{"id":"https://openalex.org/W4393552162","doi":"https://doi.org/10.5281/zenodo.5801914","title":"Data for Cyrillic Reference Parsing","display_name":"Data for Cyrillic Reference Parsing","publication_year":2021,"publication_date":"2021-12-23","ids":{"openalex":"https://openalex.org/W4393552162","doi":"https://doi.org/10.5281/zenodo.5801914"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.5801914","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.5801914","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.5801914","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":["Karlsruhe Institute of Technology (KIT)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":["Karlsruhe Institute of Technology (KIT)"],"raw_orcid":"https://orcid.org/0000-0001-5028-0109","affiliations":[{"raw_affiliation_string":"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":["Karlsruhe Institute of Technology (KIT)"],"raw_orcid":"https://orcid.org/0000-0001-5458-8645","affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology (KIT)","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.9803000092506409,"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":0.9803000092506409,"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/parsing","display_name":"Parsing","score":0.7557364702224731},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7220332622528076},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5836064219474792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4733821451663971},{"id":"https://openalex.org/keywords/bottom-up-parsing","display_name":"Bottom-up parsing","score":0.4659508168697357},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.42179417610168457},{"id":"https://openalex.org/keywords/top-down-parsing","display_name":"Top-down parsing","score":0.3472733497619629},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3239611089229584}],"concepts":[{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.7557364702224731},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7220332622528076},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5836064219474792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4733821451663971},{"id":"https://openalex.org/C60690694","wikidata":"https://www.wikidata.org/wiki/Q894902","display_name":"Bottom-up parsing","level":4,"score":0.4659508168697357},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.42179417610168457},{"id":"https://openalex.org/C42560504","wikidata":"https://www.wikidata.org/wiki/Q15419395","display_name":"Top-down parsing","level":3,"score":0.3472733497619629},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3239611089229584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.5801914","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.5801914","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.5801914","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.5801914","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"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/W2792937288","https://openalex.org/W3143982968","https://openalex.org/W3088470625","https://openalex.org/W3035970863","https://openalex.org/W2619584063","https://openalex.org/W2952780262","https://openalex.org/W2804916787","https://openalex.org/W2389755172","https://openalex.org/W4320024782","https://openalex.org/W4381248170"],"abstract_inverted_index":{"We":[0],"provide":[1],"a":[2,16,40,62,104,172,200],"<strong>synthetic":[3],"reference":[4,115],"data":[5,35,54,109,118,162,180,215,224],"set</strong>":[6],"covering":[7],"over":[8,112,126],"100,000":[9,113],"labeled":[10,114,129,186],"references":[11,22,38],"(mostly":[12],"Russian":[13],"language)":[14],"and":[15,52,72,107,124,154,181,196,205],"manually":[17,128,185],"annotated":[18],"set":[19,110,119,216],"of":[20,46,65,82,91,111,140,143,159,171,194,249],"real":[21],"(771":[23],"in":[24,94],"number)":[25],"gathered":[26],"from":[27,36,243],"multidisciplinary":[28,108],"<strong>Cyrillic":[29],"script":[30,96],"publications</strong>.":[31],"<strong>Background:</strong>":[32],"Extracting":[33],"structured":[34],"bibliographic":[37],"is":[39,61,87,217],"crucial":[41],"task":[42,58],"for":[43,56,67,212,239],"the":[44,57,76,83,132,157,178,184,214,223,228,250],"creation":[45],"scholarly":[47],"databases.":[48],"While":[49],"approaches,":[50],"tools,":[51],"evaluation":[53],"sets":[55],"exist,":[59],"there":[60],"distinct":[63],"lack":[64],"support":[66],"languages":[68,123],"other":[69,74],"than":[70,75],"English":[71],"scripts":[73],"Latin":[77],"alphabet.":[78],"A":[79],"significant":[80],"portion":[81],"scientific":[84],"literature":[85],"that":[86],"thereby":[88,197],"excluded":[89],"consists":[90],"publications":[92],"written":[93],"Cyrillic":[95,122,244],"languages.":[97],"To":[98,164],"address":[99],"this":[100,144,165],"problem,":[101],"we":[102,146,167,203],"introduce":[103],"new":[105],"multilingual":[106,173],"strings.":[116],"The":[117,210],"covers":[120],"multiple":[121,148],"contains":[125],"700":[127],"references,":[130],"while":[131],"remaining":[133],"are":[134],"generated":[135],"synthetically.":[136],"With":[137],"random":[138],"samples":[139],"varying":[141],"size":[142],"data,":[145],"train":[147],"well-performing":[149],"sequence":[150],"labeling":[151],"BERT":[152,174],"models":[153],"thus":[155],"show":[156],"usability":[158],"our":[160,208],"proposed":[161],"set.":[163],"end,":[166],"showcase":[168],"an":[169,191],"implementation":[170],"model":[175,189,202],"trained":[176],"on":[177,183,207,253],"synthetic":[179],"evaluated":[182],"references.":[187],"Our":[188],"achieves":[190],"F1":[192],"score":[193],"0.93":[195],"significantly":[198],"outperforms":[199],"state-of-the-art":[201],"retrain":[204],"evaluate":[206],"data.":[209],"code":[211],"generating":[213],"available":[218],"at":[219],"https://github.com/igor261/Sequence-Labeling-for-Citation-Field-Extraction-from-Cyrillic-Script-References":[220],"When":[221],"using":[222],"set,":[225],"please":[226],"cite":[227],"following":[229],"paper:":[230],"<em>Igor":[231],"Shapiro,":[232],"Tarek":[233],"Saier,":[234],"Michael":[235],"F\u00e4rber:":[236],"\"Sequence":[237],"Labeling":[238],"Citation":[240],"Field":[241],"Extraction":[242],"Script":[245],"References\".":[246],"In":[247],"Proceedings":[248],"AAAI-22":[251],"Workshop":[252],"Scientific":[254],"Document":[255],"Understanding":[256],"(SDU@AAAI'22),":[257],"2022.</em>":[258]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
