{"id":"https://openalex.org/W2900753330","doi":"https://doi.org/10.1007/978-3-030-04257-8_1","title":"Evaluating the Impact of OCR Errors on Topic Modeling","display_name":"Evaluating the Impact of OCR Errors on Topic Modeling","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2900753330","doi":"https://doi.org/10.1007/978-3-030-04257-8_1","mag":"2900753330"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-04257-8_1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-04257-8_1","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-03025563","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085451602","display_name":"Stephen Mutuvi","orcid":"https://orcid.org/0000-0002-3067-9806"},"institutions":[{"id":"https://openalex.org/I327535454","display_name":"Multimedia University of Kenya","ror":"https://ror.org/028r4zr88","country_code":"KE","type":"education","lineage":["https://openalex.org/I327535454"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Stephen Mutuvi","raw_affiliation_strings":["Multimedia University Kenya, Nairobi, Kenya"],"affiliations":[{"raw_affiliation_string":"Multimedia University Kenya, Nairobi, Kenya","institution_ids":["https://openalex.org/I327535454"]}]},{"author_position":"middle","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"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Antoine Doucet","raw_affiliation_strings":["La Rochelle University, La Rochelle, France"],"affiliations":[{"raw_affiliation_string":"La Rochelle University, La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041130858","display_name":"Moses Odeo","orcid":"https://orcid.org/0000-0001-5068-3450"},"institutions":[{"id":"https://openalex.org/I327535454","display_name":"Multimedia University of Kenya","ror":"https://ror.org/028r4zr88","country_code":"KE","type":"education","lineage":["https://openalex.org/I327535454"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Moses Odeo","raw_affiliation_strings":["Multimedia University Kenya, Nairobi, Kenya"],"affiliations":[{"raw_affiliation_string":"Multimedia University Kenya, Nairobi, Kenya","institution_ids":["https://openalex.org/I327535454"]}]},{"author_position":"last","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"],"affiliations":[{"raw_affiliation_string":"Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5033491986"],"corresponding_institution_ids":["https://openalex.org/I78744979"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":1.089,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.90560437,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"14"},"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9991000294685364,"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/T11439","display_name":"Video Analysis and Summarization","score":0.996999979019165,"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":0.867796778678894},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.7831214070320129},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.7005634307861328},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.658438503742218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6158198118209839},{"id":"https://openalex.org/keywords/unavailability","display_name":"Unavailability","score":0.5514182448387146},{"id":"https://openalex.org/keywords/font","display_name":"Font","score":0.5217272043228149},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.4980347156524658},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.44142279028892517},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4256439507007599},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4154353737831116},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3205433487892151},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.14424854516983032}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.867796778678894},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7831214070320129},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.7005634307861328},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.658438503742218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6158198118209839},{"id":"https://openalex.org/C2780505938","wikidata":"https://www.wikidata.org/wiki/Q17093282","display_name":"Unavailability","level":2,"score":0.5514182448387146},{"id":"https://openalex.org/C2777737414","wikidata":"https://www.wikidata.org/wiki/Q4868296","display_name":"Font","level":2,"score":0.5217272043228149},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.4980347156524658},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.44142279028892517},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4256439507007599},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4154353737831116},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3205433487892151},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.14424854516983032},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/978-3-030-04257-8_1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-04257-8_1","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:HAL:hal-03025563v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03025563","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":"Maturity and Innovation in Digital Libraries. 20th International Conference on Asia-Pacific Digital Libraries, ICADL 2018, Hamilton, New Zealand, November 19-22, 2018, Proceedings, pp.3 - 14, 2018, &#x27E8;10.1007/978-3-030-04257-8_1&#x27E9;","raw_type":"Book sections"},{"id":"pmh:oai:zenodo.org:2542539","is_oa":true,"landing_page_url":"https://zenodo.org/record/2542539","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"","raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03025563v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03025563","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":"Maturity and Innovation in Digital Libraries. 20th International Conference on Asia-Pacific Digital Libraries, ICADL 2018, Hamilton, New Zealand, November 19-22, 2018, Proceedings, pp.3 - 14, 2018, &#x27E8;10.1007/978-3-030-04257-8_1&#x27E9;","raw_type":"Book sections"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7900000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W10112829","https://openalex.org/W33249699","https://openalex.org/W1513115070","https://openalex.org/W1601566332","https://openalex.org/W1880262756","https://openalex.org/W1902027874","https://openalex.org/W1988680150","https://openalex.org/W2004340073","https://openalex.org/W2039013656","https://openalex.org/W2060397030","https://openalex.org/W2085763602","https://openalex.org/W2113972683","https://openalex.org/W2116219421","https://openalex.org/W2120379285","https://openalex.org/W2122172122","https://openalex.org/W2128521126","https://openalex.org/W2133058591","https://openalex.org/W2140124448","https://openalex.org/W2140265115","https://openalex.org/W2157023969","https://openalex.org/W2159426623","https://openalex.org/W2404506086","https://openalex.org/W2592771984","https://openalex.org/W2613930770","https://openalex.org/W2741009929","https://openalex.org/W2950577311","https://openalex.org/W2964209171","https://openalex.org/W4230543443","https://openalex.org/W4230857708"],"related_works":["https://openalex.org/W4237235066","https://openalex.org/W207884067","https://openalex.org/W3127016596","https://openalex.org/W2026539069","https://openalex.org/W2365973415","https://openalex.org/W3146085540","https://openalex.org/W1482423459","https://openalex.org/W2996457675","https://openalex.org/W1991513203","https://openalex.org/W3178467699"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
