{"id":"https://openalex.org/W3012358066","doi":"https://doi.org/10.1007/978-3-030-45442-5_48","title":"Contextualized Embeddings in Named-Entity Recognition: An Empirical Study on Generalization","display_name":"Contextualized Embeddings in Named-Entity Recognition: An Empirical Study on Generalization","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3012358066","doi":"https://doi.org/10.1007/978-3-030-45442-5_48","mag":"3012358066"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-45442-5_48","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-45442-5_48","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-030-45442-5_48.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-030-45442-5_48.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064059414","display_name":"Bruno Taill\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210159731","display_name":"LIP6","ror":"https://ror.org/05krcen59","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210159245","https://openalex.org/I4210159731"]},{"id":"https://openalex.org/I95549939","display_name":"BNP Paribas (France)","ror":"https://ror.org/02v616z87","country_code":"FR","type":"company","lineage":["https://openalex.org/I95549939"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Bruno Taill\u00e9","raw_affiliation_strings":["BNP Paribas, Paris, France","Sorbonne Universit\u00e9, CNRS, Laboratoire d\u2019Informatique de Paris 6, LIP6, Paris, France","Sorbonne Universit\u00e9, CNRS, Laboratoire d'Informatique de Paris 6, LIP6, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BNP Paribas, Paris, France","institution_ids":["https://openalex.org/I95549939"]},{"raw_affiliation_string":"Sorbonne Universit\u00e9, CNRS, Laboratoire d\u2019Informatique de Paris 6, LIP6, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210159731"]},{"raw_affiliation_string":"Sorbonne Universit\u00e9, CNRS, Laboratoire d'Informatique de Paris 6, LIP6, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210159731"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044389669","display_name":"Vincent Guigue","orcid":"https://orcid.org/0000-0002-1450-5566"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210159731","display_name":"LIP6","ror":"https://ror.org/05krcen59","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210159245","https://openalex.org/I4210159731"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Vincent Guigue","raw_affiliation_strings":["Sorbonne Universit\u00e9, CNRS, Laboratoire d\u2019Informatique de Paris 6, LIP6, Paris, France","Sorbonne Universit\u00e9, CNRS, Laboratoire d'Informatique de Paris 6, LIP6, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9, CNRS, Laboratoire d\u2019Informatique de Paris 6, LIP6, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210159731"]},{"raw_affiliation_string":"Sorbonne Universit\u00e9, CNRS, Laboratoire d'Informatique de Paris 6, LIP6, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210159731"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103252936","display_name":"Patrick Gallinari","orcid":"https://orcid.org/0000-0002-5679-0617"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I39804081","display_name":"Sorbonne Universit\u00e9","ror":"https://ror.org/02en5vm52","country_code":"FR","type":"education","lineage":["https://openalex.org/I39804081"]},{"id":"https://openalex.org/I4210159731","display_name":"LIP6","ror":"https://ror.org/05krcen59","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210159245","https://openalex.org/I4210159731"]},{"id":"https://openalex.org/I4210161401","display_name":"Criteo (France)","ror":"https://ror.org/04vyg0r47","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210161401"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Patrick Gallinari","raw_affiliation_strings":["Criteo AI Lab, Paris, France","Sorbonne Universit\u00e9, CNRS, Laboratoire d\u2019Informatique de Paris 6, LIP6, Paris, France","Sorbonne Universit\u00e9, CNRS, Laboratoire d'Informatique de Paris 6, LIP6, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Criteo AI Lab, Paris, France","institution_ids":["https://openalex.org/I4210161401"]},{"raw_affiliation_string":"Sorbonne Universit\u00e9, CNRS, Laboratoire d\u2019Informatique de Paris 6, LIP6, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210159731"]},{"raw_affiliation_string":"Sorbonne Universit\u00e9, CNRS, Laboratoire d'Informatique de Paris 6, LIP6, Paris, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210159731"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5064059414"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I39804081","https://openalex.org/I4210159731","https://openalex.org/I95549939"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":1.7248,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.87495933,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"383","last_page":"391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9970999956130981,"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/T13629","display_name":"Text Readability and