{"id":"https://openalex.org/W3046591412","doi":"https://doi.org/10.1145/3383583.3398605","title":"Neural Machine Translation with BERT for Post-OCR Error Detection and Correction","display_name":"Neural Machine Translation with BERT for Post-OCR Error Detection and Correction","publication_year":2020,"publication_date":"2020-08-01","ids":{"openalex":"https://openalex.org/W3046591412","doi":"https://doi.org/10.1145/3383583.3398605","mag":"3046591412"},"language":"en","primary_location":{"id":"doi:10.1145/3383583.3398605","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3383583.3398605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-03026937","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061375391","display_name":"Thi Tuyet Ha\u00ef Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I4403928318","display_name":"Laboratoire Informatique, Image et Interaction (L3i)","ror":"https://ror.org/03r7r0k94","country_code":null,"type":"facility","lineage":["https://openalex.org/I4403928318","https://openalex.org/I78744979"]},{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Thi Tuyet Hai Nguyen","raw_affiliation_strings":["L3i, University of La Rochelle, La Rochelle, France","Laboratoire Informatique, Image et Interaction - EA 2118"],"affiliations":[{"raw_affiliation_string":"L3i, University of La Rochelle, La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]},{"raw_affiliation_string":"Laboratoire Informatique, Image et Interaction - EA 2118","institution_ids":["https://openalex.org/I4403928318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079733597","display_name":"Adam Jatowt","orcid":"https://orcid.org/0000-0001-7235-0665"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Adam Jatowt","raw_affiliation_strings":["Kyoto University, Kyoto, Japan","Kyoto University (Yoshidahonmachi, Sakyo Ward, Kyoto, Kyoto Prefecture 606-8501 - Japan)"],"affiliations":[{"raw_affiliation_string":"Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]},{"raw_affiliation_string":"Kyoto University (Yoshidahonmachi, Sakyo Ward, Kyoto, Kyoto Prefecture 606-8501 - Japan)","institution_ids":["https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101471226","display_name":"Nhu-Van Nguyen","orcid":"https://orcid.org/0000-0003-2271-6918"},"institutions":[{"id":"https://openalex.org/I4403928318","display_name":"Laboratoire Informatique, Image et Interaction (L3i)","ror":"https://ror.org/03r7r0k94","country_code":null,"type":"facility","lineage":["https://openalex.org/I4403928318","https://openalex.org/I78744979"]},{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nhu-Van Nguyen","raw_affiliation_strings":["L3i, University of La Rochelle, La Rochelle, France","Laboratoire Informatique, Image et Interaction - EA 2118"],"affiliations":[{"raw_affiliation_string":"L3i, University of La Rochelle, La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]},{"raw_affiliation_string":"Laboratoire Informatique, Image et Interaction - EA 2118","institution_ids":["https://openalex.org/I4403928318"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063992777","display_name":"Micka\u00ebl Coustaty","orcid":"https://orcid.org/0000-0002-0123-439X"},"institutions":[{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]},{"id":"https://openalex.org/I4403928318","display_name":"Laboratoire Informatique, Image et Interaction (L3i)","ror":"https://ror.org/03r7r0k94","country_code":null,"type":"facility","lineage":["https://openalex.org/I4403928318","https://openalex.org/I78744979"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mickael Coustaty","raw_affiliation_strings":["L3i, University of La Rochelle, La Rochelle, France","Laboratoire Informatique, Image et Interaction - EA 2118"],"affiliations":[{"raw_affiliation_string":"L3i, University of La Rochelle, La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]},{"raw_affiliation_string":"Laboratoire Informatique, Image et Interaction - EA 2118","institution_ids":["https://openalex.org/I4403928318"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033491986","display_name":"Antoine Doucet","orcid":"https://orcid.org/0000-0001-6160-3356"},"institutions":[{"id":"https://openalex.org/I78744979","display_name":"La Rochelle Universit\u00e9","ror":"https://ror.org/04mv1z119","country_code":"FR","type":"education","lineage":["https://openalex.org/I78744979"]},{"id":"https://openalex.org/I4403928318","display_name":"Laboratoire Informatique, Image et Interaction (L3i)","ror":"https://ror.org/03r7r0k94","country_code":null,"type":"facility","lineage":["https://openalex.org/I4403928318","https://openalex.org/I78744979"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Doucet","raw_affiliation_strings":["L3i, University of La Rochelle, La Rochelle, France","Laboratoire Informatique, Image et Interaction - EA 2118"],"affiliations":[{"raw_affiliation_string":"L3i, University of La Rochelle, La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]},{"raw_affiliation_string":"Laboratoire Informatique, Image et Interaction - EA 