{"id":"https://openalex.org/W2984268726","doi":"https://doi.org/10.18653/v1/k19-1081","title":"BIOfid Dataset: Publishing a German Gold Standard for Named Entity Recognition in Historical Biodiversity Literature","display_name":"BIOfid Dataset: Publishing a German Gold Standard for Named Entity Recognition in Historical Biodiversity Literature","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2984268726","doi":"https://doi.org/10.18653/v1/k19-1081","mag":"2984268726"},"language":"en","primary_location":{"id":"doi:10.18653/v1/k19-1081","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k19-1081","pdf_url":"https://www.aclweb.org/anthology/K19-1081.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":"Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/K19-1081.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003022499","display_name":"Sajawel Ahmed","orcid":null},"institutions":[{"id":"https://openalex.org/I114090438","display_name":"Goethe University Frankfurt","ror":"https://ror.org/04cvxnb49","country_code":"DE","type":"education","lineage":["https://openalex.org/I114090438"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Sajawel Ahmed","raw_affiliation_strings":["Goethe University Frankfurt"],"affiliations":[{"raw_affiliation_string":"Goethe University Frankfurt","institution_ids":["https://openalex.org/I114090438"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003652298","display_name":"Manuel Stoeckel","orcid":"https://orcid.org/0000-0002-3562-1339"},"institutions":[{"id":"https://openalex.org/I114090438","display_name":"Goethe University Frankfurt","ror":"https://ror.org/04cvxnb49","country_code":"DE","type":"education","lineage":["https://openalex.org/I114090438"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Manuel Stoeckel","raw_affiliation_strings":["Goethe University Frankfurt"],"affiliations":[{"raw_affiliation_string":"Goethe University Frankfurt","institution_ids":["https://openalex.org/I114090438"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024832363","display_name":"Christine Driller","orcid":null},"institutions":[{"id":"https://openalex.org/I2802697327","display_name":"Senckenberg - Leibniz Institution for Biodiversity and Earth System Research","ror":"https://ror.org/00xmqmx64","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I2802697327","https://openalex.org/I315704651"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christine Driller","raw_affiliation_strings":["Senckenberg Nature Research Society"],"affiliations":[{"raw_affiliation_string":"Senckenberg Nature Research Society","institution_ids":["https://openalex.org/I2802697327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054729123","display_name":"Adrian Pachzelt","orcid":"https://orcid.org/0000-0003-3748-3766"},"institutions":[{"id":"https://openalex.org/I114090438","display_name":"Goethe University Frankfurt","ror":"https://ror.org/04cvxnb49","country_code":"DE","type":"education","lineage":["https://openalex.org/I114090438"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Adrian Pachzelt","raw_affiliation_strings":["Frankfurt University Library"],"affiliations":[{"raw_affiliation_string":"Frankfurt University Library","institution_ids":["https://openalex.org/I114090438"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008340710","display_name":"Alexander Mehler","orcid":"https://orcid.org/0000-0003-2567-7539"},"institutions":[{"id":"https://openalex.org/I114090438","display_name":"Goethe University Frankfurt","ror":"https://ror.org/04cvxnb49","country_code":"DE","type":"education","lineage":["https://openalex.org/I114090438"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Mehler","raw_affiliation_strings":["Goethe University Frankfurt"],"affiliations":[{"raw_affiliation_string":"Goethe University Frankfurt","institution_ids":["https://openalex.org/I114090438"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5003022499"],"corresponding_institution_ids":["https://openalex.org/I114090438"],"apc_list":null,"apc_paid":null,"fwci":1.1561,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.84720487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"871","last_page":"880"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9954000115394592,"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/T10028","display_name":"Topic Modeling","score":0.9954000115394592,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9864000082015991,"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/german","display_name":"German","score":0.7919595241546631},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7081867456436157},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.7016206383705139},{"id":"https://openalex.org/keywords/biodiversity","display_name":"Biodiversity","score":0.6459633111953735},{"id":"https://openalex.org/keywords/publishing","display_name":"Publishing","score":0.6273801922798157},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5316446423530579},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5047320127487183},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5039185881614685},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.49879002571105957},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.497205525636673},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4283319413661957},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.421468585729599},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3947310447692871},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32783621549606323},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.15899795293807983},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15219324827194214},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.14755743741989136},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.127696692943573},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09426996111869812}],"concepts":[{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.7919595241546631},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7081867456436157},