{"id":"https://openalex.org/W7160247692","doi":"https://doi.org/10.47810/clib.26.13","title":"A Systematic Benchmark of Machine Transliteration Models for the Tajik-Farsi Language Pair: A Comparative Study from Rule-Based to Transformer Architectures","display_name":"A Systematic Benchmark of Machine Transliteration Models for the Tajik-Farsi Language Pair: A Comparative Study from Rule-Based to Transformer Architectures","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7160247692","doi":"https://doi.org/10.47810/clib.26.13"},"language":"en","primary_location":{"id":"doi:10.47810/clib.26.13","doi":"https://doi.org/10.47810/clib.26.13","is_oa":true,"landing_page_url":"https://doi.org/10.47810/clib.26.13","pdf_url":"https://doi.org/10.47810/clib.26.13","source":{"id":"https://openalex.org/S7407113786","display_name":"International Conference Computational Linguistics in Bulgaria (CLIB)","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 International Conference Computational Linguistics in Bulgaria","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.47810/clib.26.13","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135642748","display_name":"Mullosharaf K. Arabov","orcid":"https://orcid.org/0000-0003-2525-1183","observed_orcids":["https://orcid.org/0000-0003-2525-1183"]},"institutions":[{"id":"https://openalex.org/I21203515","display_name":"Kazan Federal University","ror":"https://ror.org/05256ym39","country_code":"RU","type":"education","lineage":["https://openalex.org/I21203515"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Mullosharaf Arabov","raw_affiliation_strings":["Kazan Federal University"],"raw_orcid":"https://orcid.org/0000-0003-2525-1183","affiliations":[{"raw_affiliation_string":"Kazan Federal University","institution_ids":["https://openalex.org/I21203515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5135642748"],"corresponding_institution_ids":["https://openalex.org/I21203515"],"apc_list":null,"apc_paid":null,"fwci":3.9672,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.93296375,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"118","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9771000146865845,"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":0.9771000146865845,"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":0.012900000438094139,"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":0.003599999938160181,"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/machine-transliteration","display_name":"machine transliteration","score":0.8650000095367432},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"parallel corpus","score":0.6679999828338623},{"id":"https://openalex.org/keywords/byt5","display_name":"ByT5","score":0.9229999780654907},{"id":"https://openalex.org/keywords/multilingual-pre-trained-language-models","display_name":"multilingual pretrained models","score":0.7680000066757202},{"id":"https://openalex.org/keywords/attention-based-lstm","display_name":"attention-based LSTM","score":0.7549999952316284},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.421999990940094}],"concepts":[{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.8948000073432922},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.795799970626831},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6801999807357788},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6729999780654907},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6603999733924866},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.5576000213623047},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5166000127792358},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5022000074386597},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4810999929904938},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4560000002384186},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45179998874664307},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.44909998774528503},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C2985367798","wikidata":"https://www.wikidata.org/wiki/Q1346592","display_name":"Parallel corpora","level":3,"score":0.27619999647140503},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2639999985694885},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.25850000977516174},{"id":"https://openalex.org/C96455323","wikidata":"https://www.wikidata.org/wiki/Q13955","display_name":"Arabic","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.47810/clib.26.13","doi":"https://doi.org/10.47810/clib.26.13","is_oa":true,"landing_page_url":"https://doi.org/10.47810/clib.26.13","pdf_url":"https://doi.org/10.47810/clib.26.13","source":{"id":"https://openalex.org/S7407113786","display_name":"International