{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:18:05Z","timestamp":1761175085903,"version":"build-2065373602"},"reference-count":26,"publisher":"Polish Information Processing Society","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.15439\/2025f1103","type":"proceedings-article","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T07:44:23Z","timestamp":1761119063000},"page":"471-478","source":"Crossref","is-referenced-by-count":0,"title":["Treating OCR Output as a Language (TOOL) \u2013 Improving OCR Output with Seq2Seq Translation"],"prefix":"10.15439","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3011-7626","authenticated-orcid":true,"given":"Thomas","family":"Asselborn","sequence":"first","affiliation":[{"name":"University of Hamburg"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1854-225X","authenticated-orcid":true,"given":"Magnus","family":"Bender","sequence":"additional","affiliation":[{"name":"Aarhus University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1174-3323","authenticated-orcid":true,"given":"Ralf","family":"M\u00f6ller","sequence":"additional","affiliation":[{"name":"University of Hamburg"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0144-5429","authenticated-orcid":true,"given":"Sylvia","family":"Melzer","sequence":"additional","affiliation":[{"name":"University of Hamburg"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"6175","published-online":{"date-parts":[[2025,10,15]]},"reference":[{"key":"ref1","unstructured":"Altbach, P.G., Reisberg, L., Rumbley, L.E.: Trends in Global Higher\nEducation: Tracking an Academic Revolution. UNESCO Publishing,\nParis (2009), https:\/\/unesdoc.unesco.org\/ark:\/48223\/pf0000183219, a report prepared for the UNESCO 2009 World Conference on Higher\nEducation"},{"key":"ref2","doi-asserted-by":"publisher","unstructured":"Asselborn, T., D\u00f6rpinghaus, J., Kausar, F., M\u00f6ller, R., Melzer, S.:\nEnhancing Text Recognition of Damaged Documents through Synergistic OCR and Large Language Models, pp. 29\u201336. Polish Information\nProcessing Society (Sep 2024). https:\/\/doi.org\/10.15439\/2024F7400","DOI":"10.15439\/2024F7400"},{"key":"ref3","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural Machine Translation by\nJointly Learning to Align and Translate (2016), https:\/\/arxiv.org\/abs\/1409.0473"},{"key":"ref4","unstructured":"Banerjee, S., Lavie, A.: METEOR: An Automatic Metric for MT\nEvaluation with Improved Correlation with Human Judgments. In:\nGoldstein, J., Lavie, A., Lin, C.Y., Voss, C. (eds.) Proceedings of\nthe ACL Workshop on Intrinsic and Extrinsic Evaluation Measures\nfor Machine Translation and\/or Summarization. pp. 65\u201372. Association for Computational Linguistics, Ann Arbor, Michigan (Jun 2005),\nhttps:\/\/aclanthology.org\/W05-0909\/"},{"key":"ref5","unstructured":"Bundesregierung der Bundesrepublik Deutschland: Handwerksordnung\n(HwO) in der Neufassung vom 24. September 1998. Bundesgesetzblatt\nTeil I Nr. 67, Bonn (1998), http:\/\/www.bgbl.de\/xaver\/bgbl\/start.xav?startbk=Bundesanzeiger_BGBl&jumpTo=bgbl198s3074.pdf"},{"key":"ref6","unstructured":"Bundesregierung der Bundesrepublik Deutschland: Berufsbildungsgesetz (BBiG) in der Neufassung vom 23. M\u00e4rz 2005. Bundesgesetzblatt\nTeil I Nr. 20, Bonn (2005), https:\/\/www.bgbl.de\/xaver\/bgbl\/start.xav?startbk=Bundesanzeiger_BGBl&jumpTo=bgbl105s0931.pdf"},{"key":"ref7","doi-asserted-by":"publisher","unstructured":"Busemeyer, M.R., Trampusch, C.: The Political Economy of\nCollective Skill Formation. Oxford University Press (11 2011).