{"id":"https://openalex.org/W4393516196","doi":"https://doi.org/10.5281/zenodo.4708696","title":"Data for Training and Evaluating Metadata Extraction Models based on 15 Thousand Cyrillic Script Publications","display_name":"Data for Training and Evaluating Metadata Extraction Models based on 15 Thousand Cyrillic Script Publications","publication_year":2021,"publication_date":"2021-04-22","ids":{"openalex":"https://openalex.org/W4393516196","doi":"https://doi.org/10.5281/zenodo.4708696"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:4708696","is_oa":true,"landing_page_url":"https://zenodo.org/record/4708696","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"info:eu-repo/semantics/other"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/4708696","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051563182","display_name":"Johan Krause","orcid":"https://orcid.org/0000-0002-5080-3587"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Krause, Johan","raw_affiliation_strings":["Institute AIFB, Karlsruhe Institute of Technology (KIT)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute AIFB, Karlsruhe Institute of Technology (KIT)","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083810978","display_name":"I. R. Shapiro","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Shapiro, Igor","raw_affiliation_strings":["Institute AIFB, Karlsruhe Institute of Technology (KIT)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute AIFB, Karlsruhe Institute of Technology (KIT)","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035495986","display_name":"Tarek Saier","orcid":"https://orcid.org/0000-0001-5028-0109"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Saier, Tarek","raw_affiliation_strings":["Institute AIFB, Karlsruhe Institute of Technology (KIT)"],"raw_orcid":"https://orcid.org/0000-0001-5028-0109","affiliations":[{"raw_affiliation_string":"Institute AIFB, Karlsruhe Institute of Technology (KIT)","institution_ids":["https://openalex.org/I102335020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031600582","display_name":"Michael F\u00e4rber","orcid":"https://orcid.org/0000-0001-5458-8645"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"F\u00e4rber, Michael","raw_affiliation_strings":["Institute AIFB, Karlsruhe Institute of Technology (KIT)"],"raw_orcid":"https://orcid.org/0000-0001-5458-8645","affiliations":[{"raw_affiliation_string":"Institute AIFB, Karlsruhe Institute of Technology (KIT)","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9919000267982483,"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":0.9919000267982483,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9714000225067139,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/metadata","display_name":"Metadata","score":0.8372177481651306},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7483097314834595},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5380380153656006},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3849087655544281},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3059609532356262}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.8372177481651306},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483097314834595},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5380380153656006},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3849087655544281},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3059609532356262}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:4708696","is_oa":true,"landing_page_url":"https://zenodo.org/record/4708696","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"info:eu-repo/semantics/other"},{"id":"doi:10.5281/zenodo.4708696","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.4708696","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"dataset"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:4708696","is_oa":true,"landing_page_url":"https://zenodo.org/record/4708696","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"info:eu-repo/semantics/other"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2382021449","https://openalex.org/W2095118173","https://openalex.org/W2104269053","https://openalex.org/W2106424170","https://openalex.org/W1985426483","https://openalex.org/W2501188010","https://openalex.org/W4299935056"],"abstract_inverted_index":{"<strong>Description</strong><br>":[0],"Data":[1],"for":[2,9,46],"training":[3],"and":[4,22,38,48,85,88,91],"evaluating":[5,49],"sequence":[6,30],"labeling":[7,31],"models":[8],"metadata":[10],"extraction":[11],"based":[12],"on":[13,56,101],"15,553":[14],"Cyrillic":[15],"script":[16],"language":[17],"papers":[18],"spanning":[19],"27":[20],"years":[21],"three":[23],"languages.":[24],"For":[25,58],"each":[26],"paper,":[27],"ground":[28],"truth":[29],"output":[32],"is":[33],"provided":[34],"in":[35,79],"TEI":[36],"format":[37],"as":[39],"annotated":[40],"plain":[41],"text.":[42],"The":[43],"<strong>code</strong>":[44],"used":[45],"creating":[47],"the":[50,67,98],"data":[51,68],"set":[52],"can":[53,61],"be":[54],"found":[55],"GitHub.":[57],"<strong>citing</strong>,":[59],"you":[60],"refer":[62],"to":[63],"our":[64],"paper":[65],"introducing":[66],"set:":[69],"<pre><code>@inproceedings{kssf-2021-cyrillic,":[70],"title":[71],"=":[72,82,95,106],"{{Bootstrapping":[73],"Multilingual":[74],"Metadata":[75],"Extraction:":[76],"A":[77],"Showcase":[78],"Cyrillic}},":[80],"author":[81],"{Krause,":[83],"Johan":[84],"Shapiro,":[86],"Igor":[87],"Saier,":[89],"Tarek":[90],"F{\\\"a}rber,":[92],"Michael},":[93],"booktitle":[94],"{Proceedings":[96],"of":[97],"Second":[99],"Workshop":[100],"Scholarly":[102],"Document":[103],"Processing},":[104],"year":[105],"{2021}":[107],"}</code></pre>":[108]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}