{"id":"https://openalex.org/W4285255669","doi":"https://doi.org/10.1007/978-3-031-06555-2_32","title":"ReadOCR: A Novel Dataset and\u00a0Readability Assessment of\u00a0OCRed Texts","display_name":"ReadOCR: A Novel Dataset and\u00a0Readability Assessment of\u00a0OCRed Texts","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285255669","doi":"https://doi.org/10.1007/978-3-031-06555-2_32"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-06555-2_32","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-06555-2_32","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101180109","display_name":"Hai Thi Tuyet Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095603","display_name":"Vietnam Posts and Telecommunications Group (Vietnam)","ror":"https://ror.org/00q0e7f94","country_code":"VN","type":"company","lineage":["https://openalex.org/I4210095603"]},{"id":"https://openalex.org/I4400600977","display_name":"Posts and Telecommunications Institute of Technology","ror":"https://ror.org/0363rtq22","country_code":null,"type":"education","lineage":["https://openalex.org/I4400600977"]}],"countries":["VN"],"is_corresponding":true,"raw_author_name":"Hai Thi Tuyet Nguyen","raw_affiliation_strings":["Posts and Telecommunications Institute of Technology, Ho Chi Minh, Vietnam","Posts and Telecommunications Institute of Technology, Vietnam"],"affiliations":[{"raw_affiliation_string":"Posts and Telecommunications Institute of Technology, Ho Chi Minh, Vietnam","institution_ids":["https://openalex.org/I4210095603","https://openalex.org/I4400600977"]},{"raw_affiliation_string":"Posts and Telecommunications Institute of Technology, Vietnam","institution_ids":["https://openalex.org/I4210095603","https://openalex.org/I4400600977"]}]},{"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/I190249584","display_name":"Universit\u00e4t Innsbruck","ror":"https://ror.org/054pv6659","country_code":"AT","type":"education","lineage":["https://openalex.org/I190249584"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Adam Jatowt","raw_affiliation_strings":["Department of Computer Science, University of Innsbruck, Innsbruck, Austria","Leopold Franzens Universit\u00e4t Innsbruck - University of Innsbruck (Innrain 52, A-6020 Innsbruck - Austria)"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Innsbruck, Innsbruck, Austria","institution_ids":["https://openalex.org/I190249584"]},{"raw_affiliation_string":"Leopold Franzens Universit\u00e4t Innsbruck - University of Innsbruck (Innrain 52, A-6020 Innsbruck - Austria)","institution_ids":["https://openalex.org/I190249584"]}]},{"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":"Micka\u00ebl Coustaty","raw_affiliation_strings":["L3i, La Rochelle University, La Rochelle, France","L3I - Laboratoire Informatique, Image et Interaction - EA 2118 (B\u00e2timent Pascal Avenue Michel Cr\u00e9peau F-17042 La Rochelle Cedex 1 - France)"],"affiliations":[{"raw_affiliation_string":"L3i, La Rochelle University, La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]},{"raw_affiliation_string":"L3I - Laboratoire Informatique, Image et Interaction - EA 2118 (B\u00e2timent Pascal Avenue Michel Cr\u00e9peau F-17042 La Rochelle Cedex 1 - France)","institution_ids":["https://openalex.org/I78744979","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, La Rochelle University, La Rochelle, France","L3I - Laboratoire Informatique, Image et Interaction - EA 2118 (B\u00e2timent Pascal Avenue Michel Cr\u00e9peau F-17042 La Rochelle Cedex 1 - France)"],"affiliations":[{"raw_affiliation_string":"L3i, La Rochelle University, La Rochelle, France","institution_ids":["https://openalex.org/I78744979"]},{"raw_affiliation_string":"L3I - Laboratoire Informatique, Image et Interaction - EA 2118 (B\u00e2timent Pascal Avenue Michel Cr\u00e9peau F-17042 La Rochelle Cedex 1 - France)","institution_ids":["https://openalex.org/I78744979","https://openalex.org/I4403928318"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101180109"],"corresponding_institution_ids":["https://openalex.org/I4210095603","https://openalex.org/I4400600977"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17048199,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"479","last_page":"491"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","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/T13629","display_name":"Text Readability and Simplification","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.995199978351593,"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/readability","display_name":"Readability","score":0.9554980993270874},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8958232402801514},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7051600217819214},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.6936778426170349},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6060037612915039},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5485501885414124},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5351031422615051},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5333820581436157},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4453761875629425},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.4160589575767517},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.087670236825943}],"concepts":[{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.9554980993270874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8958232402801514},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7051600217819214},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.6936778426170349},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6060037612915039},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5485501885414124},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5351031422615051},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5333820581436157},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4453761875629425},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.4160589575767517},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.087670236825943},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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":2,"locations":[{"id":"doi:10.1007/978-3-031-06555-2_32","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-06555-2_32","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-04089422v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04089422","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IAPR International Workshop on Document Analysis Systems, May 2022, La Rochelle, France. pp.479-491, &#x27E8;10.1007/978-3-031-06555-2_32&#x27E9;","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1507711477","https://openalex.org/W1746111881","https://openalex.org/W2141403362","https://openalex.org/W2170037364","https://openalex.org/W2212003014","https://openalex.org/W2327037637","https://openalex.org/W2470673105","https://openalex.org/W2601349024","https://openalex.org/W2763103160","https://openalex.org/W2806183494","https://openalex.org/W2964941017","https://openalex.org/W2968567788","https://openalex.org/W2982632725","https://openalex.org/W3012289950","https://openalex.org/W3015310959","https://openalex.org/W3101680040","https://openalex.org/W3134409176","https://openalex.org/W3178709966","https://openalex.org/W4237342689","https://openalex.org/W4251372957"],"related_works":["https://openalex.org/W1964661231","https://openalex.org/W4254960163","https://openalex.org/W3110264473","https://openalex.org/W2999103397","https://openalex.org/W2370831213","https://openalex.org/W4315704968","https://openalex.org/W4285478380","https://openalex.org/W2100255360","https://openalex.org/W1991513203","https://openalex.org/W3178467699"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
