{"id":"https://openalex.org/W4205417736","doi":"https://doi.org/10.1145/3493700.3493707","title":"Fine Grained Classification of Personal Data Entities with Language Models","display_name":"Fine Grained Classification of Personal Data Entities with Language Models","publication_year":2022,"publication_date":"2022-01-07","ids":{"openalex":"https://openalex.org/W4205417736","doi":"https://doi.org/10.1145/3493700.3493707"},"language":"en","primary_location":{"id":"doi:10.1145/3493700.3493707","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3493700.3493707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Joint International Conference on Data Science & Management of Data (9th ACM IKDD CODS and 27th COMAD)","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/A5021796589","display_name":"Abhinav Nagpal","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Abhinav Nagpal","raw_affiliation_strings":["VIT Vellore, IN"],"affiliations":[{"raw_affiliation_string":"VIT Vellore, IN","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042390201","display_name":"Riddhiman Dasgupta","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":"Riddhiman Dasgupta","raw_affiliation_strings":["Microsoft Corporation, IN"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, IN","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004415373","display_name":"Balaji Ganesan","orcid":"https://orcid.org/0000-0003-4604-1329"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Balaji Ganesan","raw_affiliation_strings":["IBM Research, IN"],"affiliations":[{"raw_affiliation_string":"IBM Research, IN","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5021796589"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8184,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73398932,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"130","last_page":"134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994999766349792,"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":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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":0.9883999824523926,"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/computer-science","display_name":"Computer science","score":0.8908065557479858},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7372579574584961},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7219858169555664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7039189338684082},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.6597861051559448},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6090514659881592},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5599218010902405},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5461964011192322},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48196741938591003},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4158622622489929},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36983370780944824},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06930309534072876}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8908065557479858},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7372579574584961},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7219858169555664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7039189338684082},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.6597861051559448},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6090514659881592},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5599218010902405},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5461964011192322},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48196741938591003},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4158622622489929},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36983370780944824},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06930309534072876},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3493700.3493707","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3493700.3493707","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th Joint International Conference on Data Science & Management of Data (9th ACM IKDD CODS and 27th COMAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2123442489","https://openalex.org/W2251264718","https://openalex.org/W2592329103","https://openalex.org/W2733628661","https://openalex.org/W2789018230","https://openalex.org/W2791170418","https://openalex.org/W2920807444","https://openalex.org/W2962713724","https://openalex.org/W2962739339","https://openalex.org/W2962891712","https://openalex.org/W2963956191","https://openalex.org/W2967884905","https://openalex.org/W2972582134","https://openalex.org/W3103304304","https://openalex.org/W3105604018","https://openalex.org/W3159924169","https://openalex.org/W6792210918"],"related_works":["https://openalex.org/W2382566571","https://openalex.org/W2349321798","https://openalex.org/W2366686860","https://openalex.org/W2350859087","https://openalex.org/W2387118502","https://openalex.org/W4233775131","https://openalex.org/W3037187668","https://openalex.org/W2391262724","https://openalex.org/W3036520466","https://openalex.org/W1986903754"],"abstract_inverted_index":{"Fine":[0],"grained":[1,11],"entity":[2],"classification":[3],"is":[4],"the":[5,21,47],"task":[6,49,71],"of":[7,23,50],"assigning":[8],"context-specific,":[9],"fine":[10],"labels":[12],"to":[13],"entities":[14],"extracted":[15],"in":[16],"an":[17],"NLP":[18],"Pipeline.":[19],"Before":[20],"advent":[22],"language":[24,75],"models,":[25],"several":[26],"artificial":[27],"neural":[28,66],"network":[29],"models":[30,39,45],"were":[31],"proposed":[32],"for":[33,46],"this":[34,70],"task.":[35],"We":[36,56],"revisit":[37],"these":[38],"and":[40,72],"compare":[41],"them":[42],"with":[43],"BERT-based":[44],"specific":[48],"classifying":[51],"Personal":[52],"Data":[53],"Entities":[54],"(PDE).":[55],"observe":[57],"that":[58],"using":[59],"side":[60],"information":[61],"from":[62],"rule-based":[63],"annotators":[64],"improves":[65],"model":[67],"performance":[68],"on":[69],"can":[73],"complement":[74],"models.":[76]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}