{"id":"https://openalex.org/W4387619734","doi":"https://doi.org/10.15439/2023f1633","title":"Punctuation Prediction for Polish Texts using Transformers","display_name":"Punctuation Prediction for Polish Texts using Transformers","publication_year":2023,"publication_date":"2023-09-26","ids":{"openalex":"https://openalex.org/W4387619734","doi":"https://doi.org/10.15439/2023f1633"},"language":"en","primary_location":{"id":"doi:10.15439/2023f1633","is_oa":true,"landing_page_url":"http://dx.doi.org/10.15439/2023f1633","pdf_url":"https://annals-csis.org/Volume_35/drp/pdf/1633.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://annals-csis.org/Volume_35/drp/pdf/1633.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055549839","display_name":"Jakub Pokrywka","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jakub Pokrywka","raw_affiliation_strings":["University Faculty of Mathematics and Computer Science,"],"affiliations":[{"raw_affiliation_string":"University Faculty of Mathematics and Computer Science,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5055549839"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1113,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.31114551,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"35","issue":null,"first_page":"1251","last_page":"1254"},"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":0.9997000098228455,"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/T12031","display_name":"Speech and dialogue systems","score":0.9968000054359436,"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","display_name":"Punctuation","score":0.9909861087799072},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8077563047409058},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6522195339202881},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5590255856513977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5184366703033447},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.4888302683830261},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34029698371887207},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08562219142913818},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06055322289466858}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.9909861087799072},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8077563047409058},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6522195339202881},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5590255856513977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5184366703033447},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.4888302683830261},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34029698371887207},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08562219142913818},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06055322289466858},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.15439/2023f1633","is_oa":true,"landing_page_url":"http://dx.doi.org/10.15439/2023f1633","pdf_url":"https://annals-csis.org/Volume_35/drp/pdf/1633.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.04621","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.04621","pdf_url":"https://arxiv.org/pdf/2410.04621","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"pmh:oai:doaj.org/article:0051cf0282f84a44a7bd5092b0b32af9","is_oa":true,"landing_page_url":"https://doaj.org/article/0051cf0282f84a44a7bd5092b0b32af9","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Annals of computer science and information systems, Vol 35, Pp 1251-1254 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.15439/2023f1633","is_oa":true,"landing_page_url":"http://dx.doi.org/10.15439/2023f1633","pdf_url":"https://annals-csis.org/Volume_35/drp/pdf/1633.pdf","source":{"id":"https://openalex.org/S4220651875","display_name":"Annals of Computer Science and Information Systems","issn_l":"2300-5963","issn":["2300-5963"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":"https://openalex.org/P4310317484","host_organization_name":"Polskie Towarzystwo Informatyczne","host_organization_lineage":["https://openalex.org/P4310317484"],"host_organization_lineage_names":["Polskie Towarzystwo Informatyczne"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annals of Computer Science and Information Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387619734.pdf","grobid_xml":"https://content.openalex.org/works/W4387619734.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W2143910127","https://openalex.org/W2300676179","https://openalex.org/W2575282817","https://openalex.org/W2972594731","https://openalex.org/W2983040767","https://openalex.org/W3033862527","https://openalex.org/W3035390927","https://openalex.org/W3039572191","https://openalex.org/W3045571807","https://openalex.org/W3097571385","https://openalex.org/W3155292524","https://openalex.org/W3157789198","https://openalex.org/W3203323280","https://openalex.org/W3204088617","https://openalex.org/W4385245566","https://openalex.org/W4387619734","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W2936002343","https://openalex.org/W2188883480","https://openalex.org/W1592364192","https://openalex.org/W656840002","https://openalex.org/W1605117403","https://openalex.org/W2381416480","https://openalex.org/W2380599343","https://openalex.org/W2181793145","https://openalex.org/W3163320880","https://openalex.org/W2365703075"],"abstract_inverted_index":{"Speech":[0],"recognition":[1],"systems":[2],"typically":[3],"output":[4],"text":[5,13],"lacking":[6],"punctuation.However,":[7],"punctuation":[8],"is":[9],"crucial":[10],"for":[11,27,34],"written":[12],"comprehension.To":[14],"tackle":[15],"this":[16],"problem,":[17],"Punctuation":[18,32],"Prediction":[19,33],"models":[20],"are":[21],"developed.This":[22],"paper":[23],"describes":[24],"a":[25,44],"solution":[26],"Poleval":[28],"2022":[29],"Task":[30],"1:":[31],"Polish":[35],"Texts,":[36],"which":[37],"scores":[38],"71.44":[39],"Weighted":[40],"F1.The":[41],"method":[42],"utilizes":[43],"single":[45],"HerBERT":[46],"model":[47],"finetuned":[48],"to":[49],"the":[50],"competition":[51],"data":[52],"and":[53],"an":[54],"external":[55],"dataset.":[56]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
