{"id":"https://openalex.org/W1601463586","doi":null,"title":"Person Name Disambiguation on the Web by Two-Stage Clustering","display_name":"Person Name Disambiguation on the Web by Two-Stage Clustering","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W1601463586","mag":"1601463586"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.330.8792","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.330.8792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nlp.uned.es/weps/weps2/papers/ITC_UT.pdf","raw_type":"text"},"volume":null,"type":"article","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/A5105217367","display_name":"Masaki Ikeda","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masaki Ikeda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shingo Ono","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shingo Ono","raw_affiliation_strings":["university of Tokyo;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"university of Tokyo;","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060421432","display_name":"Issei Sato","orcid":"https://orcid.org/0000-0002-5066-1435","observed_orcids":["https://orcid.org/0000-0002-5066-1435"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Issei Sato","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5066-1435","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101566876","display_name":"Minoru W. Yoshida","orcid":"https://orcid.org/0000-0001-5316-5958","observed_orcids":["https://orcid.org/0000-0001-5316-5958"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minoru W. Yoshida","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-5316-5958","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020912760","display_name":"Hiroshi Nakagawa","orcid":"https://orcid.org/0000-0002-3024-9136","observed_orcids":["https://orcid.org/0000-0002-3024-9136","https://orcid.org/0009-0000-5170-2588"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hiroshi Nakagawa","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3024-9136","affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.5901,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.97477914,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"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":0.9369999766349792,"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":0.9369999766349792,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.028699999675154686,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.012299999594688416,"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/person-name-disambiguation","display_name":"person name disambiguation","score":0.9940000176429749},{"id":"https://openalex.org/keywords/web-search-results","display_name":"web search results","score":0.8069999814033508},{"id":"https://openalex.org/keywords/document-clustering","display_name":"document clustering","score":0.8299999833106995},{"id":"https://openalex.org/keywords/agglomerative-hierarchical-clustering","display_name":"agglomerative clustering","score":0.9610000252723694},{"id":"https://openalex.org/keywords/named-entities","display_name":"named entities","score":0.8169999718666077},{"id":"https://openalex.org/keywords/url-features","display_name":"URL features","score":0.7570000290870667},{"id":"https://openalex.org/keywords/document-similarity","display_name":"document similarity","score":0.8230000138282776},{"id":"https://openalex.org/keywords/two-stage-clustering","display_name":"two-stage clustering","score":0.9490000009536743}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8477843403816223},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7496777176856995},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5709991455078125},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5328263640403748},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5263140201568604},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.469598650932312},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4398159682750702},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.43264198303222656},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4110868573188782},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.3857273459434509},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3660207986831665},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.31040382385253906},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.330.8792","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.330.8792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nlp.uned.es/weps/weps2/papers/ITC_UT.pdf","raw_type":"text"},{"id":"mag:1601463586","doi":null,"is_oa":false,"landing_page_url":"http://nlp.uned.es/weps/weps2/papers/ITC_UT.pdf","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":17,"referenced_works":["https://openalex.org/W1485484201","https://openalex.org/W1548663377","https://openalex.org/W1567907259","https://openalex.org/W1574901103","https://openalex.org/W1686946872","https://openalex.org/W1772558542","https://openalex.org/W1982678692","https://openalex.org/W2018063852","https://openalex.org/W2060314721","https://openalex.org/W2064742743","https://openalex.org/W2072240081","https://openalex.org/W2097734711","https://openalex.org/W2113227740","https://openalex.org/W2121080163","https://openalex.org/W2153911474","https://openalex.org/W2161682962","https://openalex.org/W2338237122"],"related_works":["https://openalex.org/W2133337392","https://openalex.org/W7097420605","https://openalex.org/W4296483","https://openalex.org/W80802106","https://openalex.org/W2584205353","https://openalex.org/W2617517354","https://openalex.org/W2740014256","https://openalex.org/W2123492197","https://openalex.org/W2350852778","https://openalex.org/W7097219865"],"abstract_inverted_index":{"The":[0],"more":[1,7],"important":[2],"web":[3,19,33],"searching":[4],"becomes,":[5],"the":[6,13,68,74,78,88,95,103,111],"we":[8,24],"have":[9],"to":[10,66,83],"focus":[11],"on":[12,43],"\u201csame":[14],"name":[15],"\u201d":[16],"problem":[17],"in":[18,32,72,87,94],"searches.":[20],"In":[21],"this":[22,99],"paper,":[23],"report":[25],"our":[26],"algorithm":[27,41,65],"for":[28,56],"disambiguating":[29],"person":[30],"names":[31],"search":[34],"results.":[35],"It":[36],"is":[37],"a":[38,62],"document":[39,57],"clustering":[40,46,64,75],"based":[42],"hierarchical":[44],"agglomerative":[45],"using":[47],"named":[48],"entities,":[49],"compound":[50],"keywords,":[51],"and":[52,105],"URLs":[53],"as":[54],"features":[55,85],"similarity":[58],"calculation.":[59],"We":[60,92,101],"propose":[61],"two-stage":[63],"improve":[67],"low":[69],"recall":[70],"values,":[71],"which":[73],"results":[76,104],"of":[77],"first":[79],"stage":[80,90],"are":[81],"used":[82,86],"extract":[84],"second":[89],"clustering.":[91],"participated":[93],"WePS-2":[96],"evaluation":[97],"with":[98,110],"algorithm.":[100],"explain":[102],"describe":[106],"other":[107],"experiments":[108],"performed":[109],"WePS-1":[112],"data":[113],"sets.":[114]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":8}],"updated_date":"2026-09-29T14:09:16.559479","created_date":"2016-06-24T00:00:00"}
