{"id":"https://openalex.org/W4387913150","doi":"https://doi.org/10.1109/ubmk59864.2023.10286690","title":"Transformer Based Punctuation Restoration for Turkish","display_name":"Transformer Based Punctuation Restoration for Turkish","publication_year":2023,"publication_date":"2023-09-13","ids":{"openalex":"https://openalex.org/W4387913150","doi":"https://doi.org/10.1109/ubmk59864.2023.10286690"},"language":"en","primary_location":{"id":"doi:10.1109/ubmk59864.2023.10286690","doi":"https://doi.org/10.1109/ubmk59864.2023.10286690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ubmk59864.2023.10286690","pdf_url":null,"source":{"id":"https://openalex.org/S4306498178","display_name":"International Conference on Computer Science and Engineering (UBMK)","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":"2023 8th International Conference on Computer Science and Engineering (UBMK)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5113030548","display_name":"Uygar Kurt","orcid":"https://orcid.org/0009-0001-1861-2115","observed_orcids":["https://orcid.org/0009-0001-1861-2115"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Uygar Kurt","raw_affiliation_strings":["Huawei T\u00fcrkiye, R&D Center,\u0130stanbul,T\u00fcrkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei T\u00fcrkiye, R&D Center,\u0130stanbul,T\u00fcrkiye","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045238511","display_name":"Aykut \u00c7ay\u0131r","orcid":"https://orcid.org/0000-0001-9564-0331","observed_orcids":["https://orcid.org/0000-0001-9564-0331"]},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aykut \u00c7ay\u0131r","raw_affiliation_strings":["Huawei T\u00fcrkiye, R&D Center,\u0130stanbul,T\u00fcrkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei T\u00fcrkiye, R&D Center,\u0130stanbul,T\u00fcrkiye","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250955327"],"apc_list":null,"apc_paid":null,"fwci":0.3314,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.53253921,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"169","last_page":"174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.6675000190734863,"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":0.6675000190734863,"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":0.21780000627040863,"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":0.0925000011920929,"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/punctuation-restoration","display_name":"punctuation restoration","score":0.9959999918937683},{"id":"https://openalex.org/keywords/turkish-language","display_name":"Turkish language","score":0.9639999866485596},{"id":"https://openalex.org/keywords/electra","display_name":"Electra","score":0.6909999847412109},{"id":"https://openalex.org/keywords/bert","display_name":"BERT","score":0.859000027179718},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.6420000195503235},{"id":"https://openalex.org/keywords/punctuation-prediction","display_name":"punctuation prediction","score":0.49399998784065247},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.5659999847412109},{"id":"https://openalex.org/keywords/social-media-text","display_name":"social media text","score":0.5410000085830688}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.9701053500175476},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7414954900741577},{"id":"https://openalex.org/C2781121862","wikidata":"https://www.wikidata.org/wiki/Q256","display_name":"Turkish","level":2,"score":0.7360132932662964},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6787862181663513},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5949043035507202},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5947073698043823},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.541344165802002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4704799950122833},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.45518630743026733},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43206387758255005},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19299879670143127},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11473396420478821},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0818001925945282},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ubmk59864.2023.10286690","doi":"https://doi.org/10.1109/ubmk59864.2023.10286690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ubmk59864.2023.10286690","pdf_url":null,"source":{"id":"https://openalex.org/S4306498178","display_name":"International Conference on Computer Science and Engineering (UBMK)","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":"2023 8th International Conference on Computer Science and Engineering (UBMK)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1816313093","https://openalex.org/W2064675550","https://openalex.org/W2101105183","https://openalex.org/W2136630431","https://openalex.org/W2147880316","https://openalex.org/W2403334028","https://openalex.org/W2406343628","https://openalex.org/W2575282817","https://openalex.org/W2626778328","https://openalex.org/W2745826985","https://openalex.org/W2810621157","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2962784628","https://openalex.org/W2963341956","https://openalex.org/W2965373594","https://openalex.org/W2979826702","https://openalex.org/W2995082385","https://openalex.org/W2996035354","https://openalex.org/W3010663975","https://openalex.org/W3037101098","https://openalex.org/W3047171714","https://openalex.org/W3096726003","https://openalex.org/W3106905592","https://openalex.org/W3156712136","https://openalex.org/W3163984848","https://openalex.org/W3166192435","https://openalex.org/W3185113268","https://openalex.org/W3186387749","https://openalex.org/W4221166827","https://openalex.org/W4284974527","https://openalex.org/W4312461310","https://openalex.org/W6759815381","https://openalex.org/W6766673545","https://openalex.org/W6771917389","https://openalex.org/W6795071438"],"related_works":["https://openalex.org/W3101555937","https://openalex.org/W7140079101","https://openalex.org/W7123432612","https://openalex.org/W3106905592","https://openalex.org/W7052442246","https://openalex.org/W4415234679","https://openalex.org/W3123106758","https://openalex.org/W3215314684","https://openalex.org/W4210452164","https://openalex.org/W4415424121"],"abstract_inverted_index":{"Mobile":[0],"devices":[1],"and":[2,45,62,97,111,115,128,141],"social":[3],"media":[4],"platforms":[5],"make":[6],"communication":[7,28],"faster":[8],"than":[9],"humans":[10],"have":[11],"had":[12],"before,":[13],"thanks":[14],"to":[15,31,78,145],"the":[16,24,56,85,118,134],"technologies":[17],"such":[18],"as":[19],"automatic":[20,57],"speech":[21,58,72],"recognition(ASR).":[22],"However,":[23,74],"speed":[25],"in":[26,71,94,133],"text-based":[27],"methods":[29],"leads":[30],"several":[32],"mistakes":[33,41],"that":[34],"could":[35],"be":[36],"solved.":[37],"The":[38,49],"two":[39],"well-known":[40],"are":[42,68,113,136],"grammatical":[43],"errors":[44],"forgotten":[46],"punctuation":[47,50,67,81,104],"usage.":[48],"restoration":[51,82],"task":[52],"is":[53],"inherited":[54],"from":[55],"recognition":[59],"domain.":[60],"Understanding":[61],"restoring":[63,92],"correct":[64],"places":[65],"of":[66],"challenging":[69],"problems":[70],"recognition.":[73],"no":[75],"datasets":[76],"exist":[77],"train":[79],"a":[80,99],"model":[83,151],"for":[84,103,122],"Turkish":[86,95,101],"language.":[87],"This":[88],"paper":[89,135],"focuses":[90],"on":[91,117],"punctuations":[93],"texts":[96],"introduces":[98],"new":[100],"dataset":[102,121],"restoration.":[105],"Three":[106],"transformer":[107],"models:":[108],"BERT,":[109],"ELECTRA,":[110],"ConvBERT,":[112],"fine-tuned":[114],"tested":[116],"newly":[119],"created":[120],"three":[123],"distinct":[124],"labels:":[125],"PERIOD,":[126],"COMMA,":[127],"QUESTION":[129],"MARK.":[130],"Benchmark":[131],"results":[132],"reported":[137],"regarding":[138],"precision,":[139],"recall,":[140],"F1":[142,159],"score":[143,160],"due":[144],"imbalanced":[146],"class":[147],"distribution.":[148],"Although":[149],"each":[150],"shows":[152],"similar":[153],"performance":[154],"scores,":[155],"ELECTRA":[156],"reaches":[157],"83.9%":[158],"overall.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-10-25T00:00:00"}