{"id":"https://openalex.org/W2621055050","doi":"https://doi.org/10.46298/jdmdh.1385","title":"Preprocessing Greek Papyri for Linguistic Annotation","display_name":"Preprocessing Greek Papyri for Linguistic Annotation","publication_year":2017,"publication_date":"2017-06-08","ids":{"openalex":"https://openalex.org/W2621055050","doi":"https://doi.org/10.46298/jdmdh.1385","mag":"2621055050"},"language":"en","primary_location":{"id":"doi:10.46298/jdmdh.1385","doi":"https://doi.org/10.46298/jdmdh.1385","is_oa":true,"landing_page_url":"https://doi.org/10.46298/jdmdh.1385","pdf_url":null,"source":{"id":"https://openalex.org/S2736708624","display_name":"Journal of Data Mining & Digital Humanities","issn_l":"2416-5999","issn":["2416-5999"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","ddh","doaj","jufo-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311340","host_organization_name":"Nicolas Turenne","host_organization_lineage":["https://openalex.org/P4310311340"],"host_organization_lineage_names":["Nicolas Turenne"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data Mining &amp; Digital Humanities","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.46298/jdmdh.1385","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051681079","display_name":"Marja Vierros","orcid":"https://orcid.org/0000-0001-8531-7055","observed_orcids":["https://orcid.org/0000-0001-8531-7055"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marja Vierros","raw_affiliation_strings":["Department of World Cultures"],"raw_orcid":"https://orcid.org/0000-0001-8531-7055","affiliations":[{"raw_affiliation_string":"Department of World Cultures","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052605195","display_name":"Erik Henriksson","orcid":"https://orcid.org/0000-0003-0850-7554","observed_orcids":["https://orcid.org/0000-0003-0850-7554"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erik Henriksson","raw_affiliation_strings":["Department of World Cultures"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of World Cultures","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":19.0646,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.98863506,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"Special Issue on...","issue":"Towards a Digital Ecosystem:...","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"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/T14170","display_name":"Classical Studies and Philology","score":0.011099999770522118,"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":0.007000000216066837,"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/greek-papyri","display_name":"Greek papyri","score":0.9110000133514404},{"id":"https://openalex.org/keywords/treebanking","display_name":"treebanking","score":0.7620000243186951},{"id":"https://openalex.org/keywords/morphological-annotation","display_name":"morphological annotation","score":0.9430000185966492},{"id":"https://openalex.org/keywords/syntactic-annotation","display_name":"syntactic annotation","score":0.9990000128746033},{"id":"https://openalex.org/keywords/linguistic-annotation","display_name":"linguistic annotation","score":0.4009999930858612},{"id":"https://openalex.org/keywords/documentary-papyri","display_name":"documentary papyri","score":0.625},{"id":"https://openalex.org/keywords/linguistic-variation","display_name":"language variation","score":0.6200000047683716},{"id":"https://openalex.org/keywords/ancient-greek","display_name":"Ancient Greek","score":0.32499998807907104},{"id":"https://openalex.org/keywords/online-platforms","display_name":"digital platforms","score":0.4000000059604645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7279322147369385},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6601402759552002},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.6599192023277283},{"id":"https://openalex.org/C2779386606","wikidata":"https://www.wikidata.org/wiki/Q2393642","display_name":"Handwriting","level":2,"score":0.6368162035942078},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6303136348724365},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6233000755310059},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5462968945503235},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.5224437117576599},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5202418565750122},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.48834940791130066},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.44086840748786926},{"id":"https://openalex.org/C2994462464","wikidata":"https://www.wikidata.org/wiki/Q9129","display_name":"Greek language","level":2,"score":0.43698757886886597},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36435118317604065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3637329638004303},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3114103078842163},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.46298/jdmdh.1385","doi":"https://doi.org/10.46298/jdmdh.1385","is_oa":true,"landing_page_url":"https://doi.org/10.46298/jdmdh.1385","pdf_url":null,"source":{"id":"https://openalex.org/S2736708624","display_name":"Journal