{"id":"https://openalex.org/W4412887728","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1098","title":"A Classifier of Word-Level Variants in Witnesses of Biblical Hebrew Manuscripts","display_name":"A Classifier of Word-Level Variants in Witnesses of Biblical Hebrew Manuscripts","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887728","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1098"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1098","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1098","pdf_url":"https://aclanthology.org/2025.findings-acl.1098.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.1098.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099442728","display_name":"Iglika Nikolova-Stoupak","orcid":"https://orcid.org/0000-0001-5230-3458"},"institutions":[{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Iglika Nikolova-Stoupak","raw_affiliation_strings":["Research Centre \u00c9critures , EA 3943 , Universit\u00e9 de Lorraine , 57000 Metz , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Centre \u00c9critures , EA 3943 , Universit\u00e9 de Lorraine , 57000 Metz , France","institution_ids":["https://openalex.org/I90183372"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066715241","display_name":"Maxime Amblard","orcid":"https://orcid.org/0000-0002-2924-475X"},"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/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Maxime Amblard","raw_affiliation_strings":["LORIA , UMR 7503 , Universit\u00e9 de Lorraine , CNRS , Inria , 54000 Nancy , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LORIA , UMR 7503 , Universit\u00e9 de Lorraine , CNRS , Inria , 54000 Nancy , France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838","https://openalex.org/I90183372"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105612384","display_name":"Sophie Robert-Hayek","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/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sophie Robert-Hayek","raw_affiliation_strings":["LORIA , UMR 7503 , Universit\u00e9 de Lorraine , CNRS , Inria , 54000 Nancy , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LORIA , UMR 7503 , Universit\u00e9 de Lorraine , CNRS , Inria , 54000 Nancy , France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838","https://openalex.org/I90183372"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115404782","display_name":"Fr\u00e9d\u00e9rique Rey","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/I4210121838","display_name":"Laboratoire Lorrain de Recherche en Informatique et ses Applications","ror":"https://ror.org/02vnf0c38","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I277688954","https://openalex.org/I4210107720","https://openalex.org/I4210121838","https://openalex.org/I4210159245","https://openalex.org/I90183372"]},{"id":"https://openalex.org/I90183372","display_name":"Universit\u00e9 de Lorraine","ror":"https://ror.org/04vfs2w97","country_code":"FR","type":"education","lineage":["https://openalex.org/I90183372"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fr\u00e9d\u00e9rique Rey","raw_affiliation_strings":["LORIA , UMR 7503 , Universit\u00e9 de Lorraine , CNRS , Inria , 54000 Nancy , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LORIA , UMR 7503 , Universit\u00e9 de Lorraine , CNRS , Inria , 54000 Nancy , France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210121838","https://openalex.org/I90183372"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19149291,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21313","last_page":"21329"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14210","display_name":"Historical and Linguistic Studies","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T14210","display_name":"Historical and Linguistic Studies","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10362","display_name":"Biblical Studies and Interpretation","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/1212","display_name":"Religious studies"},"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":0.9282000064849854,"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/hebrew","display_name":"Hebrew","score":0.7487995624542236},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6098352670669556},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.592226505279541},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.582639217376709},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5525116324424744},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5006442070007324},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.46288013458251953},{"id":"https://openalex.org/keywords/hebrew-bible","display_name":"Hebrew Bible","score":0.4491288363933563},{"id":"https://openalex.org/keywords/biblical-studies","display_name":"Biblical