{"id":"https://openalex.org/W4414857666","doi":"https://doi.org/10.63317/5pjzh8ma5v76","title":"CoMMA, a Large-scale Corpus of Multilingual Medieval Archives","display_name":"CoMMA, a Large-scale Corpus of Multilingual Medieval Archives","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W4414857666","doi":"https://doi.org/10.63317/5pjzh8ma5v76"},"language":"en","primary_location":{"id":"doi:10.63317/5pjzh8ma5v76","is_oa":false,"landing_page_url":"https://doi.org/10.63317/5pjzh8ma5v76","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-05299220","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076012918","display_name":"Thibault Cl\u00e9rice","orcid":"https://orcid.org/0000-0003-1852-9204"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thibault Cl\u00e9rice","raw_affiliation_strings":["ALMAnaCH - Automatic Language Modelling and ANAlysis & Computational Humanities (48 Rue Barrault, 75013 Paris - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALMAnaCH - Automatic Language Modelling and ANAlysis & Computational Humanities (48 Rue Barrault, 75013 Paris - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083756330","display_name":"Simon Gabay","orcid":"https://orcid.org/0000-0001-9094-4475"},"institutions":[{"id":"https://openalex.org/I114457229","display_name":"University of Geneva","ror":"https://ror.org/01swzsf04","country_code":"CH","type":"education","lineage":["https://openalex.org/I114457229"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Simon Gabay","raw_affiliation_strings":["UNIGE - Universit\u00e9 de Gen\u00e8ve = University of Geneva (24 rue du G\u00e9n\u00e9ral-Dufour CH - 1211 Gen\u00e8ve 4\r\nSuisse - Switzerland)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UNIGE - Universit\u00e9 de Gen\u00e8ve = University of Geneva (24 rue du G\u00e9n\u00e9ral-Dufour CH - 1211 Gen\u00e8ve 4\r\nSuisse - Switzerland)","institution_ids":["https://openalex.org/I114457229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024966814","display_name":"Malamatenia Vlachou-Efstathiou","orcid":"https://orcid.org/0000-0002-9397-356X"},"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/I159885104","display_name":"\u00c9cole Pratique des Hautes \u00c9tudes","ror":"https://ror.org/046b3cj80","country_code":"FR","type":"education","lineage":["https://openalex.org/I159885104","https://openalex.org/I2746051580"]},{"id":"https://openalex.org/I4210152518","display_name":"Laboratoire d'Informatique Gaspard-Monge","ror":"https://ror.org/04t50yk91","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I142631665","https://openalex.org/I4210145102","https://openalex.org/I4210152518","https://openalex.org/I4210154111","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I4210154111","display_name":"Universit\u00e9 Gustave Eiffel","ror":"https://ror.org/03x42jk29","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210154111"]},{"id":"https://openalex.org/I4210156313","display_name":"Institut de Recherche et d'Histoire des Textes","ror":"https://ror.org/05evznf71","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210150854","https://openalex.org/I4210156313"]},{"id":"https://openalex.org/I4387153491","display_name":"\u00c9tablissement public Campus Condorcet","ror":"https://ror.org/00cd48p72","country_code":"FR","type":"education","lineage":["https://openalex.org/I4387153491"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Malamatenia Vlachou-Efsthatiou","raw_affiliation_strings":["EPHE - \u00c9cole Pratique des Hautes \u00c9tudes (4-14 Rue Ferrus, 75014 Paris - France)","IRHT - Institut de recherche et d'histoire des textes (IRHT-CNRS, Campus Condorcet 14, cours des Humanit\u00e9s\r\n93322 Aubervilliers. - France)","LIGM - Laboratoire d'Informatique Gaspard-Monge (Universit\u00e9 Gustave Eiffel, Cit\u00e9 Descartes, B\u00e2timent Copernic, 5 bd Descartes, 77454 Marne-la-Vall\u00e9e Cedex 2 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPHE - \u00c9cole Pratique des Hautes \u00c9tudes (4-14 Rue Ferrus, 75014 Paris - France)","institution_ids":["https://openalex.org/I159885104"]},{"raw_affiliation_string":"IRHT - Institut de recherche et d'histoire des textes (IRHT-CNRS, Campus Condorcet 14, cours des Humanit\u00e9s\r\n93322 Aubervilliers. - France)","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210156313","https://openalex.org/I4387153491"]},{"raw_affiliation_string":"LIGM - Laboratoire d'Informatique Gaspard-Monge (Universit\u00e9 Gustave Eiffel, Cit\u00e9 Descartes, B\u00e2timent Copernic, 5 bd Descartes, 77454 Marne-la-Vall\u00e9e Cedex 2 - France)","institution_ids":["https://openalex.org/I4210152518","https://openalex.org/I4210154111"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090258074","display_name":"Ariane Pinche","orcid":"https://orcid.org/0000-0002-7843-5050"},"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/I4210096419","display_name":"Maison des Sciences sociales et des Humanit\u00e9s - Lyon St-\u00c9tienne","ror":"https://ror.org/00rawf147","country_code":"FR","type":"facility","lineage":["https://openalex.org/I100532134","https://openalex.org/I113428412","https://openalex.org/I1294671590","https://openalex.org/I188626449","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I4210096419","https://openalex.org/I4210123735","https://openalex.org/I4405259976","https://openalex.org/I874609350"]},{"id":"https://openalex.org/I4210156974","display_name":"Histoire, Arch\u00e9ologie, Litt\u00e9ratures des Mondes Chr\u00e9tiens et Musulmans M\u00e9di\u00e9vaux","ror":"https://ror.org/05mqwtr17","country_code":"FR","type":"facility","lineage":["https://openalex.org/I113428412","https://openalex.org/I1294671590","https://openalex.org/I188626449","https://openalex.org/I198415970","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I203339264","https://openalex.org/I4210156974","https://openalex.org/I874609350","https://openalex.org/I90669466"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ariane