{"id":"https://openalex.org/W2411309731","doi":"https://doi.org/10.1145/2910896.2925465","title":"Inventor Name Disambiguation for a Patent Database Using a Random Forest and DBSCAN","display_name":"Inventor Name Disambiguation for a Patent Database Using a Random Forest and DBSCAN","publication_year":2016,"publication_date":"2016-06-10","ids":{"openalex":"https://openalex.org/W2411309731","doi":"https://doi.org/10.1145/2910896.2925465","mag":"2411309731"},"language":"en","primary_location":{"id":"doi:10.1145/2910896.2925465","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2910896.2925465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM/IEEE-CS on 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/A5019980812","display_name":"Kunho Kim","orcid":"https://orcid.org/0009-0006-4087-2577"},"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":"Kunho Kim","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054253075","display_name":"Madian Khabsa","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Madian Khabsa","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"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, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019980812"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":3.2315,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.92194195,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"269","last_page":"270"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998000264167786,"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":0.9998000264167786,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9556000232696533,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9506999850273132,"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/computer-science","display_name":"Computer science","score":0.8171595335006714},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6702607870101929},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6658722162246704},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5468820929527283},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5364388227462769},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5121438503265381},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4963443875312805},{"id":"https://openalex.org/keywords/dbscan","display_name":"DBSCAN","score":0.47335171699523926},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4662771224975586},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43049710988998413},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4238916337490082},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33672797679901123},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.07086604833602905}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8171595335006714},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6702607870101929},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6658722162246704},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5468820929527283},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5364388227462769},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5121438503265381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4963443875312805},{"id":"https://openalex.org/C46576248","wikidata":"https://www.wikidata.org/wiki/Q1114630","display_name":"DBSCAN","level":5,"score":0.47335171699523926},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4662771224975586},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43049710988998413},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4238916337490082},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33672797679901123},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.07086604833602905},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2910896.2925465","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2910896.2925465","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th ACM/IEEE-CS on Joint Conference on Digital Libraries","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"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":9,"referenced_works":["https://openalex.org/W1490467549","https://openalex.org/W1673310716","https://openalex.org/W1999254925","https://openalex.org/W2011239631","https://openalex.org/W2080099271","https://openalex.org/W2906926620","https://openalex.org/W2911964244","https://openalex.org/W3122640307","https://openalex.org/W6758076146"],"related_works":["https://openalex.org/W3163639875","https://openalex.org/W3176449234","https://openalex.org/W2767235736","https://openalex.org/W2353158678","https://openalex.org/W4225278791","https://openalex.org/W2045002201","https://openalex.org/W2971352445","https://openalex.org/W4322502698","https://openalex.org/W2604015980","https://openalex.org/W2889302474"],"abstract_inverted_index":{"Inventor":[0],"name":[1,27,52,59],"disambiguation":[2],"is":[3,22,65,75,82,92],"the":[4,76,95,107,124,139,154],"task":[5,21],"that":[6,44],"distinguishes":[7],"each":[8,70,116],"unique":[9],"inventor":[10,14,58,73,85,130],"from":[11,142],"all":[12,43,150],"other":[13],"records":[15,74,131],"in":[16,29,134],"a":[17,36,40],"patent":[18,126],"database.":[19],"This":[20],"essential":[23],"for":[24,84],"processing":[25],"person":[26],"queries":[28],"order":[30],"to":[31,35,57,67,105,153],"get":[32],"information":[33],"related":[34],"specific":[37],"inventor,":[38],"e.g.":[39],"list":[41],"of":[42,72,109],"inventor's":[45],"patents.":[46],"Using":[47],"earlier":[48],"work":[49],"on":[50,123,138],"author":[51],"disambiguation,":[53],"we":[54],"apply":[55],"it":[56],"disambiguation.":[60],"A":[61],"random":[62,96],"forest":[63,97],"classifier":[64],"trained":[66],"classify":[68],"whether":[69],"pair":[71],"same":[77],"person.":[78],"The":[79],"DBSCAN":[80],"algorithm":[81,148],"use":[83],"record":[86,110],"clustering,":[87],"and":[88,112],"its":[89],"distance":[90],"function":[91],"derived":[93],"using":[94],"classifier.":[98],"For":[99],"scalability,":[100],"blocking":[101],"functions":[102],"are":[103],"used":[104],"reduce":[106],"complexity":[108],"matching":[111],"enable":[113],"parallelization":[114],"since":[115],"block":[117],"can":[118],"be":[119],"run":[120],"simultaneously.":[121],"Tested":[122],"USPTO":[125,143],"database,":[127],"12":[128],"million":[129],"were":[132],"disambiguated":[133],"6.5":[135],"hours.":[136],"Evaluation":[137],"labeled":[140],"datasets":[141],"PatentsView":[144],"competition":[145],"shows":[146],"our":[147],"outperforms":[149],"algorithms":[151],"submitted":[152],"competition.":[155]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}