{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T22:34:06Z","timestamp":1758926046069,"version":"3.40.3"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031724398"},{"type":"electronic","value":"9783031724404"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72440-4_12","type":"book-chapter","created":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T17:01:50Z","timestamp":1727197310000},"page":"125-132","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Is Text Normalization Relevant for\u00a0Classifying Medieval Charters?"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8157-8629","authenticated-orcid":false,"given":"Florian","family":"Atzenhofer-Baumgartner","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3913-2946","authenticated-orcid":false,"given":"Tam\u00e1s","family":"Kov\u00e1cs","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,25]]},"reference":[{"key":"12_CR1","unstructured":"Atzenhofer-Baumgartner, F.: Quantifying Formulaic Flexibility of Middle High German Legal Texts. Master\u2019s thesis (2023). http:\/\/unipub.uni-graz.at\/obvugrhs\/8653213"},{"issue":"2","key":"12_CR2","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1075\/nowele.00057.bec","volume":"74","author":"C Becker","year":"2021","unstructured":"Becker, C., Schallert, O.: Areal variation in middle high German: a perspective from charters. NOWELE. North-Western Europ. Lang. Evol. 74(2), 199\u2013241 (2021). https:\/\/doi.org\/10.1075\/nowele.00057.bec","journal-title":"NOWELE. North-Western Europ. Lang. Evol."},{"key":"12_CR3","doi-asserted-by":"publisher","unstructured":"Bollmann, M.: A large-scale comparison of historical text normalization systems. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). p. 3885-3898. Association for Computational Linguistics, Minneapolis, Minnesota (Jun 2019). https:\/\/doi.org\/10.18653\/v1\/N19-1389","DOI":"10.18653\/v1\/N19-1389"},{"key":"12_CR4","doi-asserted-by":"publisher","unstructured":"Chen, T., Guestrin, C.: Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785\u2013794. ACM, San Francisco California USA (Aug 2016). https:\/\/doi.org\/10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"12_CR5","unstructured":"Chiarcos, C., Kosmehl, B., F\u00e4th, C., Sukhareva, M.: Analyzing middle high german syntax with rdf and sparql. In: Calzolari, N., et al., (eds.) Proceedings of the Eleventh International Conference on Language Resources and Evaluation, LREC 2018, Miyazaki, Japan, May 7-12, 2018. European Language Resources Association (ELRA) (2018). http:\/\/www.lrec-conf.org\/proceedings\/lrec2018\/summaries\/1016.html"},{"issue":"2","key":"12_CR6","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1353\/dph.2017.0015","volume":"6","author":"M Chinca","year":"2017","unstructured":"Chinca, M., Young, C.: Responsible philology: editing the kaiserchronik in the digital age. Digital Philol.: J. Medieval Cultures 6(2), 288\u2013329 (2017). https:\/\/doi.org\/10.1353\/dph.2017.0015","journal-title":"Digital Philol.: J. Medieval Cultures"},{"issue":"4","key":"12_CR7","doi-asserted-by":"publisher","first-page":"1523","DOI":"10.1109\/TIT.2005.844059","volume":"51","author":"R Cilibrasi","year":"2005","unstructured":"Cilibrasi, R., Vitanyi, P.: Clustering by compression. IEEE Trans. Inf. Theory 51(4), 1523\u20131545 (2005). https:\/\/doi.org\/10.1109\/TIT.2005.844059","journal-title":"IEEE Trans. Inf. Theory"},{"key":"12_CR8","doi-asserted-by":"publisher","unstructured":"Clavi\u00e9, B., Alphonsus, M.: The unreasonable effectiveness of the baseline: Discussing svms in legal text classification (arXiv:2109.07234) (Oct 2021). https:\/\/doi.org\/10.48550\/arXiv.2109.07234","DOI":"10.48550\/arXiv.2109.07234"},{"issue":"3","key":"12_CR9","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/BF00994018","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273\u2013297 (1995). https:\/\/doi.org\/10.1007\/BF00994018","journal-title":"Mach. Learn."},{"issue":"2","key":"12_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3604931","volume":"56","author":"M Ehrmann","year":"2023","unstructured":"Ehrmann, M., Hamdi, A., Pontes, E.L., Romanello, M., Doucet, A.: Named entity recognition and classification in historical documents: a survey. ACM Comput. Surv. 56(2), 1\u201347 (2023). https:\/\/doi.org\/10.1145\/3604931","journal-title":"ACM Comput. Surv."