{"id":"https://openalex.org/W4221078158","doi":"https://doi.org/10.1145/3479159","title":"Toward a Period-specific Optimized Neural Network for OCR Error Correction of Historical Hebrew Texts","display_name":"Toward a Period-specific Optimized Neural Network for OCR Error Correction of Historical Hebrew Texts","publication_year":2022,"publication_date":"2022-04-01","ids":{"openalex":"https://openalex.org/W4221078158","doi":"https://doi.org/10.1145/3479159"},"language":"en","primary_location":{"id":"doi:10.1145/3479159","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3479159","pdf_url":null,"source":{"id":"https://openalex.org/S4210184050","display_name":"Journal on Computing and Cultural Heritage","issn_l":"1556-4673","issn":["1556-4673","1556-4711"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal on Computing and Cultural Heritage","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2307.16213","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081395585","display_name":"Omri Suissa","orcid":"https://orcid.org/0000-0002-9703-2222"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Omri Suissa","raw_affiliation_strings":["Bar Ilan University, Ramat Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Bar Ilan University, Ramat Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006766510","display_name":"Maayan Zhitomirsky\u2010Geffet","orcid":"https://orcid.org/0000-0002-9161-2541"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Maayan Zhitomirsky-Geffet","raw_affiliation_strings":["Bar Ilan University, Ramat Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Bar Ilan University, Ramat Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047276842","display_name":"Avshalom Elmalech","orcid":"https://orcid.org/0000-0001-6142-3881"},"institutions":[{"id":"https://openalex.org/I13955877","display_name":"Bar-Ilan University","ror":"https://ror.org/03kgsv495","country_code":"IL","type":"education","lineage":["https://openalex.org/I13955877"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Avshalom Elmalech","raw_affiliation_strings":["Bar Ilan University, Ramat Gan, Israel"],"affiliations":[{"raw_affiliation_string":"Bar Ilan University, Ramat Gan, Israel","institution_ids":["https://openalex.org/I13955877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081395585"],"corresponding_institution_ids":["https://openalex.org/I13955877"],"apc_list":null,"apc_paid":null,"fwci":0.8171,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.72196432,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"15","issue":"2","first_page":"1","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9986000061035156,"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":0.9955000281333923,"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/hebrew","display_name":"Hebrew","score":0.8324687480926514},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7801792621612549},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.7265758514404297},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5745216012001038},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5487379431724548},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.5458917021751404},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.544533908367157},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.49706795811653137},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.48900994658470154},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4547604024410248},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.42260050773620605},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3283964991569519},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1835181713104248},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.17383810877799988},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08354660868644714}],"concepts":[{"id":"https://openalex.org/C91304198","wikidata":"https://www.wikidata.org/wiki/Q9288","display_name":"Hebrew","level":2,"score":0.8324687480926514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7801792621612549},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7265758514404297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5745216012001038},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5487379431724548},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5458917021751404},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.544533908367157},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.49706795811653137},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.48900994658470154},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4547604024410248},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.42260050773620605},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3283964991569519},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1835181713104248},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.17383810877799988},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08354660868644714},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3479159","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3479159","pdf_url":null,"source":{"id":"https://openalex.org/S4210184050","display_name":"Journal on Computing and Cultural Heritage","issn_l":"1556-4673","issn":["1556-4673","1556-4711"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal on Computing and Cultural