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.7016206383705139},{"id":"https://openalex.org/C130217890","wikidata":"https://www.wikidata.org/wiki/Q47041","display_name":"Biodiversity","level":2,"score":0.6459633111953735},{"id":"https://openalex.org/C151719136","wikidata":"https://www.wikidata.org/wiki/Q3972943","display_name":"Publishing","level":2,"score":0.6273801922798157},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5316446423530579},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5047320127487183},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5039185881614685},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.49879002571105957},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.497205525636673},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4283319413661957},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.421468585729599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3947310447692871},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32783621549606323},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.15899795293807983},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15219324827194214},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.14755743741989136},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.127696692943573},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09426996111869812},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/k19-1081","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k19-1081","pdf_url":"https://www.aclweb.org/anthology/K19-1081.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":"Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},{"id":"pmh:oai:publikationen.ub.uni-frankfurt.de:57720","is_oa":true,"landing_page_url":"http://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/57720","pdf_url":null,"source":{"id":"https://openalex.org/S4306400432","display_name":"Publication Server of Goethe University Frankfurt am Main (Goethe University Frankfurt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114090438","host_organization_name":"Goethe University Frankfurt","host_organization_lineage":["https://openalex.org/I114090438"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"doc-type:conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/k19-1081","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/k19-1081","pdf_url":"https://www.aclweb.org/anthology/K19-1081.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":"Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G237006784","display_name":null,"funder_award_id":"326061700","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6052429835","display_name":null,"funder_award_id":"(DFG)","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G6279457960","display_name":null,"funder_award_id":"project 13","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2984268726.pdf","grobid_xml":"https://content.openalex.org/works/W2984268726.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1505083828","https://openalex.org/W2081580037","https://openalex.org/W2144578941","https://openalex.org/W2153579005","https://openalex.org/W2183656857","https://openalex.org/W2222142803","https://openalex.org/W2250600805","https://openalex.org/W2251160521","https://openalex.org/W2251771443","https://openalex.org/W2296194829","https://openalex.org/W2296283641","https://openalex.org/W2466573295","https://openalex.org/W2740887992","https://openalex.org/W2792992299","https://openalex.org/W2880875857","https://openalex.org/W2883818012","https://openalex.org/W2896457183","https://openalex.org/W2914274808","https://openalex.org/W2952087486","https://openalex.org/W2962739339","https://openalex.org/W2963341956","https://openalex.org/W2990977009","https://openalex.org/W4294170691","https://openalex.org/W4386506836"],"related_works":["https://openalex.org/W2916255597","https://openalex.org/W3091569222","https://openalex.org/W2999302224","https://openalex.org/W1495833002","https://openalex.org/W2075635421","https://openalex.org/W3006227201","https://openalex.org/W2964631078","https://openalex.org/W3160627956","https://openalex.org/W4289715253","https://openalex.org/W2360236096"],"abstract_inverted_index":{"The":[0],"Specialized":[1],"Information":[2],"Service":[3],"Biodiversity":[4],"Research":[5],"(BIOfid)":[6],"has":[7],"been":[8],"launched":[9],"to":[10,95],"mobilize":[11],"valuable":[12],"biological":[13,58,89],"data":[14,75,94],"from":[15,38],"printed":[16],"literature":[17,41],"hidden":[18],"in":[19,62,88,111,155,161],"German":[20,33],"libraries":[21],"for":[22,76,109,139,152],"over":[23],"the":[24,43,54,63,77,137,150,156],"past":[25],"250":[26],"years.":[27],"In":[28,144],"this":[29,70,93,145],"project,":[30],"we":[31,72,116],"annotate":[32],"texts":[34],"converted":[35],"by":[36],"OCR":[37],"historical":[39],"scientific":[40],"on":[42],"biodiversity":[44,112],"of":[45,57,65,79,99,121,136,158],"plants,":[46],"birds,":[47],"moths":[48],"and":[49,67,84,104,131],"butterflies.":[50],"Our":[51],"work":[52,154],"enables":[53],"automatic":[55],"extraction":[56,160],"information":[59,159],"previously":[60],"buried":[61],"mass":[64],"papers":[66],"volumes.":[68],"For":[69],"purpose,":[71],"generated":[73,124],"training":[74],"tasks":[78],"Named":[80],"Entity":[81],"Recognition":[82,86],"(NER)":[83],"Taxa":[85],"(TR)":[87],"documents.":[90],"We":[91],"use":[92],"train":[96],"a":[97,106,118,133],"number":[98],"leading":[100],"machine":[101],"learning":[102],"tools":[103],"create":[105],"gold":[107],"standard":[108],"TR":[110,140],"literature.":[113],"More":[114],"specifically,":[115],"perform":[117],"practical":[119],"analysis":[120],"our":[122,147],"newly":[123],"BIOfid":[125],"dataset":[126],"through":[127],"various":[128],"downstream-task":[129],"evaluations":[130],"establish":[132],"new":[134],"state":[135],"art":[138],"with":[141],"80.23%":[142],"Fscore.":[143],"sense,":[146],"paper":[148],"lays":[149],"foundations":[151],"future":[153],"field":[157],"biology":[162],"texts.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