},{"key":"12_CR11","volume-title":"Documentalit\u00e0: perch\u00e9 \u00e8 necessario lasciar tracce","author":"M Ferraris","year":"2014","unstructured":"Ferraris, M.: Documentalit\u00e0: perch\u00e9 \u00e8 necessario lasciar tracce, 2nd edn. Laterza, Roma (2014)","edition":"2"},{"issue":"5","key":"12_CR12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0232525","volume":"15","author":"Y HaCohen-Kerner","year":"2020","unstructured":"HaCohen-Kerner, Y., Miller, D., Yigal, Y.: The influence of preprocessing on text classification using a bag-of-words representation. PLoS ONE 15(5), e0232525 (2020). https:\/\/doi.org\/10.1371\/journal.pone.0232525","journal-title":"PLoS ONE"},{"key":"12_CR13","doi-asserted-by":"publisher","unstructured":"He, P., Liu, X., Gao, J., Chen, W.: Deberta: decoding-enhanced bert with disentangled attention (arXiv:2006.03654) (Oct 2021). https:\/\/doi.org\/10.48550\/arXiv.2006.03654","DOI":"10.48550\/arXiv.2006.03654"},{"issue":"11","key":"12_CR14","doi-asserted-by":"publisher","first-page":"5252","DOI":"10.1109\/TIP.2016.2602078","volume":"25","author":"S He","year":"2016","unstructured":"He, S., Samara, P., Burgers, J., Schomaker, L.: A multiple-label guided clustering algorithm for historical document dating and localization. IEEE Trans. Image Process. 25(11), 5252\u20135265 (2016). https:\/\/doi.org\/10.1109\/TIP.2016.2602078","journal-title":"IEEE Trans. Image Process."},{"key":"12_CR15","doi-asserted-by":"publisher","unstructured":"Jiang, Z., Yang, M., Tsirlin, M., Tang, R., Dai, Y., Lin, J.: \u201clow-resource\u201d text classification: a parameter-free classification method with compressors. In: Findings of the Association for Computational Linguistics: ACL 2023. p. 6810-6828. Association for Computational Linguistics, Toronto, Canada (Jul 2023). https:\/\/doi.org\/10.18653\/v1\/2023.findings-acl.426","DOI":"10.18653\/v1\/2023.findings-acl.426"},{"key":"12_CR16","doi-asserted-by":"publisher","unstructured":"Keogh, E., Lonardi, S., Ratanamahatana, C.A.: Towards parameter-free data mining. In: Proceedings of the tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 206\u2013215. ACM, Seattle WA USA (Aug 2004). https:\/\/doi.org\/10.1145\/1014052.1014077","DOI":"10.1145\/1014052.1014077"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Kragl, F.: Normalmittelhochdeutsch. theorieentwurf einer gelebten praxis. Zeitschrift f\u00fcr Deutsches Altertum und Deutsche Literatur 144(1), 1-27 (2015)","DOI":"10.3813\/zfda-2015-0001"},{"issue":"2","key":"12_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3495162","volume":"13","author":"Q Li","year":"2022","unstructured":"Li, Q., et al.: A survey on text classification: from traditional to deep learning. ACM Trans. Intell. Syst. Technol. 13(2), 1\u201341 (2022). https:\/\/doi.org\/10.1145\/3495162","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"12_CR19","doi-asserted-by":"publisher","unstructured":"Liu, Y., et al.: Roberta: A robustly optimized bert pretraining approach (arXiv:1907.11692) (Jul 2019). https:\/\/doi.org\/10.48550\/arXiv.1907.11692","DOI":"10.48550\/arXiv.1907.11692"},{"key":"12_CR20","doi-asserted-by":"publisher","unstructured":"Manjavacas, E., Fonteyn, L.: Adapting vs. pre-training language models for historical languages. J. Data Mining Digital Humanities NLP4DH (Jun 2022). https:\/\/doi.org\/10.46298\/jdmdh.9152","DOI":"10.46298\/jdmdh.9152"},{"issue":"3","key":"12_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3439726","volume":"54","author":"S Minaee","year":"2022","unstructured":"Minaee, S., Kalchbrenner, N., Cambria, E., Nikzad, N., Chenaghlu, M., Gao, J.: Deep learning-based text classification: A comprehensive review. ACM Comput. Surv. 54(3), 1\u201340 (2022). https:\/\/doi.org\/10.1145\/3439726","journal-title":"ACM Comput. Surv."},{"key":"12_CR22","doi-asserted-by":"publisher","unstructured":"Nie, E., Schmid, H., Sch\u00fctze, H.: Cross-lingual constituency parsing for middle high German: a delexicalized approach (arXiv:2308.04645) (Aug 2023). https:\/\/doi.org\/10.48550\/arXiv.2308.04645","DOI":"10.48550\/arXiv.2308.04645"},{"key":"12_CR23","doi-asserted-by":"publisher","unstructured":"Petran, F., Bollmann, M., Dipper, S., Klein, T.: Rem: a reference corpus of middle high german \u2013 corpus compilation, annotation, and access. J. Lang. Technol. Comput. Linguist. 