{"id":"https://openalex.org/W2980630167","doi":"https://doi.org/10.26615/issn.2603-2821.2019_010","title":"Corpora and Processing Tools for Non-Standard Contemporary and Diachronic Balkan Slavic","display_name":"Corpora and Processing Tools for Non-Standard Contemporary and Diachronic Balkan Slavic","publication_year":2019,"publication_date":"2019-09-15","ids":{"openalex":"https://openalex.org/W2980630167","doi":"https://doi.org/10.26615/issn.2603-2821.2019_010","mag":"2980630167"},"language":"en","primary_location":{"id":"doi:10.26615/issn.2603-2821.2019_010","is_oa":true,"landing_page_url":"http://doi.org/10.26615/issn.2603-2821.2019_010","pdf_url":"https://doi.org/10.26615/issn.2603-2821.2019_010","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Student Research Workshop Associated with RANLP 2019","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.26615/issn.2603-2821.2019_010","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045661451","display_name":"Teodora Vukovi\u0107","orcid":"https://orcid.org/0000-0002-5780-5665"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Teodora Vukovi\u0107","raw_affiliation_strings":["Slavic Departement, University of Zurich, Plattenstrasse 43, Zurich"],"affiliations":[{"raw_affiliation_string":"Slavic Departement, University of Zurich, Plattenstrasse 43, Zurich","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079325053","display_name":"Nora Muheim","orcid":null},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Nora Muheim","raw_affiliation_strings":["Slavic Departement, University of Zurich, Plattenstrasse 43, Zurich"],"affiliations":[{"raw_affiliation_string":"Slavic Departement, University of Zurich, Plattenstrasse 43, Zurich","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034139734","display_name":"Olivier Andreas Winist\u00f6rfer","orcid":null},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Olivier Winist\u00f6rfer","raw_affiliation_strings":["Slavic Departement, University of Zurich, Plattenstrasse 43, Zurich"],"affiliations":[{"raw_affiliation_string":"Slavic Departement, University of Zurich, Plattenstrasse 43, Zurich","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103191814","display_name":"Ivan \u0160imko","orcid":"https://orcid.org/0000-0002-7304-5627"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ivan \u0160imko","raw_affiliation_strings":["Slavic Departement, University of Zurich, Plattenstrasse 43, Zurich"],"affiliations":[{"raw_affiliation_string":"Slavic Departement, University of Zurich, Plattenstrasse 43, Zurich","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051435862","display_name":"Anastasia Makarova","orcid":"https://orcid.org/0000-0002-0468-9867"},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Anastasia Makarova","raw_affiliation_strings":["Slavic Departement, University of Zurich, Plattenstrasse 43, Zurich"],"affiliations":[{"raw_affiliation_string":"Slavic Departement, University of Zurich, Plattenstrasse 43, Zurich","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089808380","display_name":"Sanja Bradjan","orcid":null},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Sanja Bradjan","raw_affiliation_strings":["Slavic Departement, University of Zurich, Plattenstrasse 43, Zurich"],"affiliations":[{"raw_affiliation_string":"Slavic Departement, University of Zurich, Plattenstrasse 43, Zurich","institution_ids":["https://openalex.org/I202697423"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5045661451"],"corresponding_institution_ids":["https://openalex.org/I202697423"],"apc_list":null,"apc_paid":null,"fwci":1.1744,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.83557624,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"62","last_page":"68"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14006","display_name":"Linguistics, Language Diversity, and Identity","score":0.9986000061035156,"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/T14006","display_name":"Linguistics, Language Diversity, and Identity","score":0.9986000061035156,"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/T12373","display_name":"Linguistic research and analysis","score":0.9944000244140625,"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/T12768","display_name":"Linguistics and language evolution","score":0.9847000241279602,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bulgarian","display_name":"Bulgarian","score":0.9303346872329712},{"id":"https://openalex.org/keywords/slavic-languages","display_name":"Slavic languages","score":0.8235049247741699},{"id":"https://openalex.org/keywords/lemmatisation","display_name":"Lemmatisation","score":0.7804373502731323},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6854816675186157},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.6506515741348267},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6114859580993652},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.6110862493515015},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5886558890342712},{"id":"https://openalex.org/keywords/macedonian","display_name":"Macedonian","score":0.5541083216667175},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5501927137374878},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48000091314315796}],"concepts":[{"id":"https://openalex.org/C2780343019","wikidata":"https://www.wikidata.org/wiki/Q7918","display_name":"Bulgarian","level":2,"score":0.9303346872329712},{"id":"https://openalex.org/C121894898","wikidata":"https://www.wikidata.org/wiki/Q23526","display_name":"Slavic