{"id":"https://openalex.org/W4415069746","doi":"https://doi.org/10.26615/978-954-452-105-9-006","title":"GeistBERT: Breathing Life into German NLP","display_name":"GeistBERT: Breathing Life into German NLP","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415069746","doi":"https://doi.org/10.26615/978-954-452-105-9-006"},"language":"en","primary_location":{"id":"doi:10.26615/978-954-452-105-9-006","doi":"https://doi.org/10.26615/978-954-452-105-9-006","is_oa":true,"landing_page_url":"https://doi.org/10.26615/978-954-452-105-9-006","pdf_url":"https://doi.org/10.26615/978-954-452-105-9-006","source":{"id":"https://openalex.org/S7407120445","display_name":"Workshop on Beyond English: Natural Language Processing for all Languages in an Era of Large Language Models","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Beyond English: Natural Language Processing for all Languages in an Era of Large Language Models","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.26615/978-954-452-105-9-006","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029151960","display_name":"Raphael Scheible","orcid":"https://orcid.org/0000-0003-2067-5569","observed_orcids":["https://orcid.org/0000-0003-2067-5569"]},"institutions":[{"id":"https://openalex.org/I115891769","display_name":"Universidade dos A\u00e7ores","ror":"https://ror.org/04276xd64","country_code":"PT","type":"education","lineage":["https://openalex.org/I115891769"]},{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE","PT"],"is_corresponding":false,"raw_author_name":"Raphael Scheible-Schmitt","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich, Germany & IS2E - Intelligent Systems, Science and Engineering, LIACC polo on Azores University, Ponta Delgada, Portugal"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich, Germany & IS2E - Intelligent Systems, Science and Engineering, LIACC polo on Azores University, Ponta Delgada, Portugal","institution_ids":["https://openalex.org/I115891769","https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033575564","display_name":"Johann Frei","orcid":"https://orcid.org/0000-0003-0323-0904","observed_orcids":["https://orcid.org/0000-0003-0323-0904"]},"institutions":[{"id":"https://openalex.org/I179225836","display_name":"University of Augsburg","ror":"https://ror.org/03p14d497","country_code":"DE","type":"education","lineage":["https://openalex.org/I179225836"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johann Frei","raw_affiliation_strings":["Chair of IT Infrastructure for Translational Medical Research, Faculty of Applied Computer Science, University of Augsburg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of IT Infrastructure for Translational Medical Research, Faculty of Applied Computer Science, University of Augsburg, Germany","institution_ids":["https://openalex.org/I179225836"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25366117,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"42","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9907000064849854,"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":0.9907000064849854,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0071000000461936,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.0005000000237487257,"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/roberta","display_name":"RoBERTa","score":0.7910000085830688},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"named entity recognition","score":0.9539999961853027},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.9089999794960022},{"id":"https://openalex.org/keywords/natural-language-inference","display_name":"natural language inference","score":0.9810000061988831},{"id":"https://openalex.org/keywords/conll-2003","display_name":"CoNLL-2003","score":0.7229999899864197}],"concepts":[{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.9233999848365784},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7294999957084656},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.7031999826431274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7002999782562256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6855999827384949},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5001000165939331},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.475600004196167},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.41929998993873596},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.36910000443458557},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36480000615119934},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.3093000054359436},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.2687999904155731}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.26615/978-954-452-105-9-006","doi":"https://doi.org/10.26615/978-954-452-105-9-006","is_oa":true,"landing_page_url":"https://doi.org/10.26615/978-954-452-105-9-006","pdf_url":"https://doi.org/10.26615/978-954-452-105-9-006","source":{"id":"https://openalex.org/S7407120445","display_name":"Workshop