{"id":"https://openalex.org/W3183246637","doi":"https://doi.org/10.1007/s10462-021-10051-x","title":"Capitalization and punctuation restoration: a survey","display_name":"Capitalization and punctuation restoration: a survey","publication_year":2021,"publication_date":"2021-07-23","ids":{"openalex":"https://openalex.org/W3183246637","doi":"https://doi.org/10.1007/s10462-021-10051-x","mag":"3183246637"},"language":"en","primary_location":{"id":"doi:10.1007/s10462-021-10051-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-021-10051-x","pdf_url":null,"source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1007/s10462-021-10051-x","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058586148","display_name":"Vasile P\u0103i\u0219","orcid":"https://orcid.org/0000-0002-0019-7574"},"institutions":[{"id":"https://openalex.org/I58077936","display_name":"Romanian Academy","ror":"https://ror.org/0561n6946","country_code":"RO","type":"archive","lineage":["https://openalex.org/I58077936"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Vasile P\u0103i\u015f","raw_affiliation_strings":["Research Institute for Artificial Intelligence \u201cMihai Dr\u0103g\u0103nescu\u201d, Romanian Academy,  CASA ACADEMIEI, 13 \u201cCalea 13 Septembrie\u201d, Bucharest, 050711, Romania","Research Institute for Artificial Intelligence \"Mihai Dr\u0103g\u0103nescu\", Romanian Academy,  CASA ACADEMIEI, 13 \"Calea 13 Septembrie\", Bucharest, 050711, Romania"],"raw_orcid":"https://orcid.org/0000-0002-0019-7574","affiliations":[{"raw_affiliation_string":"Research Institute for Artificial Intelligence \u201cMihai Dr\u0103g\u0103nescu\u201d, Romanian Academy,  CASA ACADEMIEI, 13 \u201cCalea 13 Septembrie\u201d, Bucharest, 050711, Romania","institution_ids":["https://openalex.org/I58077936"]},{"raw_affiliation_string":"Research Institute for Artificial Intelligence \"Mihai Dr\u0103g\u0103nescu\", Romanian Academy,  CASA ACADEMIEI, 13 \"Calea 13 Septembrie\", Bucharest, 050711, Romania","institution_ids":["https://openalex.org/I58077936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062940611","display_name":"Dan Tufi\u015f","orcid":"https://orcid.org/0000-0002-8280-9852"},"institutions":[{"id":"https://openalex.org/I58077936","display_name":"Romanian Academy","ror":"https://ror.org/0561n6946","country_code":"RO","type":"archive","lineage":["https://openalex.org/I58077936"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Dan Tufi\u015f","raw_affiliation_strings":["Research Institute for Artificial Intelligence \u201cMihai Dr\u0103g\u0103nescu\u201d, Romanian Academy,  CASA ACADEMIEI, 13 \u201cCalea 13 Septembrie\u201d, Bucharest, 050711, Romania","Research Institute for Artificial Intelligence \"Mihai Dr\u0103g\u0103nescu\", Romanian Academy,  CASA ACADEMIEI, 13 \"Calea 13 Septembrie\", Bucharest, 050711, Romania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Institute for Artificial Intelligence \u201cMihai Dr\u0103g\u0103nescu\u201d, Romanian Academy,  CASA ACADEMIEI, 13 \u201cCalea 13 Septembrie\u201d, Bucharest, 050711, Romania","institution_ids":["https://openalex.org/I58077936"]},{"raw_affiliation_string":"Research Institute for Artificial Intelligence \"Mihai Dr\u0103g\u0103nescu\", Romanian Academy,  CASA ACADEMIEI, 13 \"Calea 13 Septembrie\", Bucharest, 050711, Romania","institution_ids":["https://openalex.org/I58077936"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5058586148"],"corresponding_institution_ids":["https://openalex.org/I58077936"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":2.7338,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.91684217,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"55","issue":"3","first_page":"1681","last_page":"1722"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9705305695533752},{"id":"https://openalex.org/keywords/casing","display_name":"Casing","score":0.8240160942077637},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7381953001022339},{"id":"https://openalex.org/keywords/capitalization","display_name":"Capitalization","score":0.5623701214790344},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5416581630706787},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4943366050720215},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4125405550003052},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3790420889854431},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3523523807525635},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2013911008834839},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10049211978912354},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.07819396257400513}],"concepts":[{"id":"https://openalex.org/C540372491","wikidata":"https://www.wikidata.org/wiki/Q82622","display_name":"Punctuation","level":2,"score":0.9705305695533752},{"id":"https://openalex.org/C30399818","wikidata":"https://www.wikidata.org/wiki/Q5048830","display_name":"Casing","level":2,"score":0.8240160942077637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7381953001022339},{"id":"https://openalex.org/C2779137862","wikidata":"https://www.wikidata.org/wiki