languages","level":2,"score":0.8235049247741699},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.7804373502731323},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6854816675186157},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6506515741348267},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6114859580993652},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.6110862493515015},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5886558890342712},{"id":"https://openalex.org/C2777642646","wikidata":"https://www.wikidata.org/wiki/Q9296","display_name":"Macedonian","level":2,"score":0.5541083216667175},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5501927137374878},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48000091314315796},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.26615/issn.2603-2821.2019_010","is_oa":true,"landing_page_url":"http://doi.org/10.26615/issn.2603-2821.2019_010","pdf_url":"https://doi.org/10.26615/issn.2603-2821.2019_010","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Student Research Workshop Associated with RANLP 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:www.zora.uzh.ch:175260","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401281","display_name":"Zurich Open Repository and Archive (University of Zurich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I202697423","host_organization_name":"University of Zurich","host_organization_lineage":["https://openalex.org/I202697423"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Vukovi\u0107, Teodora; Nora, Muheim; Winist\u00f6rfer, Olivier-Andreas; Anastasia, Makarova; Ivan, \u0160imko; Sanja, Bradjan  (2019). Corpora and Processing Tools for Non-Standard Contemporary and Diachronic Balkan Slavic.  In: The 12th International Conference on Recent Advances in Natural Language Processing (RANLP 2019), Varna, Bulgaria, 2 September 2019 - 4 September 2019. INCOMA, 62-68.","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"doi:10.5167/uzh-175260","is_oa":true,"landing_page_url":"https://doi.org/10.5167/uzh-175260","pdf_url":null,"source":{"id":"https://openalex.org/S7407051291","display_name":"Universit\u00e4t Z\u00fcrich, ZORA","issn_l":null,"issn":[],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":""}],"best_oa_location":{"id":"doi:10.26615/issn.2603-2821.2019_010","is_oa":true,"landing_page_url":"http://doi.org/10.26615/issn.2603-2821.2019_010","pdf_url":"https://doi.org/10.26615/issn.2603-2821.2019_010","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Student Research Workshop Associated with RANLP 2019","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G5996440340","display_name":"\u2018Ill-bred sons\u2019, family and friends: tracing the multiple affiliations of Balkan Slavic","funder_award_id":"176378","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G6142993779","display_name":null,"funder_award_id":"00015_176378/1","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G6930740709","display_name":"Geometry, Topology and Transformation Groups","funder_award_id":"100015","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G8405232034","display_name":null,"funder_award_id":"177557","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2980630167.pdf","grobid_xml":"https://content.openalex.org/works/W2980630167.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W6305478","https://openalex.org/W165885000","https://openalex.org/W1967169497","https://openalex.org/W2250320249","https://openalex.org/W2250721602","https://openalex.org/W2252262936","https://openalex.org/W2343019173","https://openalex.org/W2400311834","https://openalex.org/W2419539795","https://openalex.org/W2526851824","https://openalex.org/W2531638282","https://openalex.org/W2573540318","https://openalex.org/W2739890504","https://openalex.org/W2786760830","https://openalex.org/W2796437857","https://openalex.org/W2801099209","https://openalex.org/W2966616872","https://openalex.org/W4244645111","https://openalex.org/W4285719527","https://openalex.org/W6691565338","https://openalex.org/W6996680150"],"related_works":["https://openalex.org/W150104121","https://openalex.org/W2795523497","https://openalex.org/W2263446221","https://openalex.org/W2261472267","https://openalex.org/W2596815692","https://openalex.org/W1855175370","https://openalex.org/W2494269529","https://openalex.org/W2969929050","https://openalex.org/W4246608874","https://openalex.org/W2079951471"],"abstract_inverted_index":{"The":[0,34,77,96,109],"paper":[1],"describes":[2],"three":[3],"corpora":[4,35,78,110],"of":[5,8,18,24,48,103,139,150],"different":[6,107],"varieties":[7,63,153],"BS":[9],"that":[10],"are":[11,64,79],"currently":[12],"being":[13,65],"developed":[14],"with":[15,154],"the":[16,22,25,46,53,87,94,100,104,120,124,127,132,137,143,148,151],"goal":[17],"providing":[19],"data":[20,105,134],"for":[21,56,61,72,136],"analysis":[23,102],"diatopic":[26],"and":[27,59,74,90,146],"diachronic":[28],"variation":[29,141],"in":[30,126,142],"non-standard":[31],"Balkan":[32,144],"Slavic.":[33],"includes":[36],"spoken":[37],"materials":[38],"from":[39,52,93,106],"Torlak,":[40],"Macedonian":[41],"dialects,":[42],"as":[43,45,67,69,129],"well":[44,68],"manuscripts":[47],"pre-standardized":[49],"Bulgarian.":[50],"Apart":[51],"texts,":[54],"tools":[55],"PoS":[57],"annotation":[58],"lemmatization":[60],"all":[62],"created,":[66],"syntactic":[70],"parsing":[71],"Torlak":[73],"Bulgarian":[75],"varieties.":[76,108],"built":[80],"using":[81],"a":[82,116],"unified":[83],"methodology,":[84],"relying":[85],"on":[86,123],"pest":[88],"practices":[89],"state-of-the-art":[91],"methods":[92],"field.":[95],"uniform":[97],"methodology":[98],"allows":[99],"contrastive":[101],"under":[111],"construction":[112],"can":[113],"be":[114],"considered":[115],"crucial":[117],"contribution":[118],"to":[119],"linguistic":[121,140],"research":[122],"languages":[125],"Balkans":[128],"they":[130],"provide":[131],"lacking":[133],"needed":[135],"studies":[138],"Slavic,":[145],"enable":[147],"comparison":[149],"said":[152],"other":[155],"neighbouring":[156],"languages.":[157]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2019-10-25T00:00:00"}