of Data Mining & Digital Humanities","issn_l":"2416-5999","issn":["2416-5999"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","ddh","doaj","jufo-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311340","host_organization_name":"Nicolas Turenne","host_organization_lineage":["https://openalex.org/P4310311340"],"host_organization_lineage_names":["Nicolas Turenne"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data Mining &amp; Digital Humanities","raw_type":"journal-article"},{"id":"pmh:oai:helda.helsinki.fi:10138/313221","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10138/313221","pdf_url":"https://jdmdh.episciences.org/1385/pdf","source":{"id":"https://openalex.org/S4210213322","display_name":"Ty\u00f6v\u00e4entutkimus Vuosikirja","issn_l":"0784-1272","issn":["0784-1272","1459-7780"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":["ddh","jufo-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:HAL:hal-01279493v2","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-01279493","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Data Mining and Digital Humanities, 2017, Special Issue on Computer-Aided Processing of Intertextuality in Ancient Languages, &#x27E8;10.46298/jdmdh.1385&#x27E9;","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:043b6b3b2e31469c8df02c2986b8173f","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/043b6b3b2e31469c8df02c2986b8173f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Data Mining and Digital Humanities, Vol 2016, Iss Towards a Digital Ecosystem:... (2017)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.46298/jdmdh.1385","doi":"https://doi.org/10.46298/jdmdh.1385","is_oa":true,"landing_page_url":"https://doi.org/10.46298/jdmdh.1385","pdf_url":null,"source":{"id":"https://openalex.org/S2736708624","display_name":"Journal of Data Mining & Digital Humanities","issn_l":"2416-5999","issn":["2416-5999"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","ddh","doaj","jufo-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311340","host_organization_name":"Nicolas Turenne","host_organization_lineage":["https://openalex.org/P4310311340"],"host_organization_lineage_names":["Nicolas Turenne"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data Mining &amp; Digital Humanities","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W65146440","https://openalex.org/W615815521","https://openalex.org/W639048528","https://openalex.org/W1235441020","https://openalex.org/W1549695605","https://openalex.org/W1795742324","https://openalex.org/W2210958423","https://openalex.org/W2490848127","https://openalex.org/W2557831068","https://openalex.org/W3046931776"],"related_works":["https://openalex.org/W3213853411","https://openalex.org/W7168961876","https://openalex.org/W3037501924","https://openalex.org/W7046661244","https://openalex.org/W4383181570","https://openalex.org/W4404372004","https://openalex.org/W1520472761","https://openalex.org/W7027197632","https://openalex.org/W6991663510","https://openalex.org/W7128631536"],"abstract_inverted_index":{"Greek":[0,18],"documentary":[1],"papyri":[2],"form":[3],"an":[4],"important":[5,85],"direct":[6],"source":[7],"for":[8,27],"Ancient":[9],"Greek.":[10],"It":[11],"has":[12],"been":[13],"exploited":[14],"surprisingly":[15],"little":[16],"in":[17,48,87,125],"linguistics":[19],"due":[20],"to":[21,53,91],"a":[22,34,54],"lack":[23],"of":[24,79,82,102,118,152],"good":[25],"tools":[26],"searching":[28],"linguistic":[29,137],"structures.":[30],"This":[31,110],"article":[32],"presents":[33],"new":[35,70],"tool":[36],"and":[37,60,64,77,104,131],"digital":[38,45],"platform,":[39],"\u201cSematia\u201d,":[40],"which":[41,56],"enables":[42],"transforming":[43],"the":[44,66,73,95,100,108,119,150,153],"texts":[46],"available":[47],"TEI":[49],"EpiDoc":[50],"XML":[51],"format":[52,55],"can":[57,68],"be":[58],"morphologically":[59],"syntactically":[61],"annotated":[62],"(treebanked),":[63],"where":[65],"user":[67],"add":[69],"metadata":[71],"concerning":[72],"text":[74],"type,":[75],"writer":[76],"handwriting":[78],"each":[80],"act":[81],"writing.":[83],"An":[84],"aspect":[86],"this":[88],"process":[89],"is":[90,111,124],"take":[92],"into":[93],"account":[94],"original":[96],"surviving":[97],"writing":[98],"vs.":[99],"standardization":[101],"language":[103],"supplements":[105],"made":[106],"by":[107,113],"editors.":[109],"performed":[112,144],"creating":[114],"two":[115],"different":[116],"layers":[117],"same":[120],"text.":[121],"The":[122],"platform":[123],"its":[126],"early":[127],"development":[128],"phase.":[129],"Ongoing":[130],"future":[132],"developments,":[133],"such":[134],"as":[135,140,142],"tagging":[136],"variation":[138],"phenomena":[139],"well":[141],"queries":[143],"within":[145],"Sematia,":[146],"are":[147],"discussed":[148],"at":[149],"end":[151],"article.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-10-25T09:29:13.331239","created_date":"2017-06-09T00:00:00"}
