{"id":"https://openalex.org/W7225465748","doi":"https://doi.org/10.6084/m9.figshare.34944079","title":"Vocabulary Structure and Subword Tokenization Cost in Arabic, Hebrew, and Targumic Aramaic: A Parallel-Text Pilot Study","display_name":"Vocabulary Structure and Subword Tokenization Cost in Arabic, Hebrew, and Targumic Aramaic: A Parallel-Text Pilot Study","publication_year":2026,"publication_date":"2026-11-07","ids":{"openalex":"https://openalex.org/W7225465748","doi":"https://doi.org/10.6084/m9.figshare.34944079"},"language":"en","primary_location":{"id":"doi:10.6084/m9.figshare.34944079","doi":"https://doi.org/10.6084/m9.figshare.34944079","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.34944079","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.6084/m9.figshare.34944079","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5151584446","display_name":"Sareena Bilal","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sareena Bilal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5151584446"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T13912","display_name":"Language, Linguistics, Cultural Analysis","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.0003000000142492354,"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/subword-tokenization","display_name":"subword tokenization","score":0.9380000233650208},{"id":"https://openalex.org/keywords/vocabulary-structure","display_name":"vocabulary structure","score":0.7350000143051147},{"id":"https://openalex.org/keywords/arabic","display_name":"Arabic language","score":0.7179999947547913},{"id":"https://openalex.org/keywords/hebrew","display_name":"Hebrew language","score":0.9990000128746033},{"id":"https://openalex.org/keywords/targum-onkelos","display_name":"Targum Onkelos","score":0.972000002861023},{"id":"https://openalex.org/keywords/semitic-languages","display_name":"Semitic languages","score":0.9409999847412109},{"id":"https://openalex.org/keywords/type-token-ratio","display_name":"type-token ratio","score":0.6880000233650208},{"id":"https://openalex.org/keywords/hapax-legomena","display_name":"hapax legomena","score":0.9710000157356262},{"id":"https://openalex.org/keywords/byte-pair-encoding","display_name":"byte pair encoding","score":0.7310000061988831},{"id":"https://openalex.org/keywords/clitics","display_name":"clitics","score":0.7390000224113464},{"id":"https://openalex.org/keywords/orthography","display_name":"orthography","score":0.6629999876022339},{"id":"https://openalex.org/keywords/book-of-genesis","display_name":"Genesis","score":0.8019999861717224},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"parallel corpus","score":0.5540000200271606},{"id":"https://openalex.org/keywords/low-resource-nlp","display_name":"low-resource NLP","score":0.7839999794960022},{"id":"https://openalex.org/keywords/morphological-analysis","display_name":"morphological analysis","score":0.921999990940094}],"concepts":[{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.8317000269889832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6557999849319458},{"id":"https://openalex.org/C132165367","wikidata":"https://www.wikidata.org/wiki/Q34049","display_name":"Semitic languages","level":3,"score":0.6492000222206116},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6154000163078308},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5742999911308289},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5422000288963318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.515999972820282},{"id":"https://openalex.org/C150670947","wikidata":"https://www.wikidata.org/wiki/Q43091","display_name":"Orthography","level":3,"score":0.43059998750686646},{"id":"https://openalex.org/C91304198","wikidata":"https://www.wikidata.org/wiki/Q9288","display_name":"Hebrew","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.39489999413490295},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C110830959","wikidata":"https://www.wikidata.org/wiki/Q178433","display_name":"Lexicology","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C2778243841","wikidata":"https://www.wikidata.org/wiki/Q56467","display_name":"Modern Standard Arabic","level":3,"score":0.2653000056743622},{"id":"https://openalex.org/C126706616","wikidata":"https://www.wikidata.org/wiki/Q2944660","display_name":"Lexical item","level":2,"score":0.26269999146461487}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.6084/m9.figshare.34944079","doi":"https://doi.org/10.6084/m9.figshare.34944079","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.34944079","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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"},{"id":"doi:10.6084/m9.figshare.34944079.v1","doi":"https://doi.org/10.6084/m9.figshare.34944079.v1","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.34944079.v1","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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:10.6084/m9.figshare.34944079","doi":"https://doi.org/10.6084/m9.figshare.34944079","is_oa":true,"landing_page_url":"https://doi.org/10.6084/m9.figshare.34944079","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7117159418","https://openalex.org/W7223001976","https://openalex.org/W7130572497","https://openalex.org/W7166831926","https://openalex.org/W4377989177","https://openalex.org/W7128404066","https://openalex.org/W7108073728","https://openalex.org/W4416037689","https://openalex.org/W2181176782","https://openalex.org/W2070483579"],"abstract_inverted_index":{"This":[0,121],"pilot":[1],"study":[2,39,145],"investigates":[3],"the":[4,34,38,46,99,105,114,128,147],"vocabulary":[5,56,84],"structure":[6],"and":[7,18,50,69,108,116,140,153,173],"subword":[8],"tokenization":[9,80,91,124,151],"cost":[10],"of":[11,30,36,48,149],"three":[12,100],"related":[13],"Semitic":[14,160],"languages:":[15,101],"Arabic,":[16],"Hebrew,":[17],"Targumic":[19],"Aramaic":[20,117],"(specifically,":[21],"Targum":[22],"Onkelos":[23],"on":[24,52],"Genesis).":[25],"Using":[26],"a":[27,95],"parallel":[28],"corpus":[29,167],"1,533":[31],"verses":[32],"from":[33],"Book":[35],"Genesis,":[37],"controls":[40],"for":[41,156],"content":[42],"differences":[43],"to":[44,87,89,110,137,168,179],"isolate":[45],"effects":[47],"language":[49],"orthography":[51],"tokenization.We":[53],"evaluate":[54],"key":[55],"statistics,":[57],"including":[58],"type":[59],"counts,":[60,62],"token":[61],"type-token":[63],"ratio":[64],"(TTR),":[65],"hapax":[66],"legomena":[67],"share,":[68],"average":[70],"word":[71],"length.":[72],"Additionally,":[73],"we":[74],"measure":[75],"Byte":[76],"Pair":[77],"Encoding":[78],"(BPE)":[79],"fertility":[81,125],"across":[82,98],"varying":[83],"sizes":[85],"(250":[86],"2,000)":[88],"assess":[90],"efficiency.Our":[92],"findings":[93],"reveal":[94],"consistent":[96],"ordering":[97],"Arabic":[102,131],"is":[103,113],"lexically":[104],"most":[106],"diverse":[107],"costliest":[109],"tokenize,":[111],"Hebrew":[112],"least,":[115],"sits":[118],"in":[119,123,159],"between.":[120],"gap":[122],"largely":[126],"reflects":[127],"fact":[129],"that":[130],"orthographic":[132],"words":[133],"are":[134],"longer":[135],"due":[136],"attached":[138],"clitics":[139],"rich":[141],"morphological":[142,154,177],"features.":[143],"The":[144],"underscores":[146],"importance":[148],"language-specific":[150],"strategies":[152],"analysis":[155,178],"low-resource":[157],"NLP":[158],"languages.":[161],"Future":[162],"work":[163],"will":[164],"extend":[165],"this":[166],"include":[169],"Syriac":[170],"(the":[171],"Peshitta)":[172],"additional":[174],"books,":[175],"alongside":[176],"further":[180],"test":[181],"clitic-based":[182],"explanations.":[183]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-08T00:00:00"}