{"id":"https://openalex.org/W7169037848","doi":"https://doi.org/10.1007/s10618-026-01239-2","title":"Palauner: policy-based active learning to augment named entity recognition datasets","display_name":"Palauner: policy-based active learning to augment named entity recognition datasets","publication_year":2026,"publication_date":"2026-07-16","ids":{"openalex":"https://openalex.org/W7169037848","doi":"https://doi.org/10.1007/s10618-026-01239-2"},"language":"en","primary_location":{"id":"doi:10.1007/s10618-026-01239-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-026-01239-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-026-01239-2.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10618-026-01239-2.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022700280","display_name":"Marco Postiglione","orcid":"https://orcid.org/0000-0003-1470-8053"},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Postiglione","raw_affiliation_strings":["Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio,21, Naples, 80125, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio,21, Naples, 80125, Italy","institution_ids":["https://openalex.org/I71267560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080628425","display_name":"Andrea Vignali","orcid":"https://orcid.org/0000-0002-0273-1056"},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Vignali","raw_affiliation_strings":["Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio,21, Naples, 80125, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio,21, Naples, 80125, Italy","institution_ids":["https://openalex.org/I71267560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080190737","display_name":"Giancarlo Sperl\u00ed","orcid":"https://orcid.org/0000-0003-4033-3777"},"institutions":[{"id":"https://openalex.org/I4210152452","display_name":"Consorzio Interuniversitario Nazionale per l'Informatica","ror":"https://ror.org/03v8v5y65","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210152452"]},{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Giancarlo Sperl\u00ed","raw_affiliation_strings":["CINI Consorzio Interuniversitario Nazionale per l\u2019Informatica, Roma, Italy","Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio,21, Naples, 80125, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CINI Consorzio Interuniversitario Nazionale per l\u2019Informatica, Roma, Italy","institution_ids":["https://openalex.org/I4210152452"]},{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio,21, Naples, 80125, Italy","institution_ids":["https://openalex.org/I71267560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141042834","display_name":"Guido Maria Secondulfo","orcid":null},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Guido Maria Secondulfo","raw_affiliation_strings":["Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio,21, Naples, 80125, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio,21, Naples, 80125, Italy","institution_ids":["https://openalex.org/I71267560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081965427","display_name":"Vincenzo Moscato","orcid":"https://orcid.org/0000-0002-0754-7696"},"institutions":[{"id":"https://openalex.org/I4210152452","display_name":"Consorzio Interuniversitario Nazionale per l'Informatica","ror":"https://ror.org/03v8v5y65","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210152452"]},{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Vincenzo Moscato","raw_affiliation_strings":["CINI Consorzio Interuniversitario Nazionale per l\u2019Informatica, Roma, Italy","Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio,21, Naples, 80125, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CINI Consorzio Interuniversitario Nazionale per l\u2019Informatica, Roma, Italy","institution_ids":["https://openalex.org/I4210152452"]},{"raw_affiliation_string":"Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II, Via Claudio,21, Naples, 80125, Italy","institution_ids":["https://openalex.org/I71267560"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5080190737"],"corresponding_institution_ids":["https://openalex.org/I4210152452","https://openalex.org/I71267560"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.91590215,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"5","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8579000234603882,"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":0.8579000234603882,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.05900000035762787,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.013100000098347664,"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/augment","display_name":"Augment","score":0.6640999913215637},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.6492000222206116},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6370000243186951},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5928999781608582},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.4862000048160553},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.45509999990463257},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4156000018119812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8267999887466431