/Q425951","display_name":"Capitalization","level":2,"score":0.5623701214790344},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5416581630706787},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4943366050720215},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4125405550003052},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3790420889854431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3523523807525635},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2013911008834839},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10049211978912354},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.07819396257400513},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C78762247","wikidata":"https://www.wikidata.org/wiki/Q1273174","display_name":"Petroleum engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10462-021-10051-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-021-10051-x","pdf_url":null,"source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2111.10746","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2111.10746","pdf_url":"https://arxiv.org/pdf/2111.10746","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,"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1007/s10462-021-10051-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10462-021-10051-x","pdf_url":null,"source":{"id":"https://openalex.org/S122814990","display_name":"Artificial Intelligence Review","issn_l":"0269-2821","issn":["0269-2821","1573-7462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Artificial Intelligence Review","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":211,"referenced_works":["https://openalex.org/W5671660","https://openalex.org/W22168010","https://openalex.org/W32283220","https://openalex.org/W40475138","https://openalex.org/W46679369","https://openalex.org/W61566120","https://openalex.org/W75790607","https://openalex.org/W94670513","https://openalex.org/W123007672","https://openalex.org/W148400104","https://openalex.org/W180226006","https://openalex.org/W182831726","https://openalex.org/W183201499","https://openalex.org/W192701511","https://openalex.org/W327273178","https://openalex.org/W375929052","https://openalex.org/W560371024","https://openalex.org/W1451631119","https://openalex.org/W1496253462","https://openalex.org/W1504308419","https://openalex.org/W1524333225","https://openalex.org/W1526024327","https://openalex.org/W1554031433","https://openalex.org/W1571969069","https://openalex.org/W1572063013","https://openalex.org/W1575801249","https://openalex.org/W1577006985","https://openalex.org/W1587490638","https://openalex.org/W1594031697","https://openalex.org/W1598259869","https://openalex.org/W1626209120","https://openalex.org/W1678356000","https://openalex.org/W1710476689","https://openalex.org/W1731081199","https://openalex.org/W1773803948","https://openalex.org/W1899794420","https://openalex.org/W1940872118","https://openalex.org/W1970042654","https://openalex.org/W1974358129","https://openalex.org/W1977182536","https://openalex.org/W1978876218","https://openalex.org/W1988790447","https://openalex.org/W1991846425","https://openalex.org/W2011084371","https://openalex.org/W2014703436","https://openalex.org/W2018130343","https://openalex.org/W2019096529","https://openalex.org/W2030904529","https://openalex.org/W2032210760","https://openalex.org/W2039117335","https://openalex.org/W2043832764","https://openalex.org/W2047449117","https://openalex.org/W2053463056","https://openalex.org/W2062267966","https://openalex.org/W2062752744","https://openalex.org/W2064675550","https://openalex.org/W2080856991","https://openalex.org/W2084480693","https://openalex.org/W2090456175","https://openalex.org/W2092269560","https://openalex.org/W2095705004","https://openalex.org/W2096389830","https://openalex.org/W2096765155","https://openalex.org/W2100506586","https://openalex.org/W2101105183","https://openalex.org/W2105126865","https://openalex.org/W2108251622","https://openalex.org/W2109886208","https://openalex.org/W2110037758","https://openalex.org/W2113410090","https://openalex.org/W2113625173","https://openalex.org/W2113851376","https://openalex.org/W2116625254","https://openalex.org/W2123343069","https://openalex.org/W2123442489","https://openalex.org/W2124246394","https://openalex.org/W2127305722","https://openalex.org/W2128808215","https://openalex.org/W2130784467","https://openalex.org/W2130942839","https://openalex.org/W2132528157","https://openalex.org/W2133564696","https://openalex.org/W2134036914","https://openalex.org/W2136933783","https://openalex.org/W2138238299","https://openalex.org/W2144896964","https://openalex.org/W2145386458","https://openalex.org/W2146502635","https://openalex.org/W2147880316","https://openalex.org/W2152463966","https://openalex.org/W2154988249","https://openalex.org/W2157331557","https://openalex.org/W2160306971","https://openalex.org/W2166116787","https://openalex.org/W2169187092","https://openalex.org/W2207587218","https://openalex.org/W2250539671","https://openalex.org/W2250855669","https://openalex.org/W2256323257","https://openalex.org/W2288371874","