{"id":"https://openalex.org/W4387608629","doi":"https://doi.org/10.15439/2023f6694","title":"Classifying Industrial Sectors from German Textual Data with a Domain Adapted Transformer","display_name":"Classifying Industrial Sectors from German Textual Data with a Domain Adapted Transformer","publication_year":2023,"publication_date":"2023-09-26","ids":{"openalex":"https://openalex.org/W4387608629","doi":"https://doi.org/10.15439/2023f6694"},"language":"en","primary_location":{"id":"doi:10.15439/2023f6694","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2023f6694","pdf_url":"https://annals-csis.org/proceedings/2023/drp/pdf/6694.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://annals-csis.org/proceedings/2023/drp/pdf/6694.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092550206","display_name":"Richard Fechner","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134559","display_name":"Federal Institute for Vocational Education and Training","ror":"https://ror.org/0420tmj11","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210134559"]},{"id":"https://openalex.org/I8087733","display_name":"University of T\u00fcbingen","ror":"https://ror.org/03a1kwz48","country_code":"DE","type":"education","lineage":["https://openalex.org/I8087733"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Richard Fechner","raw_affiliation_strings":["University of T\u00fcbingen, Germany","Federal Institute for Vocational Education and Training (BIBB), Bonn, Germany,"],"affiliations":[{"raw_affiliation_string":"University of T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I8087733"]},{"raw_affiliation_string":"Federal Institute for Vocational Education and Training (BIBB), Bonn, Germany,","institution_ids":["https://openalex.org/I4210134559"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047464344","display_name":"Jens D\u00f6rpinghaus","orcid":"https://orcid.org/0000-0003-0245-7752"},"institutions":[{"id":"https://openalex.org/I4210134559","display_name":"Federal Institute for Vocational Education and Training","ror":"https://ror.org/0420tmj11","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210134559"]},{"id":"https://openalex.org/I16264642","display_name":"Koblenz University of Applied Sciences","ror":"https://ror.org/04j351e79","country_code":"DE","type":"education","lineage":["https://openalex.org/I16264642"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jens D\u00f6rpinghaus","raw_affiliation_strings":["Federal Institute for Vocational Education and Training (BIBB), Bonn, Germany,","University Koblenz, Koblenz, Germany"],"affiliations":[{"raw_affiliation_string":"Federal Institute for Vocational Education and Training (BIBB), Bonn, Germany,","institution_ids":["https://openalex.org/I4210134559"]},{"raw_affiliation_string":"University Koblenz, Koblenz, Germany","institution_ids":["https://openalex.org/I16264642"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5093057123","display_name":"Anja Firll","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134559","display_name":"Federal Institute for Vocational Education and Training","ror":"https://ror.org/0420tmj11","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210134559"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anja Firll","raw_affiliation_strings":["Federal Institute for Vocational Education and Training (BIBB), Bonn, Germany,"],"affiliations":[{"raw_affiliation_string":"Federal Institute for Vocational Education and Training (BIBB), Bonn, Germany,","institution_ids":["https://openalex.org/I4210134559"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5092550206"],"corresponding_institution_ids":["https://openalex.org/I4210134559","https://openalex.org/I8087733"],"apc_list":null,"apc_paid":null,"fwci":0.7879,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.70171786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"35","issue":null,"first_page":"463","last_page":"470"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9842000007629395,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9842000007629395,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9598000049591064,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11719","display_name":"Data Quality and Management","score":0.9379000067710876,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.771246075630188},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7181199193000793},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.6803804636001587},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6358124613761902},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5459553003311157},{"id":"https://openalex.org/keywords/german","display_name":"German","score":0.5376943349838257},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.45691049098968506},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.452062726020813},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.43685758113861084},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.395442396402359},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3496524691581726},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32893288135528564},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32025593519210815},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2087768018245697},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12569251656532288}