{"id":"https://openalex.org/W7140077255","doi":"https://doi.org/10.18653/v1/2026.sigturk-1.1","title":"SindBERT, the Sailor: Charting the Seas of Turkish NLP","display_name":"SindBERT, the Sailor: Charting the Seas of Turkish NLP","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140077255","doi":"https://doi.org/10.18653/v1/2026.sigturk-1.1"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.sigturk-1.1","doi":"https://doi.org/10.18653/v1/2026.sigturk-1.1","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.sigturk-1.1","pdf_url":"https://aclanthology.org/2026.sigturk-1.1.pdf","source":{"id":"https://openalex.org/S7407120482","display_name":"Workshop on Natural Language Processing for Turkic Languages (SIGTURK)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 Second Workshop Natural Language Processing for Turkic Languages (SIGTURK 2026)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.sigturk-1.1.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126838959","display_name":"Raphael Schmitt","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]},{"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"],"is_corresponding":false,"raw_author_name":"Raphael Schmitt","raw_affiliation_strings":["Institute of General Practice , Faculty of Medicine and Medical Center , University of Freiburg , Germany,","School of Computation, Information and Technology , Technical University of Munich , Germany,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of General Practice , Faculty of Medicine and Medical Center , University of Freiburg , Germany,","institution_ids":["https://openalex.org/I161046081"]},{"raw_affiliation_string":"School of Computation, Information and Technology , Technical University of Munich , Germany,","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024609215","display_name":"Stefan Schweter","orcid":"https://orcid.org/0000-0002-7190-2090","observed_orcids":["https://orcid.org/0000-0002-7190-2090"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Schweter","raw_affiliation_strings":["Independent Researcher , Holzkirchen , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher , Holzkirchen , Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.9362,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95144213,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9467999935150146,"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":0.9467999935150146,"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":0.04899999871850014,"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":0.000699999975040555,"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/turkish-language-models","display_name":"Turkish language models","score":0.7670000195503235},{"id":"https://openalex.org/keywords/morphologically-rich-languages","display_name":"morphologically rich languages","score":0.9559999704360962},{"id":"https://openalex.org/keywords/part-of-speech-tagging","display_name":"part-of-speech tagging","score":0.777999997138977},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"named entity recognition","score":1.0},{"id":"https://openalex.org/keywords/offensive-language-identification","display_name":"offensive language detection","score":0.9990000128746033},{"id":"https://openalex.org/keywords/linguistic-acceptability","display_name":"linguistic acceptability","score":0.746999979019165},{"id":"https://openalex.org/keywords/corpus-quality","display_name":"corpus quality","score":0.4950000047683716},{"id":"https://openalex.org/keywords/scaling-laws","display_name":"scaling laws","score":0.4569999873638153},{"id":"https://openalex.org/keywords/berturk","display_name":"BERTurk","score":0.7409999966621399},{"id":"https://openalex.org/keywords/multilingual-nlp","display_name":"multilingual NLP","score":0.5299999713897705}],"concepts":[{"id":"https://openalex.org/C2781121862","wikidata":"https://www.wikidata.org/wiki/Q256","display_name":"Turkish","level":2,"score":0.6122000217437744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5335000157356262},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5076000094413757},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4880000054836273},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4616999924182892},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.4368000030517578},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2483000010251999},{"id":"https://openalex.org/C2781291010","wikidata":"https://www.wikidata.org/wiki/Q178580","display_name":"Period (music)","level":2,"score":0.23929999768733978},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2168000042438507}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.sigturk-1.1","doi":"https://doi.org/10.18653/v1/2026.sigturk-1.1","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.sigturk-1.1","pdf_url":"https://aclanthology.org/2026.sigturk-1.1.pdf","source":{"id":"https://openalex.org/S7407120482","display_name":"Workshop