https://openalex.org/W2295240344","https://openalex.org/W2296283641","https://openalex.org/W2316931181","https://openalex.org/W2395106899","https://openalex.org/W2395173459","https://openalex.org/W2397873193","https://openalex.org/W2398009384","https://openalex.org/W2398104528","https://openalex.org/W2398916001","https://openalex.org/W2403334028","https://openalex.org/W2406343628","https://openalex.org/W2407834842","https://openalex.org/W2408025694","https://openalex.org/W2436001372","https://openalex.org/W2505454603","https://openalex.org/W2508418541","https://openalex.org/W2513522215","https://openalex.org/W2514151559","https://openalex.org/W2543715743","https://openalex.org/W2546302380","https://openalex.org/W2557529195","https://openalex.org/W2561932123","https://openalex.org/W2562621885","https://openalex.org/W2579198251","https://openalex.org/W2586117383","https://openalex.org/W2594990650","https://openalex.org/W2602427488","https://openalex.org/W2619251921","https://openalex.org/W2626778328","https://openalex.org/W2705373224","https://openalex.org/W2739681611","https://openalex.org/W2741483887","https://openalex.org/W2745785989","https://openalex.org/W2745826985","https://openalex.org/W2750292073","https://openalex.org/W2757416441","https://openalex.org/W2781510043","https://openalex.org/W2797022143","https://openalex.org/W2802020728","https://openalex.org/W2806626660","https://openalex.org/W2810621157","https://openalex.org/W2882319491","https://openalex.org/W2884262036","https://openalex.org/W2888942278","https://openalex.org/W2890448475","https://openalex.org/W2896457183","https://openalex.org/W2899902398","https://openalex.org/W2911304011","https://openalex.org/W2913340405","https://openalex.org/W2916456038","https://openalex.org/W2917604489","https://openalex.org/W2937326859","https://openalex.org/W2937375285","https://openalex.org/W2938040855","https://openalex.org/W2938722449","https://openalex.org/W2949888546","https://openalex.org/W2950577311","https://openalex.org/W2952436057","https://openalex.org/W2962739339","https://openalex.org/W2962784628","https://openalex.org/W2962989741","https://openalex.org/W2962996306","https://openalex.org/W2963186636","https://openalex.org/W2963212250","https://openalex.org/W2963351448","https://openalex.org/W2963363527","https://openalex.org/W2963418779","https://openalex.org/W2963425185","https://openalex.org/W2963726581","https://openalex.org/W2963995225","https://openalex.org/W2964308564","https://openalex.org/W2970065520","https://openalex.org/W2970119519","https://openalex.org/W2970529259","https://openalex.org/W2970597249","https://openalex.org/W2971277088","https://openalex.org/W2972388764","https://openalex.org/W2972411269","https://openalex.org/W2973832122","https://openalex.org/W2979826702","https://openalex.org/W3003218517","https://openalex.org/W3010663975","https://openalex.org/W3011222885","https://openalex.org/W3011866533","https://openalex.org/W3016128928","https://openalex.org/W3016199006","https://openalex.org/W3030788518","https://openalex.org/W3033205556","https://openalex.org/W3037101098","https://openalex.org/W3045571807","https://openalex.org/W3085162807","https://openalex.org/W3085780840","https://openalex.org/W3088256047","https://openalex.org/W3096070023","https://openalex.org/W3096718507","https://openalex.org/W3096726003","https://openalex.org/W3118493733","https://openalex.org/W3124955340","https://openalex.org/W3163457913","https://openalex.org/W4242817248","https://openalex.org/W4244952642","https://openalex.org/W4248437541","https://openalex.org/W4255653685","https://openalex.org/W4287821920","https://openalex.org/W4292779060","https://openalex.org/W4297747548","https://openalex.org/W4298289240","https://openalex.org/W4300987104","https://openalex.org/W4385245566","https://openalex.org/W4390912752","https://openalex.org/W6600474606"],"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/W2013684995"],"abstract_inverted_index":{"Ensuring":[0],"proper":[1],"punctuation":[2,26,53,69],"and":[3,27,45,50,54,64,70,77],"letter":[4],"casing":[5,28],"is":[6,19],"a":[7],"key":[8],"pre-processing":[9],"step":[10],"towards":[11],"applying":[12],"complex":[13],"natural":[14],"language":[15],"processing":[16],"algorithms.":[17],"This":[18,56],"especially":[20],"significant":[21],"for":[22,67],"textual":[23],"sources":[24],"where":[25],"are":[29,80],"missing,":[30],"such":[31],"as":[32],"the":[33],"raw":[34],"output":[35],"of":[36,61],"automatic":[37],"speech":[38],"recognition":[39],"systems.":[40],"Additionally,":[41],"short":[42],"text":[43],"messages":[44],"micro-blogging":[46],"platforms":[47],"offer":[48],"unreliable":[49],"often":[51],"wrong":[52],"casing.":[55,73],"survey":[57],"offers":[58],"an":[59],"overview":[60],"both":[62],"historical":[63],"state-of-the-art":[65],"techniques":[66],"restoring":[68],"correcting":[71],"word":[72],"Furthermore,":[74],"current":[75],"challenges":[76],"research":[78],"directions":[79],"highlighted.":[81]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":9}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2021-08-02T00:00:00"}