on Beyond English: Natural Language Processing for all Languages in an Era of Large Language Models","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Beyond English: Natural Language Processing for all Languages in an Era of Large Language Models","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.11903","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2506.11903","pdf_url":"https://arxiv.org/pdf/2506.11903","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.2506.11903","doi":"https://doi.org/10.48550/arxiv.2506.11903","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.11903","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.26615/978-954-452-105-9-006","doi":"https://doi.org/10.26615/978-954-452-105-9-006","is_oa":true,"landing_page_url":"https://doi.org/10.26615/978-954-452-105-9-006","pdf_url":"https://doi.org/10.26615/978-954-452-105-9-006","source":{"id":"https://openalex.org/S7407120445","display_name":"Workshop on Beyond English: Natural Language Processing for all Languages in an Era of Large Language Models","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop on Beyond English: Natural Language Processing for all Languages in an Era of Large Language Models","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415069746.pdf","grobid_xml":"https://content.openalex.org/works/W4415069746.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3114950584","https://openalex.org/W4404781950","https://openalex.org/W3203667772","https://openalex.org/W2982364408","https://openalex.org/W4412886796","https://openalex.org/W4309111272","https://openalex.org/W4414317303","https://openalex.org/W3159496320","https://openalex.org/W2899768266","https://openalex.org/W4416429971"],"abstract_inverted_index":{"Advances":[0],"in":[1,147,159,164],"transformer-based":[2],"language":[3,41],"models":[4,140],"have":[5],"highlighted":[6],"the":[7,30,34,63,100,171],"benefits":[8],"of":[9,33,94],"languagespecific":[10],"pre-training":[11],"on":[12,46,80,102],"high-quality":[13],"corpora.In":[14],"this":[15],"context,":[16],"German":[17,35,40,84,165],"NLP":[18,56],"stands":[19],"to":[20,29,38],"gain":[21],"from":[22,74],"updated":[23],"architectures":[24],"and":[25,50,72,89,118,126,141],"modern":[26],"datasets":[27],"tailored":[28],"linguistic":[31],"characteristics":[32],"language.GeistBERT":[36],"seeks":[37],"improve":[39],"processing":[42],"by":[43],"incrementally":[44],"training":[45],"a":[47,81,90,143],"diverse":[48],"corpus":[49,85],"optimizing":[51],"model":[52,77,101],"performance":[53],"across":[54,134],"various":[55],"tasks.We":[57],"pre-trained":[58],"GeistBERT":[59,169],"using":[60,122],"fairseq,":[61],"following":[62],"RoBERTa":[64],"base":[65,139],"configuration":[66],"with":[67,86],"Whole":[68],"Word":[69],"Masking":[70],"(WWM),":[71],"initialized":[73],"GottBERT":[75],"weights.The":[76],"was":[78],"trained":[79],"1.3":[82],"TB":[83],"dynamic":[87],"masking":[88],"fixed":[91],"sequence":[92],"length":[93],"512":[95],"tokens.For":[96],"evaluation,":[97],"we":[98,167],"fine-tuned":[99],"standard":[103],"downstream":[104],"tasks,":[105,136],"including":[106],"NER":[107],"(CoNLL":[108],"2003,":[109],"GermEval":[110,148],"2014),":[111],"text":[112,151],"classification":[113,160],"(GermEval":[114],"2018":[115,149],"coarse/fine,":[116],"10kGNAD),":[117],"NLI":[119],"(German":[120],"XNLI),":[121],"F":[123],"1":[124],"score":[125],"accuracy":[127],"as":[128],"evaluation":[129],"metrics.GeistBERT":[130],"achieved":[131],"strong":[132],"results":[133],"all":[135],"leading":[137],"among":[138],"setting":[142],"new":[144],"state-of-the-art":[145],"(SOTA)":[146],"fine":[150],"classification.It":[152],"also":[153],"outperformed":[154],"several":[155],"larger":[156],"models,":[157],"particularly":[158],"benchmarks.To":[161],"support":[162],"research":[163],"NLP,":[166],"release":[168],"under":[170],"MIT":[172],"license.":[173]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2025-10-11T00:00:00"}