{"id":"https://openalex.org/W3097441245","doi":null,"title":"SinNer@Clef-Hipe2020 : Sinful adaptation of SotA models for Named Entity Recognition in French and German","display_name":"SinNer@Clef-Hipe2020 : Sinful adaptation of SotA models for Named Entity Recognition in French and German","publication_year":2020,"publication_date":"2020-09-23","ids":{"openalex":"https://openalex.org/W3097441245","mag":"3097441245"},"language":"en","primary_location":{"id":"pmh:oai:HAL:hal-02984746v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-02984746","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://impresso.github.io/CLEF-HIPE-2020/","raw_type":"info:eu-repo/semantics/conferenceObject"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-02984746","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054913492","display_name":"Pedro Ortiz Su\u00e1rez","orcid":"https://orcid.org/0000-0003-0343-8852","observed_orcids":["https://orcid.org/0000-0003-0343-8852"]},"institutions":[{"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/I4405261730","display_name":"ALMANACH: Mod\u00e9lisation et analyse linguistique automatique et humanit\u00e9s computationnelles","ror":"https://ror.org/05rnwy495","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4405257605","https://openalex.org/I4405261730"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ortiz Su\u00e1rez, Pedro Javier","raw_affiliation_strings":["ALMAnaCH - Automatic Language Modelling and ANAlysis & Computational Humanities (France)","SU - Sorbonne Universite\u0301 (21 rue de l\u2019\u00c9cole de m\u00e9decine - 75006 Paris - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALMAnaCH - Automatic Language Modelling and ANAlysis & Computational Humanities (France)","institution_ids":["https://openalex.org/I4405261730"]},{"raw_affiliation_string":"SU - Sorbonne Universite\u0301 (21 rue de l\u2019\u00c9cole de m\u00e9decine - 75006 Paris - France)","institution_ids":["https://openalex.org/I39804081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082161062","display_name":"Yoann Dupont","orcid":"https://orcid.org/0000-0001-8997-6189","observed_orcids":["https://orcid.org/0000-0001-8997-6189"]},"institutions":[{"id":"https://openalex.org/I4389425349","display_name":"Sens, Texte, Informatique, Histoire","ror":"https://ror.org/02q5emw59","country_code":"FR","type":"facility","lineage":["https://openalex.org/I39804081","https://openalex.org/I4389425349"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Dupont, Yoann","raw_affiliation_strings":["STIH - Sens, Texte, Informatique, Histoire (1 rue Victor Cousin 75230 Paris cedex - France)","STIH-LC - \u00c9quipe Linguistique computationnelle (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STIH - Sens, Texte, Informatique, Histoire (1 rue Victor Cousin 75230 Paris cedex - France)","institution_ids":["https://openalex.org/I4389425349"]},{"raw_affiliation_string":"STIH-LC - \u00c9quipe Linguistique computationnelle (France)","institution_ids":["https://openalex.org/I4389425349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070835832","display_name":"Ga\u00ebl Lejeune","orcid":"https://orcid.org/0000-0002-4795-2362","observed_orcids":["https://orcid.org/0000-0002-4795-2362"]},"institutions":[{"id":"https://openalex.org/I4389425349","display_name":"Sens, Texte, Informatique, Histoire","ror":"https://ror.org/02q5emw59","country_code":"FR","type":"facility","lineage":["https://openalex.org/I39804081","https://openalex.org/I4389425349"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Lejeune, Ga\u00ebl","raw_affiliation_strings":["STIH - Sens, Texte, Informatique, Histoire (1 rue Victor Cousin 75230 Paris cedex - France)","STIH-LC - \u00c9quipe Linguistique computationnelle (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STIH - Sens, Texte, Informatique, Histoire (1 rue Victor Cousin 75230 Paris cedex - France)","institution_ids":["https://openalex.org/I4389425349"]},{"raw_affiliation_string":"STIH-LC - \u00c9quipe Linguistique computationnelle (France)","institution_ids":["https://openalex.org/I4389425349"]}]},{"author_position":"last","author":{"id":null,"display_name":"Tian, Tian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4389425349","display_name":"Sens, Texte, Informatique, Histoire","ror":"https://ror.org/02q5emw59","country_code":"FR","type":"facility","lineage":["https://openalex.org/I39804081","https://openalex.org/I4389425349"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Tian, Tian","raw_affiliation_strings":["STIH - Sens, Texte, Informatique, Histoire (1 rue Victor Cousin 75230 Paris cedex - France)","STIH-LC - \u00c9quipe Linguistique computationnelle (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"STIH - Sens, Texte, Informatique, Histoire (1 rue Victor Cousin 75230 Paris cedex - France)","institution_ids":["https://openalex.org/I4389425349"]},{"raw_affiliation_string":"STIH-LC - \u00c9quipe Linguistique computationnelle (France)","institution_ids":["https://openalex.org/I4389425349"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0796,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.22648055,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":93},"biblio":{"volume":null,"issue":null,"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":0.9980000257492065,"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":0.0006000000284984708,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9980000257492065},{"id":"https://openalex.org/keywords/historical-newspapers","display_name":"historical newspapers","score":0.8289999961853027},{"id":"https://openalex.org/keywords/french-language","display_name":"French language","score":0.7170000076293945},{"id":"https://openalex.org/keywords/german-language","display_name":"German language","score":1.0},{"id":"https://openalex.org/keywords/fasttext-embeddings","display_name":"FastText embeddings","score":0.8450000286102295},{"id":"https://openalex.org/keywords/sentence-segmentation","display_name":"sentence segmentation","score":0.921999990940094},{"id":"https://openalex.org/keywords/sinners","display_name":"sinners","score":0.47099998593330383}],"concepts":[{"id":"https://openalex.org/C107763842","wikidata":"https://www.wikidata.org/wiki/Q181040","display_name":"Clef","level":3,"score":0.963596761226654},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.8642182350158691},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8183720111846924},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7133087515830994},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.6753749847412109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6306459903717041},{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.5643887519836426},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.45544034242630005},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.423003613948822},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.36294054985046387},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0646178126335144},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.05444002151489258},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:HAL:hal-02984746v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-02984746","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://impresso.github.io/CLEF-HIPE-2020/","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-02984746v1","doi":null,"is_oa":true,"landing_page_url":"https://inria.hal.science/hal-02984746","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://impresso.github.io/CLEF-HIPE-2020/","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1990349324","https://openalex.org/W2144578941","https://openalex.org/W2160986985","https://openalex.org/W2171674772","https://openalex.org/W2885185669","https://openalex.org/W2951053127","https://openalex.org/W3034617741"],"related_works":["https://openalex.org/W7095073871","https://openalex.org/W6950140111","https://openalex.org/W2096825029","https://openalex.org/W2754577026","https://openalex.org/W2899768266","https://openalex.org/W3195399379","https://openalex.org/W2948533454","https://openalex.org/W4310925487","https://openalex.org/W3097692446","https://openalex.org/W7034069313"],"abstract_inverted_index":{"In":[0],"this":[1],"article":[2],"we":[3,37,51],"present":[4],"the":[5,9,16,79,82,90,99],"approaches":[6],"developed":[7],"by":[8],"Sorbonne-INRIA":[10],"for":[11,15,32,55,84],"NER":[12],"(SinNer)":[13],"team":[14],"CLEF-HIPE":[17],"2020":[18],"challenge":[19,28],"on":[20,24,39,98],"Named":[21,40],"Entity":[22,41],"Processing":[23],"old":[25],"newspapers.":[26],"The":[27,48],"proposed":[29,52],"various":[30],"tasks":[31],"three":[33],"languages,":[34,58],"among":[35],"them":[36],"focused":[38],"Recognition":[42],"in":[43,92],"French":[44],"and":[45,63,68,88],"German":[46,69],"texts.":[47],"best":[49],"system":[50],"ranked":[53],"third":[54],"these":[56],"two":[57],"it":[59],"uses":[60],"FastText":[61],"em-beddings":[62],"Elmo":[64],"language":[65],"models":[66],"(FrELMo":[67],"ELMo).":[70],"We":[71],"show":[72],"that":[73,89],"combining":[74],"several":[75],"word":[76],"representations":[77],"enhances":[78],"quality":[80],"of":[81],"results":[83],"all":[85],"NE":[86],"types":[87],"segmentation":[91],"sentences":[93],"has":[94],"an":[95],"important":[96],"impact":[97],"results.":[100]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2020-11-09T00:00:00"}