Heritage","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2307.16213","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.16213","pdf_url":"https://arxiv.org/pdf/2307.16213","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2307.16213","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.16213","pdf_url":"https://arxiv.org/pdf/2307.16213","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4221078158.pdf"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W175100101","https://openalex.org/W1522301498","https://openalex.org/W1592997058","https://openalex.org/W1601807985","https://openalex.org/W1647671624","https://openalex.org/W1699166917","https://openalex.org/W1815076433","https://openalex.org/W1924770834","https://openalex.org/W1965154800","https://openalex.org/W1990871427","https://openalex.org/W2005227457","https://openalex.org/W2064675550","https://openalex.org/W2069143585","https://openalex.org/W2074231493","https://openalex.org/W2076605490","https://openalex.org/W2095705004","https://openalex.org/W2109000768","https://openalex.org/W2118629817","https://openalex.org/W2123442489","https://openalex.org/W2127008633","https://openalex.org/W2130942839","https://openalex.org/W2131774270","https://openalex.org/W2157331557","https://openalex.org/W2167277498","https://openalex.org/W2251592786","https://openalex.org/W2508817996","https://openalex.org/W2524182563","https://openalex.org/W2525778437","https://openalex.org/W2559655401","https://openalex.org/W2566260077","https://openalex.org/W2568187431","https://openalex.org/W2575366139","https://openalex.org/W2587019100","https://openalex.org/W2619532290","https://openalex.org/W2735929801","https://openalex.org/W2735998760","https://openalex.org/W2760493402","https://openalex.org/W2774106489","https://openalex.org/W2786672397","https://openalex.org/W2793452059","https://openalex.org/W2798685342","https://openalex.org/W2809806860","https://openalex.org/W2810576820","https://openalex.org/W2891526782","https://openalex.org/W2950773754","https://openalex.org/W2955430668","https://openalex.org/W2963212250","https://openalex.org/W2964322605","https://openalex.org/W2968567788","https://openalex.org/W2970171327","https://openalex.org/W2979371944","https://openalex.org/W2980063486","https://openalex.org/W2988898388","https://openalex.org/W2995333594","https://openalex.org/W2999622538","https://openalex.org/W3012957048","https://openalex.org/W3046591412","https://openalex.org/W3159754263","https://openalex.org/W3168456505","https://openalex.org/W3173544627","https://openalex.org/W4237342689","https://openalex.org/W4312290170","https://openalex.org/W4385473920","https://openalex.org/W6631190155","https://openalex.org/W6731910864"],"related_works":["https://openalex.org/W2140186469","https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W4390421286","https://openalex.org/W4280563792","https://openalex.org/W1732468982","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W4389724018","https://openalex.org/W2575782020"],"abstract_inverted_index":{"Over":[0],"the":[1,20,70,96,130,172,208,217,228,236,242,247,253,258],"past":[2],"few":[3],"decades,":[4],"large":[5,74],"archives":[6],"of":[7,41,62,72,101,105,132,177],"paper-based":[8],"historical":[9,67],"documents,":[10],"such":[11],"as":[12],"books":[13],"and":[14,99,124,156,187,234,256,267,285,291],"newspapers,":[15],"have":[16,46,274],"been":[17],"digitized":[18],"using":[19,63,179,216],"Optical":[21],"Character":[22],"Recognition":[23],"(OCR)":[24],"technology.":[25],"Unfortunately,":[26],"this":[27],"broadly":[28],"used":[29],"technology":[30],"is":[31,69,91],"error-prone,":[32],"especially":[33,82],"when":[34],"an":[35,161],"OCRed":[36,287],"document":[37],"was":[38],"written":[39],"hundreds":[40],"years":[42],"ago.":[43],"Neural":[44],"networks":[45,65,107],"shown":[47],"great":[48],"success":[49],"in":[50,112,168,289],"solving":[51],"various":[52,185],"text":[53],"processing":[54],"tasks,":[55],"including":[56],"OCR":[57,109,133,154,166,213],"post-correction.":[58],"The":[59,191,270],"main":[60],"disadvantage":[61],"neural":[64,106,135,163,263],"for":[66,83,108,148,159,165,230,277],"corpora":[68,183],"lack":[71],"sufficiently":[73],"training":[75,151,197],"datasets":[76,152],"they":[77],"require":[78],"to":[79,115,211,252,283],"learn":[80],"from,":[81],"morphologically":[84,294],"rich":[85,295],"languages":[86,120],"like":[87],"Hebrew.":[88,169],"Moreover,":[89],"it":[90],"not":[92],"clear":[93],"what":[94],"are":[95],"optimal":[97],"structure":[98],"values":[100],"hyperparameters":[102],"(predefined":[103],"parameters)":[104],"error":[110,219],"correction":[111],"Hebrew":[113,182,290],"due":[114],"its":[116],"unique":[117],"features.":[118],"Furthermore,":[119],"change":[121],"across":[122],"genres":[123,188],"periods.":[125],"These":[126],"changes":[127],"may":[128,273],"affect":[129],"accuracy":[131,238,248],"post-correction":[134,167],"network":[136,164,199,237,244,261],"models.":[137],"To":[138,170],"overcome":[139],"these":[140],"challenges,":[141],"we":[142],"developed":[143],"a":[144,175,198,203],"new":[145],"multi-phase":[146],"method":[147],"generating":[149],"artificial":[150],"with":[153],"errors":[155],"hyperparameters\u2019":[157],"optimization":[158],"building":[160],"effective":[162],"evaluate":[171],"proposed":[173,218,271],"approach,":[174],"series":[176],"experiments":[178],"several":[180],"literary":[181],"from":[184,202],"periods":[186],"were":[189],"conducted.":[190],"obtained":[192],"results":[193],"demonstrate":[194],"that":[195,281],"(1)":[196],"on":[200,223],"texts":[201],"similar":[204],"period":[205],"dramatically":[206],"improves":[207,235,246],"network's":[209],"ability":[210],"fix":[212],"errors,":[214,226],"(2)":[215],"injection":[220],"algorithm,":[221],"based":[222],"character-level":[224],"period-specific":[225],"minimizes":[227],"need":[229],"manually":[231],"corrected":[232],"data":[233],"by":[239,249],"9%,":[240],"(3)":[241],"optimized":[243,260],"design":[245],"3%":[250],"compared":[251],"state-of-the-art":[254],"network,":[255],"(4)":[257],"constructed":[259],"outperforms":[262],"machine":[264],"translation":[265],"models":[266],"industry-leading":[268],"spellcheckers.":[269],"methodology":[272],"practical":[275],"implications":[276],"digital":[278],"humanities":[279],"projects":[280],"aim":[282],"search":[284],"analyze":[286],"documents":[288],"potentially":[292],"other":[293],"languages.":[296]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2022-04-03T00:00:00"}