{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T20:27:07Z","timestamp":1781641627276,"version":"3.54.5"},"publisher-location":"Cham","reference-count":14,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030454418","type":"print"},{"value":"9783030454425","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-45442-5_13","type":"book-chapter","created":{"date-parts":[[2020,4,10]],"date-time":"2020-04-10T21:03:47Z","timestamp":1586552627000},"page":"102-109","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Assessing the Impact of OCR Errors in Information Retrieval"],"prefix":"10.1007","author":[{"given":"Guilherme Torresan","family":"Bazzo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gustavo Acauan","family":"Lorentz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danny","family":"Suarez Vargas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4400-054X","authenticated-orcid":false,"given":"Viviane P.","family":"Moreira","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,4,8]]},"reference":[{"key":"13_CR1","unstructured":"Beitzel, S.M., Jensen, E.C., Grossman, D.A.: A survey of retrieval strategies for OCR text collections. In: Proceedings of the Symposium on Document Image Understanding Technologies (2003)"},{"key":"13_CR2","doi-asserted-by":"crossref","unstructured":"Chiron, G., Doucet, A., Coustaty, M., Moreux, J.: ICDAR 2017 competition on post-OCR text correction. In: International Conference on Document Analysis and Recognition (ICDAR), vol. 01, pp. 1423\u20131428 (2017)","DOI":"10.1109\/ICDAR.2017.232"},{"key":"13_CR3","unstructured":"Croft, W.B., Harding, S., Taghva, K., Borsack, J.: An evaluation of information retrieval accuracy with simulated OCR output. In: Symposium of Document Analysis and Information Retrieval (1994)"},{"key":"13_CR4","unstructured":"Droettboom, M.: Correcting broken characters in the recognition of historical printed documents. In: Proceedings 2003 Joint Conference on Digital Libraries, pp. 364\u2013366, May 2003"},{"key":"13_CR5","doi-asserted-by":"crossref","unstructured":"Evershed, J., Fitch, K.: Correcting noisy OCR: context beats confusion. In: Proceedings of the First International Conference on Digital Access to Textual Cultural Heritage (DATeCH 2014), pp. 45\u201351 (2014)","DOI":"10.1145\/2595188.2595200"},{"key":"13_CR6","unstructured":"Grimes, S.: Unstructured data and the 80 percent rule, p. 10. Carabridge Bridgepoints (2008)"},{"issue":"2","key":"13_CR7","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1023\/A:1009902609570","volume":"2","author":"PB Kantor","year":"2000","unstructured":"Kantor, P.B., Voorhees, E.M.: The TREC-5 confusion track: comparing retrieval methods for scanned text. Inf. Retrieval 2(2), 165\u2013176 (2000). https:\/\/doi.org\/10.1023\/A:1009902609570","journal-title":"Inf. Retrieval"},{"key":"13_CR8","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1016\/0022-2836(70)90057-4","volume":"48","author":"S Needleman","year":"1970","unstructured":"Needleman, S., Wunsch, C.: A general method applicable to the search for similarities in the amino acid sequence of two proteins. J. Mol. Biol. 48, 443\u2013453 (1970)","journal-title":"J. Mol. Biol."},{"key":"13_CR9","doi-asserted-by":"crossref","unstructured":"Nguyen, T., Jatowt, A., Coustaty, M., Nguyen, N., Doucet, A.: Deep statistical analysis of OCR errors for effective post-OCR processing. In: ACM\/IEEE Joint Conference on Digital Libraries (JCDL), pp. 29\u201338, June 2019","DOI":"10.1109\/JCDL.2019.00015"},{"key":"13_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"680","DOI":"10.1007\/978-3-642-00958-7_66","volume-title":"Advances in Information Retrieval","author":"J Parapar","year":"2009","unstructured":"Parapar, J., Freire, A., Barreiro, \u00c1.: Revisiting N-gram based models for retrieval in degraded large collections. In: Boughanem, M., Berrut, C., Mothe, J., Soule-Dupuy, C. (eds.) ECIR 2009. LNCS, vol. 5478, pp. 680\u2013684. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-00958-7_66"},{"issue":"12","key":"13_CR11","doi-asserted-by":"publisher","first-page":"1067","DOI":"10.1002\/asi.1164","volume":"52","author":"C Peters","year":"2001","unstructured":"Peters, C., Braschler, M.: European research letter: cross-language system evaluation: the CLEF campaigns. J. Am. Soc. Inf. Sci. Technol. 52(12), 1067\u20131072 (2001)","journal-title":"J. Am. Soc. Inf. Sci. Technol."},{"key":"13_CR12","doi-asserted-by":"crossref","unstructured":"Rigaud, C., Doucet, A., Coustaty, M., Moreux, J.P.: ICDAR 2019 competition on post-OCR text correction. In: International Conference on Document Analysis and Recognition (ICDAR) (2019)","DOI":"10.1109\/ICDAR.2019.00255"},{"issue":"1","key":"13_CR13","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1145\/214174.214180","volume":"14","author":"K Taghva","year":"1996","unstructured":"Taghva, K., Borsack, J., Condit, A.: Evaluation of model-based retrieval effectiveness with OCR text. ACM Trans. Inf. Syst. 14(1), 64\u201393 (1996)","journal-title":"ACM Trans. Inf. Syst."},{"issue":"7\/8","key":"13_CR14","first-page":"1082","volume":"15","author":"S Tanner","year":"2009","unstructured":"Tanner, S., Mu\u00f1oz, T., Ros, P.H.: Measuring mass text digitization quality and usefulness: lessons learned from assessing the OCR accuracy of the British library\u2019s 19th century online newspaper archive. D-Lib Mag. 15(7\/8), 1082\u20139873 (2009)","journal-title":"D-Lib Mag."}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-45442-5_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T19:23:36Z","timestamp":1710357816000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-45442-5_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030454418","9783030454425"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-45442-5_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"8 April 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lisbon","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 April 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 April 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"42","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecir2020.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"457","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"55","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"46","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"12% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Also included: 8 reproducibility papers, 10 demonstration papers, 12 CLEF organizers lab track papers, 7 doctoral consortium papers, 4 workshops, 3 tutorials. Due to the COVID-19 pandemic, this conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}