{"id":"https://openalex.org/W4375869225","doi":"https://doi.org/10.1109/icassp49357.2023.10096769","title":"Text Classification In The Wild: A Large-Scale Long-Tailed Name Normalization Dataset","display_name":"Text Classification In The Wild: A Large-Scale Long-Tailed Name Normalization Dataset","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869225","doi":"https://doi.org/10.1109/icassp49357.2023.10096769"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096769","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5082388465","display_name":"Jiexing Qi","orcid":"https://orcid.org/0000-0002-6709-0034"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiexing Qi","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China","Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100706220","display_name":"Shuhao Li","orcid":"https://orcid.org/0009-0008-5175-7667"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuhao Li","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China","Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100764133","display_name":"Zhixin Guo","orcid":"https://orcid.org/0000-0003-0510-6851"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhixin Guo","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China","Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074884191","display_name":"Yu\u2010Sheng Huang","orcid":"https://orcid.org/0000-0002-1119-7836"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yusheng Huang","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China","Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023919188","display_name":"Chenghu Zhou","orcid":"https://orcid.org/0000-0003-3331-2302"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210160793","display_name":"Institute of Geographic Sciences and Natural Resources Research","ror":"https://ror.org/04t1cdb72","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210160793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenghu Zhou","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China","Shanghai Jiao Tong University, Shanghai, China","IGSNRR, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"IGSNRR, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210160793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090720315","display_name":"Weinan Zhang","orcid":"https://orcid.org/0000-0002-0127-2425"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weinan Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China","Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034483183","display_name":"Xinbing Wang","orcid":"https://orcid.org/0000-0002-0357-8356"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinbing Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China","Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024900991","display_name":"Zhouhan Lin","orcid":"https://orcid.org/0009-0009-7204-0689"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhouhan Lin","raw_affiliation_strings":["Shanghai Jiao Tong University,Shanghai,China","Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"46","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9980999827384949,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9980999827384949,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9966999888420105,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9955000281333923,"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/normalization","display_name":"Normalization (sociology)","score":0.7456749677658081},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7355961799621582},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6141653060913086},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5715562105178833},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.496509850025177},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.469261109828949},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4445810317993164},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4441077411174774},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4408392608165741},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4297035038471222},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4114387631416321},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3534242808818817},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15878787636756897},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09848228096961975}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7456749677658081},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7355961799621582},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6141653060913086},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5715562105178833},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.496509850025177},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.469261109828949},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4445810317993164},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4441077411174774},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4408392608165741},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4297035038471222},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4114387631416321},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3534242808818817},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15878787636756897},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09848228096961975},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096769","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1932742904","https://openalex.org/W1977518804","https://openalex.org/W2009190245","https://openalex.org/W2138621090","https://openalex.org/W2338548345","https://openalex.org/W2508953474","https://openalex.org/W2896457183","https://openalex.org/W2950627632","https://openalex.org/W2962933664","https://openalex.org/W2995197345","https://openalex.org/W3000599705","https://openalex.org/W3034369739","https://openalex.org/W3034601242","https://openalex.org/W4241411770","https://openalex.org/W6755207826","https://openalex.org/W6768920361"],"related_works":["https://openalex.org/W4254851101","https://openalex.org/W3171007296","https://openalex.org/W22115721","https://openalex.org/W2786391746","https://openalex.org/W4381430104","https://openalex.org/W2995102745","https://openalex.org/W4226059458","https://openalex.org/W2914559142","https://openalex.org/W1990237101","https://openalex.org/W3196471634"],"abstract_inverted_index":{"Real-world":[0],"data":[1,164],"usually":[2],"exhibits":[3],"a":[4,8,13,25,54,87,117],"long-tailed":[5,153,169,174,207],"distribution,":[6],"with":[7,37],"few":[9],"frequent":[10],"labels":[11],"and":[12,81,98,142,171,185,208],"lot":[14],"of":[15,20,40,160],"few-shot":[16,82,97,141],"labels.":[17],"The":[18],"study":[19,189],"institution":[21,56],"name":[22,57],"normalization":[23,58],"is":[24,172,197],"perfect":[26],"application":[27],"case":[28],"showing":[29],"this":[30,49,190,196,206],"phenomenon:":[31],"there":[32],"are":[33,66,92],"many":[34],"institutions":[35],"worldwide,":[36],"enormous":[38],"variations":[39],"their":[41],"names":[42],"in":[43],"the":[44,96,103,152,166,198],"publicly":[45],"available":[46],"literature.":[47],"In":[48],"work,":[50],"we":[51,128],"first":[52,199],"collect":[53],"large-scale":[55],"dataset":[59,156,202],"containing":[60],"over":[61],"25k":[62],"classes":[63],"whose":[64],"frequencies":[65],"naturally":[67,173],"long-tail":[68],"distributed.":[69],"We":[70,107,179],"construct":[71],"our":[72,114,130,155,193],"test":[73,144],"set":[74],"from":[75,102,120],"four":[76],"different":[77,186],"subsets:":[78],"many-,":[79],"medium-,":[80],"sets,":[83],"as":[84,86],"well":[85],"zero-shot":[88,99,143],"open":[89],"set,":[90],"which":[91],"meant":[93],"to":[94,123,147,188],"isolate":[95],"learning":[100],"scenarios":[101],"massive":[104],"many-shot":[105],"classes.":[106],"also":[108],"replicate":[109],"several":[110],"important":[111,184],"benchmarks":[112],"on":[113,140,151,205],"data,":[115],"covering":[116],"wide":[118],"range":[119],"search-based":[121],"methods":[122],"neural":[124],"network":[125],"methods.":[126],"Further,":[127],"propose":[129],"specially":[131],"pretrained,":[132],"BERT-based":[133],"model":[134],"that":[135,203],"shows":[136],"better":[137],"out-of-distribution":[138],"generalization":[139],"sets.":[145],"Compared":[146],"other":[148],"datasets":[149,170],"focusing":[150],"phenomenon,":[154],"has":[157],"one":[158],"order":[159],"magnitude":[161],"more":[162],"training":[163],"than":[165,176],"largest":[167],"existing":[168],"rather":[175],"manually":[177],"synthesized.":[178],"believe":[180],"it":[181],"provides":[182],"an":[183],"scenario":[187],"problem.":[191,211],"To":[192],"best":[194],"knowledge,":[195],"natural":[200],"language":[201],"focuses":[204],"open-set":[209],"classification":[210],"<sup":[212],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[213],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}