\nhttps:\/\/doi.org\/10.1093\/acprof:oso\/9780199599431.001.0001","DOI":"10.1093\/acprof:oso\/9780199599431.001.0001"},{"key":"ref8","doi-asserted-by":"publisher","unstructured":"Cedefop: Vocational education and training in Europe, 1995\u20132035:\nScenarios for European vocational education and training in the 21st\ncentury. No. 114 in Cedefop reference series, Publications Office of the\nEuropean Union, Luxembourg (2020). https:\/\/doi.org\/10.2801\/794471","DOI":"10.2801\/794471"},{"key":"ref9","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: Pre-training of\nDeep Bidirectional Transformers for Language Understanding. CoRR\nabs\/1810.04805 (2018), http:\/\/arxiv.org\/abs\/1810.04805"},{"key":"ref10","unstructured":"European Commission: Education Levels (nd), https:\/\/education.ec.europa.eu\/education-levels, accessed: 2025-05-09"},{"key":"ref11","doi-asserted-by":"crossref","unstructured":"Feng, F., Yang, Y., Cer, D., Arivazhagan, N., Wang, W.: Language-agnostic BERT Sentence Embedding (2022), https:\/\/arxiv.org\/abs\/2007.01852","DOI":"10.18653\/v1\/2022.acl-long.62"},{"key":"ref12","doi-asserted-by":"publisher","unstructured":"Junczys-Dowmunt, M., Grundkiewicz, R., Dwojak, T., Hoang, H.,\nHeafield, K., Neckermann, T., Seide, F., Germann, U., Aji, A.F.,\nBogoychev, N., Martins, A.F.T., Birch, A.: Marian: Fast Neural Machine Translation in C++. In: Liu, F., Solorio, T. (eds.) Proceedings of ACL 2018, System Demonstrations. pp. 116\u2013121. Association for Computational Linguistics, Melbourne, Australia (Jul 2018).\nhttps:\/\/doi.org\/10.18653\/v1\/P18-4020","DOI":"10.18653\/v1\/P18-4020"},{"key":"ref13","doi-asserted-by":"crossref","unstructured":"Junczys-Dowmunt, M., Grundkiewicz, R., Dwojak, T., Hoang, H.,\nHeafield, K., Neckermann, T., Seide, F., Germann, U., Aji, A.F., Bogoychev, N., Martins, A.F.T., Birch, A.: Marian: Fast Neural Machine\nTranslation in C++ (2018), https:\/\/arxiv.org\/abs\/1804.00344","DOI":"10.18653\/v1\/P18-4020"},{"key":"ref14","doi-asserted-by":"publisher","unstructured":"Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A.,\nLevy, O., Stoyanov, V., Zettlemoyer, L.: BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. In: Jurafsky, D., Chai, J., Schluter,\nN., Tetreault, J. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. pp. 7871\u20137880. Association for Computational Linguistics, Online (Jul 2020).\nhttps:\/\/doi.org\/10.18653\/v1\/2020.acl-main.703","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref15","unstructured":"Lin, C.Y.: ROUGE: A Package for Automatic Evaluation of Summaries.\nIn: Text Summarization Branches Out. pp. 74\u201381. Association for Computational Linguistics, Barcelona, Spain (Jul 2004), https:\/\/aclanthology.org\/W04-1013\/"},{"key":"ref16","doi-asserted-by":"publisher","unstructured":"Loper, E., Bird, S.: NLTK: the Natural Language Toolkit. In: Proceedings of the ACL-02 Workshop on Effective Tools and Methodologies for\nTeaching Natural Language Processing and Computational Linguistics\n- Volume 1. p. 63\u201370. ETMTNLP \u201902, Association for Computational\nLinguistics, USA (2002). https:\/\/doi.org\/10.3115\/1118108.1118117","DOI":"10.3115\/1118108.1118117"},{"key":"ref17","unstructured":"Melhuish, E.C., Ereky-Stevens, K., Petrogiannis, K., Aricescu, A.M.,\nPenderi, E., Rentzou, K., Tawell, A., Slot, P., Broekhuizen, M., Leseman,\nP.: A review of research on the effects of Early Childhood Education and\nCare (ECEC) upon child development. Technical