},{"id":"https://openalex.org/C2779070825","wikidata":"https://www.wikidata.org/wiki/Q760434","display_name":"Augment","level":2,"score":0.6640999913215637},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6492000222206116},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6370000243186951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.635200023651123},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5928999781608582},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5397999882698059},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.4862000048160553},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.45509999990463257},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4156000018119812},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.40059998631477356},{"id":"https://openalex.org/C121687571","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Activity recognition","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C66782513","wikidata":"https://www.wikidata.org/wiki/Q864601","display_name":"Biomedicine","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2897999882698059},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27320000529289246},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2632000148296356}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10618-026-01239-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-026-01239-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-026-01239-2.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10618-026-01239-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-026-01239-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-026-01239-2.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309590","display_name":"Universit\u00e0 degli Studi di Napoli Federico II","ror":"https://ror.org/05290cv24"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7169037848.pdf","grobid_xml":"https://content.openalex.org/works/W7169037848.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W1832693441","https://openalex.org/W1956471287","https://openalex.org/W2040298461","https://openalex.org/W2080021732","https://openalex.org/W2100627415","https://openalex.org/W2145339207","https://openalex.org/W2154142897","https://openalex.org/W2169099542","https://openalex.org/W2346452181","https://openalex.org/W2911489562","https://openalex.org/W2949071206","https://openalex.org/W2963696295","https://openalex.org/W2970641574","https://openalex.org/W3011594683","https://openalex.org/W3115908473","https://openalex.org/W3197893554","https://openalex.org/W4285106586","https://openalex.org/W4312727753","https://openalex.org/W4384697538","https://openalex.org/W4386486129","https://openalex.org/W4387363444","https://openalex.org/W4393160979","https://openalex.org/W4394996828","https://openalex.org/W4401042223","https://openalex.org/W4401338706","https://openalex.org/W4404239715","https://openalex.org/W4409150401","https://openalex.org/W4411119577","https://openalex.org/W7131793457"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Named":[1,58],"Entity":[2,59],"Recognition":[3],"(NER)":[4],"in":[5,42,123],"specialized":[6],"domains":[7],"like":[8],"biomedicine":[9],"suffers":[10],"from":[11,71,110],"acute":[12],"data":[13,20,73,142],"scarcity,":[14],"requiring":[15],"expensive":[16],"expert":[17],"annotations.":[18],"While":[19],"augmentation":[21,108,134],"offers":[22],"a":[23,61,76,137],"promising":[24],"solution,":[25],"it":[26],"inevitably":[27],"introduces":[28],"noisy":[29],"and":[30,87],"mislabeled":[31],"samples":[32,70,82],"that":[33,65,103],"can":[34],"degrade":[35],"model":[36,88],"performance.":[37,96],"This":[38],"problem":[39],"is":[40],"amplified":[41],"few-shot":[43,124],"scenarios":[44],"where":[45],"every":[46],"training":[47,141],"example":[48],"matters.":[49],"We":[50,145],"introduce":[51],"PALAUNER":[52,104],"(Policy-based":[53],"Active":[54],"Learning":[55],"to":[56,67,113],"Augment":[57],"Recognition),":[60],"reinforcement":[62],"learning":[63],"framework":[64],"learns":[66],"select":[68],"high-quality":[69],"augmented":[72],"pools.":[74],"Using":[75],"deep":[77],"Q-network,":[78],"our":[79,148],"agent":[80],"evaluates":[81],"based":[83],"on":[84,150],"content":[85],"features":[86],"predictions,":[89],"deciding":[90],"which":[91],"examples":[92],"will":[93],"improve":[94],"NER":[95],"Experiments":[97],"across":[98],"five":[99],"BioNER":[100],"benchmarks":[101],"demonstrate":[102],"consistently":[105],"enhances":[106],"diverse":[107],"methods,":[109],"simple":[111],"perturbations":[112],"GPT-based":[114],"generation.":[115],"Average":[116],"F1":[117],"improvements":[118],"are":[119],"of":[120],"0.5\u22127.1":[121],"points":[122],"settings.":[125],"PALAUNER\u2019s":[126],"modular":[127],"design":[128],"enables":[129],"seamless":[130],"integration":[131],"with":[132],"emerging":[133],"techniques,":[135],"providing":[136],"generalizable":[138],"solution":[139],"for":[140],"quality":[143],"enhancement.":[144],"publicly":[146],"release":[147],"code":[149],"GitHub:":[151],"(":[152],"https://github.com/picuslab/palauner":[153],").":[154]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-07-17T00:00:00"}