{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T11:30:04Z","timestamp":1778758204631,"version":"3.51.4"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2022,9,25]],"date-time":"2022-09-25T00:00:00Z","timestamp":1664064000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,9,25]],"date-time":"2022-09-25T00:00:00Z","timestamp":1664064000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"crossref","award":["19H01330"],"award-info":[{"award-number":["19H01330"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"DOI":"10.1007\/s42979-022-01393-6","type":"journal-article","created":{"date-parts":[[2022,9,25]],"date-time":"2022-09-25T08:02:41Z","timestamp":1664092961000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Corpus Construction for Historical Newspapers: A Case Study on Public Meeting Corpus Construction Using OCR Error Correction"],"prefix":"10.1007","volume":"3","author":[{"given":"Koji","family":"Tanaka","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9848-6384","authenticated-orcid":false,"given":"Chenhui","family":"Chu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomoyuki","family":"Kajiwara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuta","family":"Nakashima","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Noriko","family":"Takemura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hajime","family":"Nagahara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takao","family":"Fujikawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,9,25]]},"reference":[{"issue":"1","key":"1393_CR1","first-page":"175","volume":"7","author":"H Afli","year":"2015","unstructured":"Afli H, Barrault L, Schwenk H. OCR error correction using statistical machine translation. Int J Comput Ling Appl. 2015;7(1):175\u201391.","journal-title":"Int J Comput Ling Appl"},{"key":"1393_CR2","unstructured":"Afli H, Qiu Z, Way A, Sheridan P. Using SMT for OCR error correction of historical texts. In: Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 2016), pp 962\u2013966. 2016"},{"key":"1393_CR3","unstructured":"Barbaresi A. Bootstrapped OCR error detection for a less-resourced language variant. In: 13th Conference on Natural Language Processing (KONVENS 2016), pp 21\u201326. 2016"},{"key":"1393_CR4","doi-asserted-by":"crossref","unstructured":"Barrault L, Bojar O, Costa-juss\u00e0 MR, Federmann C, Fishel M, Graham Y, Haddow B, Huck M, Koehn P, Malmasi S, Monz C, M\u00fcller M, Pal S, Post M, Zampieri M. Findings of the 2019 conference on machine translation (WMT19). In: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), pp 1\u201361. 2019","DOI":"10.18653\/v1\/W19-5301"},{"key":"1393_CR5","unstructured":"Cassidy S. Publishing the Trove newspaper corpus. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC\u201916), pp 4520\u20134525. 2016"},{"key":"1393_CR6","doi-asserted-by":"crossref","unstructured":"Chiron G, Doucet A, Coustaty M, Visani M, Moreux JP. Impact of OCR errors on the use of digital libraries: towards a better access to information. In: Proceedings of the 17th ACM\/IEEE Joint Conference on Digital Libraries, JCDL \u201917, pp 249\u2013252. 2017","DOI":"10.1109\/JCDL.2017.7991582"},{"key":"1393_CR7","doi-asserted-by":"crossref","unstructured":"Cho K, van Merri\u00ebnboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y. Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp 1724\u20131734. 2014","DOI":"10.3115\/v1\/D14-1179"},{"key":"1393_CR8","doi-asserted-by":"crossref","unstructured":"Chu C, Nakazawa T, Kurohashi S. Integrated parallel sentence and fragment extraction from comparable corpora: A case study on chinese\u2013japanese wikipedia. ACM Trans Asian Low-Resour Lang Inform Process. 2015;15(2):10:1\u201310:22","DOI":"10.1145\/2833089"},{"key":"1393_CR9","doi-asserted-by":"crossref","unstructured":"Chung J, Cho K, Bengio Y. A character-level decoder without explicit segmentation for neural machine translation. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp 1693\u20131703. 2016","DOI":"10.18653\/v1\/P16-1160"},{"key":"1393_CR10","doi-asserted-by":"publisher","first-page":"121","DOI":"10.3366\/cor.2012.0024","volume":"7","author":"M Davies","year":"2012","unstructured":"Davies M. Expanding horizons in historical linguistics with the 400-million word corpus of historical american english. Corpora. 2012;7:121\u201357.","journal-title":"Corpora"},{"key":"1393_CR11","doi-asserted-by":"crossref","unstructured":"Dong R, Smith D. Multi-input attention for unsupervised OCR correction. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp 2363\u20132372. 2018","DOI":"10.18653\/v1\/P18-1220"},{"key":"1393_CR12","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"Duchi J, Hazan E, Singer Y. Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res. 2011;12:2121\u201359.","journal-title":"J Mach Learn Res"},{"key":"1393_CR13","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1515\/pralin-2016-0004","volume":"106","author":"S Eger","year":"2016","unstructured":"Eger S, Br\u00fcck T, Mehler A. A comparison of four character-level string-to-string translation models for (ocr) spelling error correction. Prag Bull Math Ling. 2016;106:77\u201399.","journal-title":"Prag Bull Math Ling"},{"key":"1393_CR14","doi-asserted-by":"crossref","unstructured":"Evershed J, Fitch K (2014) Correcting noisy OCR: context beats confusion. In: Proceedings of the First International Conference on Digital Access to Textual Cultural Heritage, pp 45\u201351","DOI":"10.1145\/2595188.2595200"},{"key":"1393_CR15","first-page":"45","volume":"76","author":"T Fujikawa","year":"1990","unstructured":"Fujikawa T. Public meetings in New South Wales: 1871\u20131901. J R Aust Hist Soc. 1990;76:45\u201361.","journal-title":"J R Aust Hist Soc"},{"key":"1393_CR16","unstructured":"Kingma D, Ba J. Adam: A method for stochastic optimization. In: International Conference on Learning Representations. 2015"},{"key":"1393_CR17","unstructured":"Klein S, Kopel M. A voting system for automatic ocr correction. 2002"},{"key":"1393_CR18","doi-asserted-by":"crossref","unstructured":"Klein G, Kim Y, Deng Y, Senellart J, Rush A. OpenNMT: open-source toolkit for neural machine translation. In: Proceedings of ACL 2017, System Demonstrations, pp 67\u201372. 2017","DOI":"10.18653\/v1\/P17-4012"},{"key":"1393_CR19","unstructured":"Koehn . Europarl: a parallel corpus for statistical machine translation. In: Proceedings of Machine Translation Summit, pp 79\u201386. 2005"},{"key":"1393_CR20","doi-asserted-by":"crossref","unstructured":"Koehn P, Hoang H, Birch A, Callison-Burch C, Federico M, Bertoldi N, Cowan B, Shen W, Moran C, Zens R, Dyer C, Bojar O, Constantin A, Herbst E. Moses: open source toolkit for statistical machine translation. In: Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions, ACL \u201907, pp 177\u2013180. 2007","DOI":"10.3115\/1557769.1557821"},{"key":"1393_CR21","doi-asserted-by":"crossref","unstructured":"Kolak O, Resnik P. OCR error correction using a noisy channel model. In: Proceedings of the Second International Conference on Human Language Technology Research, pp 257\u2013262. 2002","DOI":"10.3115\/1289189.1289208"},{"key":"1393_CR22","doi-asserted-by":"crossref","unstructured":"Kolak O, Byrne W, Resnik P. A generative probabilistic OCR model for NLP applications. In: Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, pp 134\u2013141. 2003","DOI":"10.3115\/1073445.1073463"},{"key":"1393_CR23","first-page":"254","volume":"8658","author":"WB Lund","year":"2013","unstructured":"Lund WB, Kennard DJ, Ringger EK. Combining multiple thresholding binarization values to improve OCR output. Doc Recogn Retrie XX. 2013;8658:254\u201364.","journal-title":"Doc Recogn Retrie XX"},{"key":"1393_CR24","first-page":"479","volume":"9","author":"L Lyu","year":"2021","unstructured":"Lyu L, Koutraki M, Krickl M, Fetahu B. Neural OCR post-hoc correction of historical corpora. Trans Assoc Comput Ling. 2021;9:479\u201393.","journal-title":"Trans Assoc Comput Ling"},{"issue":"2","key":"1393_CR25","first-page":"313","volume":"19","author":"MP Marcus","year":"1993","unstructured":"Marcus MP, Marcinkiewicz MA, Santorini B. Building a large annotated corpus of English: The Penn Treebank. Comput Ling. 1993;19(2):313\u201330.","journal-title":"Comput Ling"},{"key":"1393_CR26","doi-asserted-by":"crossref","unstructured":"Mokhtar K, Bukhari SS, Dengel A. OCR error correction: state-of-the-art vs an nmt-based approach. In: Proceedings of the 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), pp 429\u2013434. 2018","DOI":"10.1109\/DAS.2018.63"},{"key":"1393_CR27","doi-asserted-by":"crossref","unstructured":"Moreno-Garc\u00eda C, Elyan E. Digitisation of assets from the oil gas industry: Challenges and opportunities. In: Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), pp 2\u20135. 2019","DOI":"10.1109\/ICDARW.2019.60122"},{"key":"1393_CR28","doi-asserted-by":"crossref","unstructured":"Moreno-Garc\u00eda C, Elyan E, Jayne C. New trends on digitisation of complex engineering drawings. 2019;31(6):1695\u2013712.","DOI":"10.1007\/s00521-018-3583-1"},{"key":"1393_CR29","unstructured":"Neudecker C. An open corpus for named entity recognition in historic newspapers. In: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC\u201916), pp 4348\u20134352. 2016"},{"key":"1393_CR30","doi-asserted-by":"crossref","unstructured":"Och FJ. Minimum error rate training in statistical machine translation. In: Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, pp 160\u2013167. 2003","DOI":"10.3115\/1075096.1075117"},{"issue":"1","key":"1393_CR31","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","volume":"9","author":"N Otsu","year":"1979","unstructured":"Otsu N. A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern. 1979;9(1):62\u20136.","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"1393_CR32","unstructured":"Radford A, Narasimhan K (2018) Improving language understanding by generative pre-training"},{"key":"1393_CR33","unstructured":"Richter C, Wickes M, Beser D, Marcus M. Low-resource post processing of noisy OCR output for historical corpus digitisation. In: Proceedings of the 11th International Conference on Language Resources and Evaluation (LREC-2018), pp 2331\u20132339. 