Conference Computational Linguistics in Bulgaria (CLIB)","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 International Conference Computational Linguistics in Bulgaria","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2605.02270","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2605.02270","pdf_url":"https://arxiv.org/pdf/2605.02270","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2605.02270","doi":"https://doi.org/10.48550/arxiv.2605.02270","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.02270","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.47810/clib.26.13","doi":"https://doi.org/10.47810/clib.26.13","is_oa":true,"landing_page_url":"https://doi.org/10.47810/clib.26.13","pdf_url":"https://doi.org/10.47810/clib.26.13","source":{"id":"https://openalex.org/S7407113786","display_name":"International Conference Computational Linguistics in Bulgaria (CLIB)","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 International Conference Computational Linguistics in Bulgaria","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7160247692.pdf","grobid_xml":"https://content.openalex.org/works/W7160247692.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W2133564696","https://openalex.org/W3168867926"],"related_works":["https://openalex.org/W7140137897","https://openalex.org/W7140102033","https://openalex.org/W7131893119","https://openalex.org/W4416150366","https://openalex.org/W7140130056","https://openalex.org/W7131795397","https://openalex.org/W2250243297","https://openalex.org/W7070811472","https://openalex.org/W7125963893","https://openalex.org/W7144043215"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,33,65,92,95,102,105,205],"systematic":[4],"comparative":[5],"benchmark":[6,211],"of":[7,32,69,136,182],"machine":[8],"learning":[9],"architectures":[10],"for":[11,138,142,187,212],"transliteration":[12],"between":[13],"the":[14,27,82,120,143,147,154,159,165,180],"Tajik":[15],"(Cyrillic":[16],"script)":[17,21],"and":[18,29,53,75,119,140,195],"Persian":[19],"(Arabic":[20],"languages.":[22,219],"A":[23],"central":[24],"contribution":[25],"is":[26,76],"creation":[28],"open":[30,201],"release":[31],"unique,":[34],"multi-domain":[35],"parallel":[36],"corpus":[37],"comprising":[38],"328,253":[39],"sentence":[40],"pairs":[41,71],"aggregated":[42],"from":[43,109],"heterogeneous":[44],"sources,":[45],"including":[46],"classical":[47],"poetry,":[48],"diplomatic":[49],"texts,":[50],"lexicographic":[51],"data,":[52,192],"crowdsourced":[54],"projects.":[55],"To":[56],"enable":[57],"fully":[58],"reproducible":[59],"experiments":[60],"under":[61,91,200],"limited":[62],"computational":[63],"resources,":[64],"representative":[66],"stratified":[67],"subset":[68],"40,000":[70],"has":[72],"been":[73],"formed":[74],"made":[77],"publicly":[78],"available":[79],"together":[80],"with":[81,100,117,133],"complete":[83],"dataset.":[84],"The":[85,124],"study":[86],"evaluates":[87],"six":[88],"model":[89,163,196],"classes":[90],"unified":[93],"protocol:":[94],"rule-based":[96],"baseline,":[97],"an":[98],"LSTM":[99],"attention,":[101],"character-level":[103],"Transformer,":[104,150],"G2P":[106,149],"Transformer":[107],"trained":[108,151],"scratch,":[110],"large":[111],"pre-trained":[112],"multilingual":[113],"models":[114,174],"(mBART,":[115],"mT5":[116],"LoRA),":[118],"byte-oriented":[121],"ByT5":[122,129],"model.":[123],"experimental":[125],"results":[126],"demonstrate":[127],"that":[128],"achieves":[130],"state-of-the-art":[131],"performance":[132],"chrF++":[134],"scores":[135],"87.4":[137],"Tajik\u2192Farsi":[139],"80.1":[141],"reverse":[144],"direction.":[145],"Notably,":[146],"proposed":[148],"exclusively":[152],"on":[153],"40,000-pair":[155],"subset,":[156],"significantly":[157],"outperforms":[158],"substantially":[160],"larger":[161],"mBART":[162],"in":[164,215],"forward":[166],"direction":[167],"(72.3":[168],"vs.":[169],"62.2":[170],"chrF++),":[171],"while":[172],"subword-based":[173],"(mT5)":[175],"fail":[176],"almost":[177],"completely,":[178],"underscoring":[179],"necessity":[181],"character-":[183],"or":[184],"byte-level":[185],"representations":[186],"this":[188],"task.":[189],"All":[190],"collected":[191],"source":[193],"code,":[194],"outputs":[197],"are":[198],"released":[199],"licenses,":[202],"thereby":[203],"establishing":[204],"FAIR":[206],"(Findable,":[207],"Accessible,":[208],"Interoperable,":[209],"Reusable)":[210],"cross-script":[213],"NLP":[214],"low-resource":[216],"Central":[217],"Asian":[218]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-05-06T00:00:00"}