31(2), 1\u201315 (2016). https:\/\/doi.org\/10.21248\/jlcl.31.2016.208","DOI":"10.21248\/jlcl.31.2016.208"},{"key":"12_CR24","doi-asserted-by":"publisher","unstructured":"Sukhareva, M.: Context-aware text normalisation for historical dialects. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 1023\u20131036. International Committee on Computational Linguistics, Barcelona, Spain (Online) (2020). https:\/\/doi.org\/10.18653\/v1\/2020.coling-main.89","DOI":"10.18653\/v1\/2020.coling-main.89"},{"key":"12_CR25","unstructured":"Torres\u00a0Aguilar, S.: Multilingual named entity recognition for medieval charters using stacked embeddings and bert-based models. In: Sprugnoli, R., Passarotti, M. (eds.) Proceedings of the Second Workshop on Language Technologies for Historical and Ancient Languages, pp. 119\u2013128. European Language Resources Association, Marseille, France (Jun 2022). https:\/\/aclanthology.org\/2022.lt4hala-1.17"},{"key":"12_CR26","doi-asserted-by":"publisher","unstructured":"Torres\u00a0Aguilar, S., Jolivet, V.: Handwritten text recognition for documentary medieval manuscripts. J. Data Mining Digital Humanities. Historical Documents and automatic text recognition (Dec 2023). https:\/\/doi.org\/10.46298\/jdmdh.10484","DOI":"10.46298\/jdmdh.10484"},{"key":"12_CR27","doi-asserted-by":"publisher","unstructured":"Uysal, A.K., Gunal, S.: The impact of preprocessing on text classification. Inf. Process. Manage. 50(1), 104\u2013112 (2014). https:\/\/doi.org\/10.1016\/j.ipm.2013.08.006","DOI":"10.1016\/j.ipm.2013.08.006"},{"issue":"2","key":"12_CR28","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1007\/s42803-019-00025-5","volume":"1","author":"G Vogeler","year":"2019","unstructured":"Vogeler, G.: The \u2018assertive edition\u2019: on the consequences of digital methods in scholarly editing for historians. Int. J. Digital Human. 1(2), 309\u2013322 (2019). https:\/\/doi.org\/10.1007\/s42803-019-00025-5","journal-title":"Int. J. Digital Human."},{"key":"12_CR29","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1007\/978-3-031-25891-6_23","volume-title":"Machine Learning, Optimization, and Data Science: 8th International Conference, LOD 2022, Certosa di Pontignano, Italy, September 18\u201322, 2022, Revised Selected Papers, Part II","author":"Y Wahba","year":"2023","unstructured":"Wahba, Y., Madhavji, N., Steinbacher, J.: A comparison of SVM Against Pre-trained Language Models (PLMs) for text classification tasks. In: Nicosia, G., et al. (eds.) Machine Learning, Optimization, and Data Science: 8th International Conference, LOD 2022, Certosa di Pontignano, Italy, September 18\u201322, 2022, Revised Selected Papers, Part II, pp. 304\u2013313. Springer Nature Switzerland, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-25891-6_23"},{"issue":"3","key":"12_CR30","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1515\/zfs-2021-2037","volume":"40","author":"S Waldenberger","year":"2021","unstructured":"Waldenberger, S., Dipper, S., Lemke, I.: Towards a broad-coverage graphemic analysis of large historical corpora. Z. Sprachwiss. 40(3), 401\u2013420 (2021). https:\/\/doi.org\/10.1515\/zfs-2021-2037","journal-title":"Z. Sprachwiss."}],"container-title":["Lecture Notes in Computer Science","Linking Theory and Practice of Digital Libraries"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72440-4_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T17:03:22Z","timestamp":1727197402000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72440-4_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031724398","9783031724404"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72440-4_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"25 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TPDL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Theory and Practice of Digital Libraries","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ljubljana","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovenia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tpdl2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/tpdl2024.nuk.si\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}