{"id":"https://openalex.org/W4385571365","doi":"https://doi.org/10.18653/v1/2023.acl-long.459","title":"Do CoNLL-2003 Named Entity Taggers Still Work Well in 2023?","display_name":"Do CoNLL-2003 Named Entity Taggers Still Work Well in 2023?","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385571365","doi":"https://doi.org/10.18653/v1/2023.acl-long.459"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.acl-long.459","doi":"https://doi.org/10.18653/v1/2023.acl-long.459","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-long.459","pdf_url":"https://aclanthology.org/2023.acl-long.459.pdf","source":{"id":"https://openalex.org/S4363608652","display_name":"Annual Meeting of the Association for Computational Linguistics (ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.acl-long.459.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048293052","display_name":"Shuheng Liu","orcid":"https://orcid.org/0000-0001-7130-1888","observed_orcids":["https://orcid.org/0000-0001-7130-1888"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuheng Liu","raw_affiliation_strings":["School of Interactive Computing Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Interactive Computing Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039096905","display_name":"Alan Ritter","orcid":"https://orcid.org/0009-0001-4602-138X","observed_orcids":["https://orcid.org/0009-0001-4602-138X"]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alan Ritter","raw_affiliation_strings":["School of Interactive Computing Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Interactive Computing Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5039096905"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":1.974,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.89046891,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8254","last_page":"8271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"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":0.9980000257492065,"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":0.00139999995008111,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":9.999999747378752e-05,"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/named-entity-recognition","display_name":"named entity recognition","score":0.9869999885559082},{"id":"https://openalex.org/keywords/conll-2003","display_name":"CoNLL-2003","score":0.9739999771118164},{"id":"https://openalex.org/keywords/temporal-drift","display_name":"temporal drift","score":0.7210000157356262},{"id":"https://openalex.org/keywords/model-generalization","display_name":"model generalization","score":0.7919999957084656},{"id":"https://openalex.org/keywords/pre-trained-transformers","display_name":"pre-trained transformer models","score":0.5590000152587891},{"id":"https://openalex.org/keywords/roberta","display_name":"RoBERTa","score":0.9789999723434448},{"id":"https://openalex.org/keywords/t5","display_name":"T5","score":0.9890000224113464},{"id":"https://openalex.org/keywords/overfitting","display_name":"overfitting","score":0.7269999980926514},{"id":"https://openalex.org/keywords/model-architecture","display_name":"model architecture","score":0.5059999823570251},{"id":"https://openalex.org/keywords/parameter-size","display_name":"parameter size","score":0.5350000262260437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8773664236068726},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8600877523422241},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.705819845199585},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6632673740386963},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6302992105484009},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5513797998428345},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5501419901847839},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.5219059586524963},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5145787596702576},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4803375005722046},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4658297896385193},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37510251998901367},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16565227508544922},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.10878923535346985},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2023.acl-long.459","doi":"https://doi.org/10.18653/v1/2023.acl-long.459","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-long.459","pdf_url":"https://aclanthology.org/2023.acl-long.459.pdf","source":{"id":"https://openalex.org/S4363608652","display_name":"Annual Meeting of the Association for Computational Linguistics (ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2212.09747","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.09747","pdf_url":"https://arxiv.org/pdf/2212.09747","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2212.09747","doi":"https://doi.org/10.48550/arxiv.2212.09747","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2212.09747","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.acl-long.459","doi":"https://doi.org/10.18653/v1/2023.acl-long.459","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.acl-long.459","pdf_url":"https://aclanthology.org/2023.acl-long.459.pdf","source":{"id":"https://openalex.org/S4363608652","display_name":"Annual Meeting of the Association for Computational Linguistics (ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1261388433","display_name":"CAREER: Large-Scale Learning for Information Extraction","funder_award_id":"2052498","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5487362199","display_name":null,"funder_award_id":"2019-19051600004","funder_id":"https://openalex.org/F4320333051","funder_display_name":"Intelligence Advanced Research Projects Activity"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320333051","display_name":"Intelligence Advanced Research Projects Activity","ror":"https://ror.org/01v3fsc55"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385571365.pdf","grobid_xml":"https://content.openalex.org/works/W4385571365.