{"id":"https://openalex.org/W4386214719","doi":"https://doi.org/10.1109/siu59756.2023.10223973","title":"Analysis of Subword Tokenization Approaches for Turkish Language","display_name":"Analysis of Subword Tokenization Approaches for Turkish Language","publication_year":2023,"publication_date":"2023-07-05","ids":{"openalex":"https://openalex.org/W4386214719","doi":"https://doi.org/10.1109/siu59756.2023.10223973"},"language":"en","primary_location":{"id":"doi:10.1109/siu59756.2023.10223973","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/siu59756.2023.10223973","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st Signal Processing and Communications Applications Conference (SIU)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001102672","display_name":"Erencan Erkaya","orcid":"https://orcid.org/0000-0001-6680-2290"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erencan Erkaya","raw_affiliation_strings":["Boğaziçi University,Department of Computer Engineering,Istanbul,Turkey,34342"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boğaziçi University,Department of Computer Engineering,Istanbul,Turkey,34342","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030496360","display_name":"Tunga G\u00fcng\u00f6r","orcid":"https://orcid.org/0000-0001-9448-9422"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tunga G\u00fcng\u00f6r","raw_affiliation_strings":["Boğaziçi University,Department of Computer Engineering,Istanbul,Turkey,34342"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boğaziçi University,Department of Computer Engineering,Istanbul,Turkey,34342","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2178,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43915505,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9984999895095825,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.957099974155426,"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/lexical-analysis","display_name":"Lexical analysis","score":0.9255077838897705},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8543256521224976},{"id":"https://openalex.org/keywords/turkish","display_name":"Turkish","score":0.7528342008590698},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7343279719352722},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6849665641784668},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.672439455986023},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6682543158531189},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5852622985839844},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41361337900161743},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.347207635641098}],"concepts":[{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.9255077838897705},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8543256521224976},{"id":"https://openalex.org/C2781121862","wikidata":"https://www.wikidata.org/wiki/Q256","display_name":"Turkish","level":2,"score":0.7528342008590698},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7343279719352722},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6849665641784668},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.672439455986023},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6682543158531189},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5852622985839844},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41361337900161743},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.347207635641098},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/siu59756.2023.10223973","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/siu59756.2023.10223973","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 31st Signal Processing and Communications Applications Conference (SIU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1997182898","https://openalex.org/W4378498597","https://openalex.org/W3101140821","https://openalex.org/W4287816966","https://openalex.org/W2944691285","https://openalex.org/W3015650676","https://openalex.org/W4389520445","https://openalex.org/W4387800341","https://openalex.org/W4388347706","https://openalex.org/W2121178211"],"abstract_inverted_index":{"Various":[0],"tokenization":[1],"approaches":[2,12],"have":[3,13],"been":[4,34],"proposed":[5],"in":[6],"natural":[7],"language":[8,60],"processing":[9],"research.":[10],"These":[11],"further":[14],"evolved":[15],"from":[16],"character-":[17],"and":[18,57,61,76],"word-level":[19],"representations":[20],"to":[21],"subword-level":[22],"representations.":[23],"However,":[24],"the":[25,71,80],"impact":[26],"of":[27,82],"tokenizations":[28],"on":[29],"model":[30],"performance":[31],"has":[32],"not":[33],"thoroughly":[35],"discussed,":[36],"especially":[37],"for":[38,50],"morphologically":[39,58],"rich":[40,59],"languages.":[41],"In":[42],"this":[43],"paper,":[44],"we":[45,62,68],"comprehensively":[46],"analyze":[47],"subword":[48],"tokenizers":[49],"Turkish":[51],"which":[52],"is":[53],"a":[54,64],"highly":[55],"inflected":[56],"propose":[63],"morphologically-based":[65],"approach.":[66],"Also,":[67],"examine":[69],"how":[70],"tokenizer":[72],"parameters":[73],"like":[74],"vocabulary":[75],"corpus":[77],"sizes":[78],"change":[79],"characteristics":[81],"tokenizers.":[83]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}