{"id":"https://openalex.org/W4212906649","doi":"https://doi.org/10.5220/0010945100003116","title":"An Assessment of the Impact of OCR Noise on Language Models","display_name":"An Assessment of the Impact of OCR Noise on Language Models","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4212906649","doi":"https://doi.org/10.5220/0010945100003116"},"language":"en","primary_location":{"id":"doi:10.5220/0010945100003116","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010945100003116","pdf_url":null,"source":{"id":"https://openalex.org/S4363608837","display_name":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","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":"conference"},"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":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.5220/0010945100003116","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049289161","display_name":"Konstantin Todorov","orcid":"https://orcid.org/0000-0002-9116-6692"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Konstantin Todorov","raw_affiliation_strings":["Institute for Logic, Language and Computation (ILLC), University of Amsterdam, The Netherlands, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Logic, Language and Computation (ILLC), University of Amsterdam, The Netherlands, --- Select a Country ---","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005227218","display_name":"Giovanni Colavizza","orcid":"https://orcid.org/0000-0002-9806-084X"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Giovanni Colavizza","raw_affiliation_strings":["Institute for Logic, Language and Computation (ILLC), University of Amsterdam, The Netherlands, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Logic, Language and Computation (ILLC), University of Amsterdam, The Netherlands, --- Select a Country ---","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I887064364"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"674","last_page":"683"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9900000095367432,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9900000095367432,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9886999726295471,"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":0.9253000020980835,"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/computer-science","display_name":"Computer science","score":0.686128556728363},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5562161803245544},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4439375400543213},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42831581830978394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39662718772888184},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3892739713191986}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.686128556728363},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5562161803245544},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4439375400543213},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42831581830978394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39662718772888184},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3892739713191986},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0010945100003116","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010945100003116","pdf_url":null,"source":{"id":"https://openalex.org/S4363608837","display_name":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","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":"conference"},"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":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:cris.unibo.it:11585/948798","is_oa":true,"landing_page_url":"https://hdl.handle.net/11585/948798","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.5220/0010945100003116","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010945100003116","pdf_url":null,"source":{"id":"https://openalex.org/S4363608837","display_name":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","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":"conference"},"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":"Proceedings of the 14th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W4376623224","https://openalex.org/W3136979370","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Neural":[0],"language":[1,9,40,59,79,82],"models":[2,41,83,101,109],"are":[3],"the":[4,33,50,95],"backbone":[5],"of":[6,32,49,58,97],"modern-day":[7],"natural":[8],"processing":[10],"applications.":[11],"Their":[12],"use":[13],"on":[14,39,55],"textual":[15],"heritage":[16],"collections":[17],"which":[18],"have":[19,38],"undergone":[20],"Optical":[21],"Character":[22],"Recognition":[23],"(OCR)":[24],"is":[25,42],"therefore":[26],"also":[27],"increasing.":[28],"Nevertheless,":[29],"our":[30],"understanding":[31],"impact":[34,51],"OCR":[35,52,72,91],"noise":[36,53,73],"could":[37],"still":[43],"limited.":[44],"We":[45,69],"perform":[46],"an":[47],"assessment":[48],"has":[54],"a":[56,75],"variety":[57],"models,":[60],"using":[61],"data":[62],"in":[63,110],"Dutch,":[64],"English,":[65],"French":[66],"and":[67,104],"German.":[68],"find":[70],"that":[71],"poses":[74],"significant":[76],"obstacle":[77],"to":[78],"modelling,":[80],"with":[81],"increasingly":[84],"diverging":[85],"from":[86],"their":[87],"noiseless":[88],"targets":[89],"as":[90],"quality":[92],"lowers.":[93],"In":[94],"presence":[96],"small":[98],"corpora,":[99],"simpler":[100],"including":[102],"PPMI":[103],"Word2Vec":[105],"consistently":[106],"outperform":[107],"transformer-based":[108],"this":[111],"respect.":[112]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