Pinche","raw_affiliation_strings":["CIHAM - CorpoSO - Axe transversal -  Corpor@Tech-Science ouverte (CIHAM-UMR 5648 MSH-LSE 14, avenue Berthelot \u2013 F-69363 Lyon Cedex 07 - France)","CIHAM - Histoire, Arch\u00e9ologie et Litt\u00e9ratures des mondes chr\u00e9tiens et musulmans m\u00e9di\u00e9vaux (14, avenue Berthelot - 69363 Lyon cedex 07 - France)","CNRS - Centre National de la Recherche Scientifique (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CIHAM - CorpoSO - Axe transversal -  Corpor@Tech-Science ouverte (CIHAM-UMR 5648 MSH-LSE 14, avenue Berthelot \u2013 F-69363 Lyon Cedex 07 - France)","institution_ids":["https://openalex.org/I4210096419","https://openalex.org/I4210156974"]},{"raw_affiliation_string":"CIHAM - Histoire, Arch\u00e9ologie et Litt\u00e9ratures des mondes chr\u00e9tiens et musulmans m\u00e9di\u00e9vaux (14, avenue Berthelot - 69363 Lyon cedex 07 - France)","institution_ids":[]},{"raw_affiliation_string":"CNRS - Centre National de la Recherche Scientifique (France)","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077663332","display_name":"Beno\u00eet Sagot","orcid":"https://orcid.org/0000-0002-0107-8526"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Beno\u00eet Sagot","raw_affiliation_strings":["ALMAnaCH - Automatic Language Modelling and ANAlysis & Computational Humanities (48 Rue Barrault, 75013 Paris - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ALMAnaCH - Automatic Language Modelling and ANAlysis & Computational Humanities (48 Rue Barrault, 75013 Paris - France)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":279.7143,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.99693408,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7034","last_page":"7045"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10759","display_name":"Translation Studies and Practices","score":0.9599000215530396,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10759","display_name":"Translation Studies and Practices","score":0.9599000215530396,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9156000018119812,"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/pipeline","display_name":"Pipeline (software)","score":0.6855000257492065},{"id":"https://openalex.org/keywords/corpus-linguistics","display_name":"Corpus linguistics","score":0.4684999883174896},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.39640000462532043},{"id":"https://openalex.org/keywords/text-corpus","display_name":"Text corpus","score":0.3937000036239624},{"id":"https://openalex.org/keywords/linguistic-analysis","display_name":"Linguistic analysis","score":0.38960000872612},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.2930000126361847}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6855000257492065},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.603600025177002},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6003000140190125},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5249999761581421},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49959999322891235},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.4684999883174896},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.3937000036239624},{"id":"https://openalex.org/C2987219923","wikidata":"https://www.wikidata.org/wiki/Q777864","display_name":"Linguistic analysis","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.3756999969482422},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C158886217","wikidata":"https://www.wikidata.org/wiki/Q16799549","display_name":"Latin Americans","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C24351657","wikidata":"https://www.wikidata.org/wiki/Q1026962","display_name":"Digital humanities","level":2,"score":0.2624000012874603}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.63317/5pjzh8ma5v76","is_oa":false,"landing_page_url":"https://doi.org/10.63317/5pjzh8ma5v76","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05299220v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-05299220","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"2025","raw_type":"info:eu-repo/semantics/preprint"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-05299220v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-05299220","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"2025","raw_type":"info:eu-repo/semantics/preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,52],"present":[1],"CoMMA,":[2],"a":[3],"large-scale":[4,58],"corpus":[5,15,83],"of":[6,41],"medieval":[7],"manuscripts":[8,26],"produced":[9],"through":[10],"automatic":[11],"text":[12,44],"recognition.":[13],"The":[14,71],"contains":[16],"around":[17],"2.5b":[18],"tokens":[19],"drawn":[20],"from":[21,78],"more":[22],"than":[23],"23,000":[24],"digitized":[25],"in":[27,49],"Latin":[28],"and":[29,60,62,65,88],"Old":[30],"French,":[31],"harvested":[32],"via":[33],"IIIF.":[34],"Unlike":[35],"other":[36],"resources,":[37],"it":[38],"is":[39],"made":[40],"raw,":[42],"non-normalized":[43],"enriched":[45],"with":[46],"layout":[47],"analysis":[48],"various":[50],"formats.":[51],"describe":[53],"the":[54],"pipeline":[55],"used":[56],"for":[57],"acquisition":[59],"processing,":[61],"report":[63],"quantitative":[64],"qualitative":[66],"evaluations":[67],"(average":[68],"CER":[69],"9.7%).":[70],"resulting":[72],"resource":[73],"supports":[74],"multiple":[75],"use":[76],"cases,":[77],"pretraining":[79],"language":[80],"models":[81],"to":[82],"linguistic":[84],"on":[85],"historical":[86],"languages":[87],"digital":[89],"humanities":[90],"applications.":[91]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-06T00:00:00"}