2118","institution_ids":["https://openalex.org/I4403928318"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5061375391"],"corresponding_institution_ids":["https://openalex.org/I4403928318","https://openalex.org/I78744979"],"apc_list":null,"apc_paid":null,"fwci":4.4896,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":{"value":0.95486421,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"333","last_page":"336"},"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":0.9976000189781189,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9916999936103821,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8599932789802551},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.8298277854919434},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6769167184829712},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6329783201217651},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.5494774580001831},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.5375331044197083},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5177711248397827},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.5048204064369202},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.45267629623413086},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35109442472457886},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2814895212650299},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09725332260131836}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8599932789802551},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.8298277854919434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6769167184829712},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6329783201217651},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5494774580001831},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.5375331044197083},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5177711248397827},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.5048204064369202},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.45267629623413086},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35109442472457886},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2814895212650299},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09725332260131836},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3383583.3398605","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3383583.3398605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03026937v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03026937","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"JCDL '20: The ACM/IEEE Joint Conference on Digital Libraries in 2020, Aug 2020, Virtual Event, China. pp.333-336, &#x27E8;10.1145/3383583.3398605&#x27E9;","raw_type":"Conference papers"},{"id":"pmh:oai:HAL:hal-04495595v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04495595","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"https://sifed2023.sciencesconf.org/","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03026937v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03026937","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"JCDL '20: The ACM/IEEE Joint Conference on Digital Libraries in 2020, Aug 2020, Virtual Event, China. pp.333-336, &#x27E8;10.1145/3383583.3398605&#x27E9;","raw_type":"Conference papers"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8700000047683716,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1558807800","https://openalex.org/W1990871427","https://openalex.org/W2052227241","https://openalex.org/W2063828767","https://openalex.org/W2212003014","https://openalex.org/W2740711318","https://openalex.org/W2756610685","https://openalex.org/W2786672397","https://openalex.org/W2901878905","https://openalex.org/W2963212250","https://openalex.org/W2964322605","https://openalex.org/W2968567788","https://openalex.org/W3004106466","https://openalex.org/W3012957048"],"related_works":["https://openalex.org/W3011059803","https://openalex.org/W2292997772","https://openalex.org/W3151736118","https://openalex.org/W4362495644","https://openalex.org/W2962780935","https://openalex.org/W2055970094","https://openalex.org/W4387896177","https://openalex.org/W4385557855","https://openalex.org/W2883671469","https://openalex.org/W2575782020"],"abstract_inverted_index":{"The":[0],"quality":[1,52],"of":[2,18,53,75],"OCR":[3],"has":[4],"a":[5,34,40],"direct":[6],"impact":[7,14],"on":[8,15,39,72,78],"information":[9,27],"access,":[10],"and":[11,44,58],"an":[12],"indirect":[13],"the":[16,51,69,76],"performance":[17],"natural":[19],"language":[20,42],"processing":[21],"applications,":[22],"making":[23],"fine-grained":[24],"(e.g.,":[25],"semantic)":[26],"access":[28],"even":[29],"harder.":[30],"This":[31,62],"work":[32],"proposes":[33],"novel":[35],"post-OCR":[36,79],"approach":[37],"based":[38],"contextual":[41],"model":[43],"neural":[45],"machine":[46],"translation,":[47],"aiming":[48],"to":[49,68],"improve":[50],"OCRed":[54],"text":[55,80],"by":[56],"detecting":[57],"rectifying":[59],"erroneous":[60],"tokens.":[61],"new":[63],"technique":[64],"obtains":[65],"results":[66],"comparable":[67],"best-performing":[70],"approaches":[71],"English":[73],"datasets":[74],"competition":[77],"correction":[81],"in":[82],"ICDAR":[83],"2017/2019.":[84]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}
