{"id":"https://openalex.org/W3114950584","doi":"https://doi.org/10.18653/v1/2020.coling-main.598","title":"German\u2019s Next Language Model","display_name":"German\u2019s Next Language Model","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3114950584","doi":"https://doi.org/10.18653/v1/2020.coling-main.598","mag":"3114950584"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.coling-main.598","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.598","pdf_url":"https://www.aclweb.org/anthology/2020.coling-main.598.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 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/2020.coling-main.598.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029572924","display_name":"Branden Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138660","display_name":"Bavarian State Library","ror":"https://ror.org/031h71w90","country_code":"DE","type":"archive","lineage":["https://openalex.org/I4210138660"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Branden Chan","raw_affiliation_strings":["Bayerische Staatsbibliothek Mnchen Digital Library/Munich Digitization Center","Bayerische Staatsbibliothek M\u00fcnchen Digital Library/Munich Digitization Center"],"affiliations":[{"raw_affiliation_string":"Bayerische Staatsbibliothek Mnchen Digital Library/Munich Digitization Center","institution_ids":["https://openalex.org/I4210138660"]},{"raw_affiliation_string":"Bayerische Staatsbibliothek M\u00fcnchen Digital Library/Munich Digitization Center","institution_ids":["https://openalex.org/I4210138660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024609215","display_name":"Stefan Schweter","orcid":"https://orcid.org/0000-0002-7190-2090"},"institutions":[{"id":"https://openalex.org/I4210138660","display_name":"Bavarian State Library","ror":"https://ror.org/031h71w90","country_code":"DE","type":"archive","lineage":["https://openalex.org/I4210138660"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Schweter","raw_affiliation_strings":["Bayerische Staatsbibliothek Mnchen Digital Library/Munich Digitization Center","Bayerische Staatsbibliothek M\u00fcnchen Digital Library/Munich Digitization Center"],"affiliations":[{"raw_affiliation_string":"Bayerische Staatsbibliothek Mnchen Digital Library/Munich Digitization Center","institution_ids":["https://openalex.org/I4210138660"]},{"raw_affiliation_string":"Bayerische Staatsbibliothek M\u00fcnchen Digital Library/Munich Digitization Center","institution_ids":["https://openalex.org/I4210138660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047807531","display_name":"Timo M\u00f6ller","orcid":null},"institutions":[{"id":"https://openalex.org/I4210138660","display_name":"Bavarian State Library","ror":"https://ror.org/031h71w90","country_code":"DE","type":"archive","lineage":["https://openalex.org/I4210138660"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Timo M\u00f6ller","raw_affiliation_strings":["Bayerische Staatsbibliothek M\u00fcnchen Digital Library/Munich Digitization Center"],"affiliations":[{"raw_affiliation_string":"Bayerische Staatsbibliothek M\u00fcnchen Digital Library/Munich Digitization Center","institution_ids":["https://openalex.org/I4210138660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5029572924"],"corresponding_institution_ids":["https://openalex.org/I4210138660"],"apc_list":null,"apc_paid":null,"fwci":15.5094,"has_fulltext":true,"cited_by_count":177,"citation_normalized_percentile":{"value":0.99252127,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6788","last_page":"6796"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T13629","display_name":"Text Readability and Simplification","score":0.9902999997138977,"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":0.8826248049736023},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7934581637382507},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7892447710037231},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7860136032104492},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6614813804626465},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5905635952949524},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5821502804756165},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5404502153396606},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5149605870246887},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4108770191669464},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3490162193775177},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.14791974425315857},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13692975044250488}],"concepts":[{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.8826248049736023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7934581637382507},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7892447710037231},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7860136032104492},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6614813804626465},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5905635952949524},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5821502804756165},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5404502153396606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5149605870246887},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4108770191669464},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3490162193775177},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.14791974425315857},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13692975044250488},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2020.coling-main.598","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.598","pdf_url":"https://www.aclweb.org/anthology/2020.coling-main.598.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 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2020.coling-main.598","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.598","pdf_url":"https://www.aclweb.org/anthology/2020.coling-main.598.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 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3114950584.pdf","grobid_xml":"https://content.openalex.org/works/W3114950584.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W630532510","https://openalex.org/W2483215953","https://openalex.org/W2795038878","https://openalex.org/W2802642435","https://openalex.org/W2880875857","https://openalex.org/W2896457183","https://openalex.org/W2911227954","https://openalex.org/W2946119234","https://openalex.org/W2948902769","https://openalex.org/W2950018712","https://openalex.org/W2962739339","https://openalex.org/W2963026768","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2965373594","https://openalex.org/W2980282514","https://openalex.org/W2986154550","https://openalex.org/W2989539713","https://openalex.org/W2995647371","https://openalex.org/W2996035354","https://openalex.org/W2996428491","https://openalex.org/W3009095382","https://openalex.org/W3013027210","https://openalex.org/W3032816972","https://openalex.org/W3035390927","https://openalex.org/W3102391739","https://openalex.org/W3216234416","https://openalex.org/W4287760320","https://openalex.org/W4287824654","https://openalex.org/W4287993739","https://openalex.org/W4294152847","https://openalex.org/W4308264370","https://openalex.org/W4381683870","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W4287644835","https://openalex.org/W3092281475","https://openalex.org/W3098003361","https://openalex.org/W3158596343","https://openalex.org/W4285322112","https://openalex.org/W4292794239","https://openalex.org/W4385572030"],"abstract_inverted_index":{"In":[0],"this":[1],"work":[2],"we":[3,40,98],"present":[4],"the":[5,10,26,33,104,119],"experiments":[6],"which":[7],"lead":[8],"to":[9,43,108,118],"creation":[11],"of":[12,35,50,62],"our":[13,78],"BERT":[14],"and":[15,22,32,53,64,77,86],"ELECTRA":[16],"based":[17],"German":[18,96,106],"language":[19],"models,":[20,97],"GBERT":[21],"GELECTRA.":[23],"By":[24,92],"varying":[25],"input":[27],"training":[28,74],"data,":[29],"model":[30,90],"size,":[31],"presence":[34],"Whole":[36],"Word":[37],"Masking":[38],"(WWM)":[39],"were":[41],"able":[42],"attain":[44],"SoTA":[45],"performance":[46],"across":[47],"a":[48],"set":[49],"document":[51],"classification":[52],"named":[54],"entity":[55],"recognition":[56],"(NER)":[57],"tasks":[58],"for":[59],"both":[60,82],"models":[61,76,102,107,112],"base":[63],"large":[65],"size.":[66],"We":[67],"adopt":[68],"an":[69],"evaluation":[70],"driven":[71],"approach":[72],"in":[73],"these":[75,101],"results":[79],"indicate":[80],"that":[81,100],"adding":[83],"more":[84],"data":[85],"utilizing":[87],"WWM":[88],"improve":[89],"performance.":[91],"benchmarking":[93],"against":[94],"existing":[95],"show":[99],"are":[103],"best":[105],"date.":[109],"Our":[110],"trained":[111],"will":[113],"be":[114],"made":[115],"publicly":[116],"available":[117],"research":[120],"community.":[121]},"counts_by_year":[{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":31},{"year":2023,"cited_by_count":53},{"year":2022,"cited_by_count":30},{"year":2021,"cited_by_count":33}],"updated_date":"2026-02-26T08:16:20.718346","created_date":"2025-10-10T00:00:00"}