report, European Commission (2015), https:\/\/eprints.bbk.ac.uk\/id\/eprint\/16443\/, cARE project;\nCurriculum Quality Analysis and Impact Review of European Early\nChildhood Education and Care (ECEC)"},{"key":"ref18","unstructured":"N\u00e9meth, L., Foundation, F.: Hunspell, https:\/\/hunspell.github.io\/, accessed: 2025-02-15"},{"key":"ref19","doi-asserted-by":"publisher","unstructured":"OECD: Education at a Glance 2021: OECD Indicators. OECD Publishing, Paris (2021). https:\/\/doi.org\/10.1787\/b35a14e5-en","DOI":"10.1787\/b35a14e5-en"},{"key":"ref20","doi-asserted-by":"publisher","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a Method for\nAutomatic Evaluation of Machine Translation. In: Isabelle, P., Charniak,\nE., Lin, D. (eds.) Proceedings of the 40th Annual Meeting of the\nAssociation for Computational Linguistics. pp. 311\u2013318. Association for\nComputational Linguistics, Philadelphia, Pennsylvania, USA (Jul 2002).\nhttps:\/\/doi.org\/10.3115\/1073083.1073135","DOI":"10.3115\/1073083.1073135"},{"key":"ref21","unstructured":"Radford, A., Narasimhan, K.: Improving Language Understanding by\nGenerative Pre-Training. In: Computer Science, Linguistics (2018),\nhttps:\/\/api.semanticscholar.org\/CorpusID:49313245"},{"key":"ref22","doi-asserted-by":"crossref","unstructured":"Schiersmann, C.: Weiterbildungsberatung im Kontext der Nationalen\nWeiterbildungsstrategie: Finanzielle und strukturelle Aspekte. Hessische\nBl\u00e4tter f\u00fcr Volksbildung 72(1), 43\u201353 (2022)","DOI":"10.3278\/HBV2201W005"},{"key":"ref23","doi-asserted-by":"crossref","unstructured":"Smith, R.: An Overview of the Tesseract OCR Engine. In: ICDAR\n\u201907: Proceedings of the Ninth International Conference on Document Analysis and Recognition. pp. 629\u2013633. IEEE Computer Society, Washington, DC, USA (2007), https:\/\/storage.googleapis.com\/pub-tools-public-publication-data\/pdf\/33418.pdf","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"ref24","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to Sequence Learning with\nNeural Networks (2014), https:\/\/arxiv.org\/abs\/1409.3215"},{"key":"ref25","doi-asserted-by":"publisher","unstructured":"UNESCO, UNICEF: Global Report on Early Childhood Care and\nEducation: The Right to a Strong Foundation. UNESCO and UNICEF,\nParis (2024). https:\/\/doi.org\/10.54675\/FWQA2113","DOI":"10.54675\/FWQA2113"},{"key":"ref26","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez,\nA.N., Kaiser, L., Polosukhin, I.: Attention Is All You Need (2023), https:\/\/arxiv.org\/abs\/1706.03762"}],"event":{"name":"20th Conference on Computer Science and Intelligence Systems (FedCSIS)","theme":"Computer Science and Intelligence Systems","location":"Krak\u00f3w, Poland","acronym":"FedCSIS","number":"20","start":{"date-parts":[[2025,9,14]]},"end":{"date-parts":[[2025,9,17]]}},"container-title":["Annals of Computer Science and Information Systems","Proceedings of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS)"],"original-title":[],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T07:48:32Z","timestamp":1761119312000},"score":1,"resource":{"primary":{"URL":"https:\/\/annals-csis.org\/Volume_43\/drp\/1103.html"}},"subtitle":[],"proceedings-subject":"Computer Science and Information Systems","short-title":[],"issued":{"date-parts":[[2025,10,15]]},"references-count":26,"URL":"https:\/\/doi.org\/10.15439\/2025f1103","relation":{},"ISSN":["2300-5963"],"issn-type":[{"value":"2300-5963","type":"print"}],"subject":[],"published":{"date-parts":[[2025,10,15]]}}}