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.771246075630188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7181199193000793},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.6803804636001587},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6358124613761902},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5459553003311157},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.5376943349838257},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.45691049098968506},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.452062726020813},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.43685758113861084},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.395442396402359},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3496524691581726},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32893288135528564},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32025593519210815},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2087768018245697},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12569251656532288},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.15439/2023f6694","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2023f6694","pdf_url":"https://annals-csis.org/proceedings/2023/drp/pdf/6694.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:DiVA.org:lnu-131818","is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-131818","pdf_url":"https://lnu.diva-portal.org/smash/get/diva2:1889335/FULLTEXT01","source":{"id":"https://openalex.org/S4306401598","display_name":"DiVA (Linnaeus University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I223464139","host_organization_name":"Linnaeus University","host_organization_lineage":["https://openalex.org/I223464139"],"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":"Conference paper"},{"id":"pmh:oai:doaj.org/article:0081b85e5b994b0c8ede24a11f1c91ca","is_oa":true,"landing_page_url":"https://doaj.org/article/0081b85e5b994b0c8ede24a11f1c91ca","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Annals of computer science and information systems, Vol 35, Pp 463-470 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.15439/2023f6694","is_oa":true,"landing_page_url":"https://doi.org/10.15439/2023f6694","pdf_url":"https://annals-csis.org/proceedings/2023/drp/pdf/6694.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4387608629.pdf"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1550206324","https://openalex.org/W1565201084","https://openalex.org/W2013486904","https://openalex.org/W2036812737","https://openalex.org/W2071684038","https://openalex.org/W2891188270","https://openalex.org/W2965090413","https://openalex.org/W3105625590","https://openalex.org/W3131214434","https://openalex.org/W3139227741","https://openalex.org/W4214861446","https://openalex.org/W4221143046","https://openalex.org/W4377130677","https://openalex.org/W4385245566","https://openalex.org/W4385573387","https://openalex.org/W4393462224","https://openalex.org/W6739901393","https://openalex.org/W6766347941","https://openalex.org/W6785658961"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W1978893398","https://openalex.org/W2201908702","https://openalex.org/W4381094582","https://openalex.org/W2369625323","https://openalex.org/W2364579609","https://openalex.org/W1977906818","https://openalex.org/W1522139108","https://openalex.org/W2353528968","https://openalex.org/W1967674543"],"abstract_inverted_index":{"For":[0],"economics":[1],"and":[2,8,19,32,48,72,127,153],"sociological":[3],"research,":[4],"lists":[5],"of":[6,26,58,67,130],"industries":[7],"their":[9],"branches":[10],"are":[11],"widely":[12],"used":[13],"in":[14],"research":[15,39,80],"to":[16,37,44,77,150],"categorize":[17,95],"data":[18,62,69,149],"get":[20],"an":[21,110],"overview":[22],"on":[23,60,137],"different":[24,30,38,45],"types":[25],"industries.":[27],"However,":[28],"many":[29],"taxonomies":[31],"ordering":[33],"schema":[34],"exist,":[35],"due":[36,43],"focus":[40,55],"but":[41],"also":[42,82],"national":[46],"scenarios":[47],"interests.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53,93,141],"will":[54,108],"without":[56],"loss":[57],"generality":[59],"regional":[61],"from":[63,87],"Germany.":[64],"Manual":[65],"annotation":[66],"textual":[68,96,148],"is":[70],"time-consuming":[71],"tedious,":[73],"naturally":[74],"giving":[75],"rise":[76],"our":[78],"initial":[79],"question,":[81],"highly":[83],"inspired":[84],"by":[85,104],"questions":[86],"computational":[88],"social":[89],"sciences:":[90],"How":[91],"can":[92],"automatically":[94],"data,":[97],"e.g.":[98],"job":[99],"advertisements":[100],"or":[101],"business":[102],"Profiles,":[103],"industrial":[105],"sectors":[106],"We":[107,120],"present":[109],"approach":[111],"towards":[112],"classification":[113],"using":[114],"a":[115],"pre-trained":[116],"domain-adapted":[117,123,134],"Transformer":[118,135],"model.":[119],"find":[121],"that":[122],"models":[124,136],"generalize":[125],"better":[126],"outperform":[128],"state":[129],"the":[131],"art":[132],"non":[133],"Out-Of-Distribution":[138],"data.":[139],"Additionally,":[140],"open":[142],"source":[143],"two":[144],"novel":[145],"data-sets":[146],"mapping":[147],"WZ2008":[151],"sections":[152],"divisions,":[154],"enabling":[155],"further":[156],"research.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-02-28T09:26:25.869077","created_date":"2025-10-10T00:00:00"}
