[57],"this":[58],"paper":[59],"we":[60,93],"present":[61],"a":[62],"hierarchical":[63],"model":[64,75],"solving":[66],"that":[69],"overcomes":[70],"these":[71,116],"issues.":[72],"First,":[73],"our":[74],"enables":[76],"scalability":[77,123],"over":[78],"rich":[79],"entity":[80],"representations":[81],"by":[82],"compactly":[83],"organizing":[84],"mentions":[86,136],"each":[88],"into":[90],"trees.":[91],"Second,":[92],"employ":[94],"Markov":[95],"chain":[96],"Monte":[97],"Carlo":[98],"(MCMC)":[99],"inference":[100],"able":[103],"existing":[107],"errors":[109],"when":[110],"processing":[111],"new":[112],"mentions.":[113],"We":[114],"validate":[115],"two":[117],"properties":[118],"empirically,":[119],"demonstrate":[121],"further":[122],"through":[124],"asynchronous":[125],"parallel":[126],"MCMC":[127],"(allowing":[128],"us":[129],"all":[133],"150,000,000":[134],"Web":[138],"Science).":[140],"1.":[141]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-09-27T08:07:27.782135","created_date":"2016-06-24T00:00:00"}