on Natural Language Processing for Turkic Languages (SIGTURK)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 Second Workshop Natural Language Processing for Turkic Languages (SIGTURK 2026)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.21364","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2510.21364","pdf_url":"https://arxiv.org/pdf/2510.21364","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.2510.21364","doi":"https://doi.org/10.48550/arxiv.2510.21364","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.21364","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:10.18653/v1/2026.sigturk-1.1","doi":"https://doi.org/10.18653/v1/2026.sigturk-1.1","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.sigturk-1.1","pdf_url":"https://aclanthology.org/2026.sigturk-1.1.pdf","source":{"id":"https://openalex.org/S7407120482","display_name":"Workshop on Natural Language Processing for Turkic Languages (SIGTURK)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 Second Workshop Natural Language Processing for Turkic Languages (SIGTURK 2026)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320324306","display_name":"Bayerische Akademie der Wissenschaften","ror":"https://ror.org/001rdaz60"},{"id":"https://openalex.org/F4320331433","display_name":"Bayerisches Staatsministerium f\u00fcr Wissenschaft und Kunst","ror":null},{"id":"https://openalex.org/F4320334763","display_name":"Leibniz-Gemeinschaft","ror":"https://ror.org/01n6r0e97"},{"id":"https://openalex.org/F4320336863","display_name":"Leibniz-Rechenzentrum","ror":"https://ror.org/05558nw16"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140077255.pdf","grobid_xml":"https://content.openalex.org/works/W7140077255.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7171693927","https://openalex.org/W7117696150","https://openalex.org/W3159472594","https://openalex.org/W4293863334","https://openalex.org/W6941393739","https://openalex.org/W4391462072","https://openalex.org/W7204451237","https://openalex.org/W4399207489","https://openalex.org/W7140146518","https://openalex.org/W4417155120"],"abstract_inverted_index":{"Transformer":[0],"models":[1,141,191],"have":[2],"revolutionized":[3],"NLP,":[4,26],"yet":[5],"many":[6],"morphologically":[7,187],"rich":[8,188],"languages":[9],"remain":[10],"underrepresented":[11],"in":[12,49,102,186,201],"large-scale":[13,30,58],"pretraining":[14],"efforts.With":[15],"SindBERT,":[16],"we":[17],"set":[18],"out":[19],"to":[20],"chart":[21],"the":[22,28,56,77,95,99,132,175,180,195],"seas":[23],"of":[24,40,104,177,183],"Turkish":[25,41,90,126,166],"providing":[27],"first":[29,57],"RoBERTa-based":[31],"encoder":[32],"for":[33,63,119,165],"Turkish.Trained":[34],"from":[35],"scratch":[36],"on":[37,67,174],"312":[38],"GB":[39],"text":[42],"(mC4,":[43],"OSCAR23,":[44],"Wikipedia),":[45],"SindBERT":[46,66,85,157,190],"is":[47],"released":[48,163,193],"both":[50,159,202],"base":[51],"and":[52,76,91,121,149,168,179,198,204],"large":[53,96],"configurations,":[54],"representing":[55],"encoder-only":[59],"language":[60,74],"model":[61],"available":[62,200],"Turkish.We":[64],"evaluate":[65],"partof-speech":[68],"tagging,":[69],"named":[70],"entity":[71],"recognition,":[72],"offensive":[73],"detection,":[75],"TUR-BLIMP":[78],"linguistic":[79],"acceptability":[80],"benchmark.Our":[81],"results":[82],"show":[83],"that":[84,124,146],"performs":[86],"competitively":[87],"with":[88,94,136],"existing":[89],"multilingual":[92],"models,":[93],"variant":[97],"achieving":[98],"best":[100],"scores":[101],"two":[103],"four":[105],"tasks":[106],"but":[107,138],"showing":[108],"no":[109],"consistent":[110],"scaling":[111,115,178],"advantage":[112],"overall.This":[113],"flat":[114],"trend,":[116],"also":[117],"observed":[118],"XLM-R":[120],"EuroBERT,":[122],"suggests":[123],"current":[125],"benchmarks":[127],"may":[128],"already":[129],"be":[130],"saturated.At":[131],"same":[133],"time,":[134],"comparisons":[135],"smaller":[137],"more":[139],"curated":[140],"such":[142],"as":[143,160,169],"BERTurk":[144],"highlight":[145],"corpus":[147,184],"quality":[148],"diversity":[150],"can":[151],"outweigh":[152],"sheer":[153],"data":[154],"volume.Taken":[155],"together,":[156],"contributes":[158],"an":[161,170],"openly":[162],"resource":[164],"NLP":[167],"empirical":[171],"case":[172],"study":[173],"limits":[176],"central":[181],"role":[182],"composition":[185],"languages.The":[189],"are":[192],"under":[194],"MIT":[196],"license":[197],"made":[199],"fairseq":[203],"Huggingface":[205],"formats.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-03-24T00:00:00"}