2018"},{"key":"1393_CR34","unstructured":"R\u00f6gnvaldsson E, Ingason AK, Sigur\u00f0sson EF, Wallenberg J. The Icelandic parsed historical corpus (IcePaHC). In: Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC\u201912), pp 1977\u20131984. 2012"},{"key":"1393_CR35","doi-asserted-by":"publisher","first-page":"1327","DOI":"10.1007\/s10579-013-9239-y","volume":"47","author":"F S\u00e1nchez-Mart\u00ednez","year":"2013","unstructured":"S\u00e1nchez-Mart\u00ednez F, Mart\u00ednez-Sempere I, Ivars-Ribes X, Carrasco R. An open diachronic corpus of historical Spanish. Lang Resour Evaluat. 2013;47:1327\u201342.","journal-title":"Lang Resour Evaluat"},{"key":"1393_CR36","unstructured":"Sherratt T (2021) Glam workbench\u2014using the trove newspaper gazette harvester (the web app version)"},{"key":"1393_CR37","doi-asserted-by":"crossref","unstructured":"Smith R. An overview of the Tesseract OCR engine. In: Proc. of International Conference on Document Analysis and Recognition, vol\u00a02, pp 629\u2013633. 2007","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"1393_CR38","doi-asserted-by":"crossref","unstructured":"Smith DA, Cordel R, Dillon EM, Stramp N, Wilkerson J. Detecting and modeling local text reuse. In: IEEE\/ACM Joint Conference on Digital Libraries, pp 183\u2013192. 2014","DOI":"10.1109\/JCDL.2014.6970166"},{"key":"1393_CR39","unstructured":"Snoek J, Larochelle H, Adams RP. Practical bayesian optimization of machine learning algorithms. In: Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 2, pp 2951\u20132959. 2012"},{"issue":"1","key":"1393_CR40","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/0734-189X(85)90016-7","volume":"30","author":"S Suzuki","year":"1985","unstructured":"Suzuki S, Abe K. Topological structural analysis of digitized binary images by border following. Comput Vis Graph Image Process. 1985;30(1):32\u201346.","journal-title":"Comput Vis Graph Image Process"},{"key":"1393_CR41","unstructured":"Tanaka K, Chu C, Ren H, Renoust B, Nakashima Y, Takemura N, Nagahara H, Fujikawa T. Constructing a public meeting corpus. In: Proceedings of The 12th Language Resources and Evaluation Conference, pp 1934\u20131940. 2020"},{"key":"1393_CR42","first-page":"91","volume":"8","author":"A Trad","year":"2016","unstructured":"Trad A, Doush I. Improving post-processing optical character recognition documents with arabic language using spelling error detection and correction. Int J Reason Based Intell Syst. 2016;8:91.","journal-title":"Int J Reason Based Intell Syst"},{"key":"1393_CR43","doi-asserted-by":"crossref","unstructured":"Wilkerson J, Smith D, Stramp N. Tracing the flow of policy ideas in legislatures: A text reuse approach. Am J Polit Sci. 2015;59(4)","DOI":"10.1111\/ajps.12175"},{"key":"1393_CR44","doi-asserted-by":"crossref","unstructured":"Xu S, Smith D. Retrieving and combining repeated passages to improve ocr. In: 2017 ACM\/IEEE Joint Conference on Digital Libraries (JCDL), pp 1\u20134. 2017","DOI":"10.1109\/JCDL.2017.7991587"},{"key":"1393_CR45","doi-asserted-by":"crossref","unstructured":"Yamazoe T, Etoh M, Yoshimura T, Tsujino K. Hypothesis preservation approach to scene text recognition with weighted finite-state transducer. In: Proceedings of the 2011 International Conference on Document Analysis and Recognition, pp 359\u2013363. 2011","DOI":"10.1109\/ICDAR.2011.80"},{"key":"1393_CR46","doi-asserted-by":"crossref","unstructured":"Zoph B, Yuret D, May J, Knight K. Transfer learning for low-resource neural machine translation. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pp 1568\u20131575. 2016","DOI":"10.18653\/v1\/D16-1163"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-022-01393-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-022-01393-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-022-01393-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,4]],"date-time":"2024-10-04T15:57:21Z","timestamp":1728057441000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-022-01393-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,25]]},"references-count":46,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2022,11]]}},"alternative-id":["1393"],"URL":"https:\/\/doi.org\/10.1007\/s42979-022-01393-6","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,25]]},"assertion":[{"value":"21 October 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 August 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 September 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they do not have a financial or personal relationship with a third party whose interests could be positively or negatively influenced by the article\u2019s content.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"489"}}