Simplification","score":0.9611999988555908,"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":0.8424973487854004},{"id":"https://openalex.org/keywords/contextualization","display_name":"Contextualization","score":0.7329877018928528},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7034564018249512},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.6711429357528687},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6705141067504883},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.619257926940918},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5764737129211426},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5684539079666138},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5404072999954224},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5263919830322266},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41269126534461975},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18143367767333984},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.10728242993354797},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09902012348175049},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08411610126495361}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8424973487854004},{"id":"https://openalex.org/C2780712339","wikidata":"https://www.wikidata.org/wiki/Q5165204","display_name":"Contextualization","level":3,"score":0.7329877018928528},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7034564018249512},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.6711429357528687},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6705141067504883},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.619257926940918},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5764737129211426},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5684539079666138},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5404072999954224},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5263919830322266},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41269126534461975},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18143367767333984},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.10728242993354797},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09902012348175049},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08411610126495361},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-030-45442-5_48","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-45442-5_48","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-030-45442-5_48.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:pubmedcentral.nih.gov:7148073","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7148073","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Advances in Information Retrieval","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1007/978-3-030-45442-5_48","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-45442-5_48","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-030-45442-5_48.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3012358066.pdf","grobid_xml":"https://content.openalex.org/works/W3012358066.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1566289585","https://openalex.org/W1940872118","https://openalex.org/W2051840895","https://openalex.org/W2158899491","https://openalex.org/W2250539671","https://openalex.org/W2296283641","https://openalex.org/W2525778437","https://openalex.org/W2573492843","https://openalex.org/W2609608256","https://openalex.org/W2611669587","https://openalex.org/W2760505947","https://openalex.org/W2787560479","https://openalex.org/W2818616479","https://openalex.org/W2880875857","https://openalex.org/W2894706950","https://openalex.org/W2948384082","https://openalex.org/W2949433733","https://openalex.org/W2951714314","https://openalex.org/W2952638691","https://openalex.org/W2962739339","https://openalex.org/W2963026768","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2964052092","https://openalex.org/W4285719527","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W1687432146","https://openalex.org/W1591874556","https://openalex.org/W3216994056","https://openalex.org/W2185608106","https://openalex.org/W3046258185","https://openalex.org/W1548083239","https://openalex.org/W2268232908","https://openalex.org/W205610463","https://openalex.org/W2893240344","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Contextualized":[0],"embeddings":[1,74],"use":[2],"unsupervised":[3],"language":[4,102],"model":[5,103],"pretraining":[6],"to":[7,29,106],"compute":[8],"word":[9],"representations":[10],"depending":[11],"on":[12,100,118],"their":[13],"context.":[14],"This":[15],"is":[16,27,124],"intuitively":[17],"useful":[18],"for":[19,91],"generalization,":[20],"especially":[21,95],"in":[22],"Named-Entity":[23],"Recognition":[24],"where":[25],"it":[26],"crucial":[28],"detect":[30],"mentions":[31,77,93],"never":[32],"seen":[33],"during":[34],"training.":[35],"However,":[36],"standard":[37],"English":[38],"benchmarks":[39],"overestimate":[40],"the":[41,68,119],"importance":[42],"of":[43,49,67,71],"lexical":[44,52],"over":[45],"contextual":[46],"features":[47],"because":[48],"an":[50,64],"unrealistic":[51],"overlap":[53],"between":[54],"train":[55],"and":[56,80],"test":[57],"mentions.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62],"perform":[63],"empirical":[65],"analysis":[66],"generalization":[69],"capabilities":[70],"state-of-the-art":[72],"contextualized":[73],"by":[75,78],"separating":[76],"novelty":[79],"with":[81],"out-of-domain":[82,117],"evaluation.":[83],"We":[84],"show":[85],"that":[86],"they":[87],"are":[88],"particularly":[89],"beneficial":[90],"unseen":[92],"detection,":[94],"out-of-domain.":[96],"For":[97],"models":[98],"trained":[99],"CoNLL03,":[101],"contextualization":[104],"leads":[105],"a":[107],"+1.2%":[108],"maximal":[109],"relative":[110],"micro-F1":[111],"score":[112],"increase":[113],"in-domain":[114],"against":[115],"+13%":[116],"WNUT":[120],"dataset":[121],"(The":[122],"code":[123],"available":[125],"at":[126],"https://github.com/btaille/contener":[127],").":[128]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}