studies","score":0.2818445563316345},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.19932901859283447},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.16757580637931824},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.15805110335350037}],"concepts":[{"id":"https://openalex.org/C91304198","wikidata":"https://www.wikidata.org/wiki/Q9288","display_name":"Hebrew","level":2,"score":0.7487995624542236},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6098352670669556},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.592226505279541},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.582639217376709},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5525116324424744},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5006442070007324},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.46288013458251953},{"id":"https://openalex.org/C65264089","wikidata":"https://www.wikidata.org/wiki/Q732870","display_name":"Hebrew Bible","level":3,"score":0.4491288363933563},{"id":"https://openalex.org/C194105502","wikidata":"https://www.wikidata.org/wiki/Q794605","display_name":"Biblical studies","level":2,"score":0.2818445563316345},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.19932901859283447},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.16757580637931824},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.15805110335350037}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1098","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1098","pdf_url":"https://aclanthology.org/2025.findings-acl.1098.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05466840v1","is_oa":false,"landing_page_url":"https://hal.science/hal-05466840","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://2025.aclweb.org/","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1098","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1098","pdf_url":"https://aclanthology.org/2025.findings-acl.1098.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6100000143051147,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5771122683","display_name":"SHERBET - Stemmatology for the HEbRew BiblE Transmission","funder_award_id":"ANR-23-CE38-0006","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887728.pdf","grobid_xml":"https://content.openalex.org/works/W4412887728.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1558215493","https://openalex.org/W1976009970","https://openalex.org/W2084800428","https://openalex.org/W2009267686","https://openalex.org/W2068961711","https://openalex.org/W2317694233","https://openalex.org/W2044179353","https://openalex.org/W2336151987","https://openalex.org/W4401178363","https://openalex.org/W2296205523"],"abstract_inverted_index":{"The":[0],"current":[1],"project":[2],"is":[3,52,72,86,129,172],"inscribed":[4],"within":[5,149],"the":[6,11,20,23,30,34,47,56,92,119,139,143,147,157,164,178,186],"field":[7],"of":[8,15,26,49,70,83,91,134,169],"stemmatology":[9],"or":[10,64],"study":[12],"and/or":[13],"reconstruction":[14],"textual":[16],"transmission":[17],"based":[18,45,117],"on":[19,46,118],"relationship":[21],"between":[22,146,166],"available":[24],"witnesses":[25],"given":[27],"texts.In":[28],"particular,":[29],"variants":[31],"(differences)":[32],"at":[33],"word-level":[35],"in":[36,39,79],"manuscripts":[37],"written":[38],"Biblical":[40],"Hebrew":[41],"are":[42,131,160],"addressed.A":[43],"dataset":[44],"Book":[48],"Ben":[50],"Sira":[51],"manually":[53],"annotated":[54],"for":[55,122],"following":[57],"variant":[58],"categories:":[59],"'plus/minus',":[60],"'inversion',":[61],"'morphological',":[62],"'lexical'":[63],"'unclassifiable'.A":[65],"strong":[66],"classifier":[67,85,153],"(F1":[68],"value":[69],"0.80)":[71],"then":[73],"trained":[74],"to":[75,138],"predict":[76],"these":[77],"categories":[78],"collated":[80],"(aligned)":[81],"pairs":[82,141],"witnesses.The":[84],"non-neural":[87],"and":[88,106,142,182],"makes":[89],"use":[90],"two":[93,167],"words":[94,148],"themselves":[95],"as":[96,98,154,156,176],"well":[97,155],"part-of-speech":[99],"(POS)":[100],"tags,":[101],"hand-crafted":[102],"rules":[103],"per":[104,177],"category,":[105],"additional":[107],"synthetically":[108],"derived":[109,184],"data.Other":[110],"models":[111],"experimented":[112],"with":[113,185],"include":[114],"neural":[115],"ones":[116],"state-of-the-art":[120],"model":[121],"Modern":[123],"Hebrew,":[124],"DictaBERT.Other":[125],"features":[126],"whose":[127],"relevance":[128],"tested":[130],"different":[132],"types":[133],"morphological":[135,170],"information":[136],"pertaining":[137],"word":[140],"Levenshtein":[144],"distance":[145],"a":[150],"pair.The":[151],"strongest":[152],"used":[158],"data":[159],"made":[161],"publicly":[162],"available.Coincidentally,":[163],"corelation":[165],"sets":[168],"labels":[171],"investigated:":[173],"professionally":[174],"established":[175],"Qumran-Digital":[179],"online":[180],"library":[181],"automatically":[183],"sub-model":[187],"DictaBERT-morph.":[188]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}