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W8550301","https://openalex.org/W1539309091","https://openalex.org/W1566289585","https://openalex.org/W1821462560","https://openalex.org/W2096765155","https://openalex.org/W2108598243","https://openalex.org/W2116522068","https://openalex.org/W2141766660","https://openalex.org/W2179519966","https://openalex.org/W2296283641","https://openalex.org/W2573492843","https://openalex.org/W2591804103","https://openalex.org/W2740215900","https://openalex.org/W2787560479","https://openalex.org/W2793978524","https://openalex.org/W2805206884","https://openalex.org/W2880875857","https://openalex.org/W2933655602","https://openalex.org/W2946558277","https://openalex.org/W2947813521","https://openalex.org/W2948902769","https://openalex.org/W2951243568","https://openalex.org/W2952087486","https://openalex.org/W2953937638","https://openalex.org/W2962902328","https://openalex.org/W2963341956","https://openalex.org/W2965373594","https://openalex.org/W2970279348","https://openalex.org/W2970771982","https://openalex.org/W2975059944","https://openalex.org/W2979826702","https://openalex.org/W2983040767","https://openalex.org/W2991486856","https://openalex.org/W3001279689","https://openalex.org/W3015468748","https://openalex.org/W3017961061","https://openalex.org/W3035067238","https://openalex.org/W3037109418","https://openalex.org/W3104382126","https://openalex.org/W3104415840","https://openalex.org/W3106433641","https://openalex.org/W3136215575","https://openalex.org/W3167136668","https://openalex.org/W3170325272","https://openalex.org/W3174266714","https://openalex.org/W3177049011","https://openalex.org/W3207715300","https://openalex.org/W3209540659","https://openalex.org/W3213460052","https://openalex.org/W3217756080","https://openalex.org/W4285190530","https://openalex.org/W4304699785","https://openalex.org/W4385572901","https://openalex.org/W4385574392","https://openalex.org/W7133218668"],"related_works":["https://openalex.org/W3208882810","https://openalex.org/W2972862903","https://openalex.org/W3099765033","https://openalex.org/W2921259037","https://openalex.org/W2970699417","https://openalex.org/W4288419306","https://openalex.org/W4312531262","https://openalex.org/W4388103534","https://openalex.org/W2987302549","https://openalex.org/W3019226033"],"abstract_inverted_index":{"The":[0],"CoNLL-2003":[1,200],"English":[2],"named":[3],"entity":[4],"recognition":[5],"(NER)":[6],"dataset":[7],"has":[8],"been":[9],"widely":[10],"used":[11],"to":[12,104,113,123,133,167],"train":[13],"and":[14,35,68,90,111,120,140],"evaluate":[15,57],"NER":[16,71,184,191],"models":[17,27,64,72,101,192],"for":[18,151],"almost":[19],"20":[20,62,188],"years.However,":[21],"it":[22],"is":[23,131],"unclear":[24],"how":[25],"well":[26,103],"that":[28,70,128,146],"are":[29,149],"trained":[30,65],"on":[31,51,66,183,197,207],"this":[32,54],"20-year-old":[33],"data":[34,106],"developed":[36],"over":[37,61,185],"a":[38],"period":[39,160],"of":[40,60,81,117,157,161,170],"decades":[41],"using":[42,95],"the":[43,58,115,137,141,162,168,186,198],"same":[44],"test":[45,124,143,201],"set":[46],"will":[47],"perform":[48],"when":[49,93],"applied":[50],"modern":[52,208],"data.In":[53],"paper,":[55],"we":[56,77],"generalization":[59],"different":[63,75],"CoNLL-2003,":[67],"show":[69],"have":[73,193],"very":[74],"generalization.Surprisingly,":[76],"find":[78],"no":[79],"evidence":[80],"performance":[82],"degradation":[83],"in":[84,165,178],"pre-trained":[85],"Transformers,":[86],"such":[87],"as":[88,190],"RoBERTa":[89],"T5,":[91],"even":[92,205],"fine-tuned":[94],"decades-old":[96],"data.We":[97,172],"investigate":[98],"why":[99],"some":[100,179],"generalize":[102],"new":[105],"while":[107],"others":[108],"do":[109],"not,":[110],"attempt":[112],"disentangle":[114],"effects":[116],"temporal":[118,134],"drift":[119],"overfitting":[121],"due":[122,132],"reuse.Our":[125],"analysis":[126],"suggests":[127],"most":[129],"deterioration":[130],"mismatch":[135],"between":[136],"pre-training":[138,163],"corpora":[139],"downstream":[142],"sets.We":[144],"found":[145,213],"four":[147],"factors":[148],"important":[150],"good":[152],"generalization:":[153],"model":[154],"architecture,":[155],"number":[156],"parameters,":[158],"time":[159],"corpus,":[164],"addition":[166],"amount":[169],"fine-tuning":[171],"suggest":[173],"current":[174],"evaluation":[175],"methods":[176],"have,":[177],"sense,":[180],"underestimated":[181],"progress":[182],"past":[187],"years,":[189],"not":[194],"only":[195],"improved":[196,204],"original":[199],"set,":[202],"but":[203],"more":[206],"data.Our":[209],"datasets":[210],"can":[211],"be":[212],"at":[214],"https://":[215],"github.com/ShuhengL/acl2023_conllpp.":[216]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}