{"id":"https://openalex.org/W3208268776","doi":"https://doi.org/10.1145/3486187.3490206","title":"Spatial Named Entity Recognition in Literary Texts","display_name":"Spatial Named Entity Recognition in Literary Texts","publication_year":2021,"publication_date":"2021-11-02","ids":{"openalex":"https://openalex.org/W3208268776","doi":"https://doi.org/10.1145/3486187.3490206","mag":"3208268776"},"language":"en","primary_location":{"id":"doi:10.1145/3486187.3490206","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3486187.3490206","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 ACM SIGSPATIAL International Workshop on Geospatial Humanities","raw_type":"proceedings-article"},"type":"preprint","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/A5017837316","display_name":"Caroline Koudoro-Parfait","orcid":null},"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/I4389425349","display_name":"Sens, Texte, Informatique, Histoire","ror":"https://ror.org/02q5emw59","country_code":null,"type":"facility","lineage":["https://openalex.org/I39804081","https://openalex.org/I4389425349"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Caroline Koudoro-Parfait","raw_affiliation_strings":["Sorbonne Universit\u00e9, Paris, France","STIH - Sens, Texte, Informatique, Histoire (1 rue Victor Cousin 75230 Paris cedex - France)"],"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9, Paris, France","institution_ids":["https://openalex.org/I39804081"]},{"raw_affiliation_string":"STIH - Sens, Texte, Informatique, Histoire (1 rue Victor Cousin 75230 Paris cedex - 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"},"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/I4389425349","display_name":"Sens, Texte, Informatique, Histoire","ror":"https://ror.org/02q5emw59","country_code":null,"type":"facility","lineage":["https://openalex.org/I39804081","https://openalex.org/I4389425349"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ga\u00ebl Lejeune","raw_affiliation_strings":["Sorbonne Universit\u00e9, Paris, France","STIH - Sens, Texte, Informatique, Histoire (1 rue Victor Cousin 75230 Paris cedex - France)"],"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9, Paris, France","institution_ids":["https://openalex.org/I39804081"]},{"raw_affiliation_string":"STIH - Sens, Texte, Informatique, Histoire (1 rue Victor Cousin 75230 Paris cedex - France)","institution_ids":["https://openalex.org/I4389425349"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010298238","display_name":"Glenn Roe","orcid":"https://orcid.org/0000-0002-5611-7916"},"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Glenn Roe","raw_affiliation_strings":["Sorbonne Universit\u00e9, Paris, France"],"affiliations":[{"raw_affiliation_string":"Sorbonne Universit\u00e9, Paris, France","institution_ids":["https://openalex.org/I39804081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017837316"],"corresponding_institution_ids":["https://openalex.org/I39804081","https://openalex.org/I4389425349"],"apc_list":null,"apc_paid":null,"fwci":0.2719,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.64024386,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"13","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9962000250816345,"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":0.8359357714653015},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7988553047180176},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.7919158339500427},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6134534478187561},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5977936387062073},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5361601710319519},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48490768671035767},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.46940672397613525},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45285940170288086},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4486251473426819},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.43868914246559143},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.4162232577800751},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1614968478679657},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0797814428806305}],"concepts":[{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.8359357714653015},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7988553047180176},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.7919158339500427},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6134534478187561},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5977936387062073},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5361601710319519},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48490768671035767},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.46940672397613525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45285940170288086},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4486251473426819},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.43868914246559143},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.4162232577800751},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1614968478679657},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0797814428806305},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"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/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3486187.3490206","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3486187.3490206","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 ACM SIGSPATIAL International Workshop on Geospatial Humanities","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04028976v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04028976","pdf_url":null,"source":{"id":"https://openalex.org/S4406922398","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM, pp.13-21, 2021, 978-1-4503-9102-3/21/11. ⟨10.1145/3486187.3490206⟩","raw_type":"Proceedings"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8600000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2001642682","https://openalex.org/W2069172670","https://openalex.org/W2155381731","https://openalex.org/W2212003014","https://openalex.org/W2258158787","https://openalex.org/W2575327185","https://openalex.org/W2626885185","https://openalex.org/W2741009929","https://openalex.org/W2907705782","https://openalex.org/W2982358276","https://openalex.org/W2982632725","https://openalex.org/W2998699029","https://openalex.org/W3004524434","https://openalex.org/W3011573503","https://openalex.org/W3012289950","https://openalex.org/W3037109418","https://openalex.org/W3049158684","https://openalex.org/W3084721699","https://openalex.org/W3097441245","https://openalex.org/W3101680040","https://openalex.org/W3107096252","https://openalex.org/W3107113245","https://openalex.org/W3116669097","https://openalex.org/W3205973312","https://openalex.org/W4250638538"],"related_works":["https://openalex.org/W2186562580","https://openalex.org/W3198729192","https://openalex.org/W4255258373","https://openalex.org/W2593907245","https://openalex.org/W3000685722","https://openalex.org/W2520117834","https://openalex.org/W3133906981","https://openalex.org/W3006227201","https://openalex.org/W3160627956","https://openalex.org/W3091569222"],"abstract_inverted_index":{"Exploring":[0],"text":[1],"collections":[2],"through":[3],"named":[4],"entities":[5,151],"remains":[6,31],"a":[7,65,129],"very":[8],"common":[9],"need":[10],"for":[11,77],"scholars.":[12],"Despite":[13],"the":[14,29,34,54,60,90,96,100,123,146,162],"recent":[15],"advances":[16],"of":[17,57,62,67,75,83,92,99,122,161],"Named":[18],"Entity":[19],"Recognition":[20,47],"(NER)":[21],"systems,":[22],"more":[23,42,116,156],"efficient":[24],"and":[25,40,102,132],"easier":[26],"to":[27,44,143,158],"use,":[28],"task":[30],"problematic":[32],"when":[33],"data":[35],"is":[36,149],"not":[37,113],"born":[38],"digital":[39],"thus":[41],"prone":[43],"Optical":[45],"Character":[46],"errors.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"investigate":[53],"real":[55],"influence":[56],"noise":[58],"on":[59,95,103,128,139],"extraction":[61],"locations":[63],"in":[64,70,86,118,133],"collection":[66],"ten":[68],"books":[69],"French":[71],"exhibiting":[72],"different":[73,104],"levels":[74],"difficulties":[76],"NER":[78,110,136],"systems":[79,94,111],"(digitization":[80],"quality,":[81],"complexity":[82],"layout,":[84],"variation":[85],"language).":[87],"We":[88,107],"compare":[89],"results":[91],"various":[93],"\"clean\"":[97],"version":[98],"documents":[101],"OCRed":[105],"versions.":[106,141],"show":[108],"that":[109],"do":[112],"yield":[114],"many":[115],"errors":[117,124],"noisy":[119,140],"documents,":[120],"most":[121],"being":[125],"already":[126],"there":[127],"reference":[130],"version,":[131],"some":[134],"cases":[135],"performs":[137],"better":[138],"According":[142],"our":[144],"results,":[145],"main":[147],"problem":[148],"rare":[150],"(especially":[152],"hapax)":[153],"which":[154],"are":[155],"likely":[157],"disappear":[159],"from":[160],"output.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-02-25T23:00:34.991745","created_date":"2025-10-10T00:00:00"}