Transformer-based HTR for Historical Documents

Autor: Ströbel, Phillip Benjamin, Clematide, Simon, Volk, Martin, Hodel, Tobias

We apply the TrOCR framework to real-world, historical manuscripts and show that TrOCR per se is a strong model, ideal for transfer learning. TrOCR has been trained on English only, but it can adapt to other languages that use the Latin alphabet fair

Externí odkaz: http://arxiv.org/abs/2203.11008

Multimodal knowledge graph construction of Chinese traditional operas and sentiment and genre recognition

Autor: Fan, Tao, Wang, Hao, Hodel, Tobias

Publikováno v: In Journal of Cultural Heritage July-August 2023 62:32-44

Transforming scholarship in the archives through handwritten text recognition : Transkribus as a case study

Autor: Muehlberger, Guenter, Seaward, Louise, Terras, Melissa, Ares Oliveira, Sofia, Bosch, Vicente, Bryan, Maximilian, Colutto, Sebastian, Déjean, Hervé, Diem, Markus, Fiel, Stefan, Gatos, Basilis, Greinoecker, Albert, Grüning, Tobias, Hackl, Guenter, Haukkovaara, Vili, Heyer, Gerhard, Hirvonen, Lauri, Hodel, Tobias, Jokinen, Matti, Kahle, Philip, Kallio, Mario, Kaplan, Frederic, Kleber, Florian, Labahn, Roger, Lang, Eva Maria, Laube, Sören, Leifert, Gundram, Louloudis, Georgios, McNicholl, Rory, Meunier, Jean-Luc, Michael, Johannes, Mühlbauer, Elena, Philipp, Nathanael, Pratikakis, Ioannis, Puigcerver Pérez, Joan, Putz, Hannelore, Retsinas, George, Romero, Verónica, Sablatnig, Robert, Sánchez, Joan Andreu, Schofield, Philip, Sfikas, Giorgos, Sieber, Christian, Stamatopoulos, Nikolaos, Strauß, Tobias, Terbul, Tamara, Toselli, Alejandro Héctor, Ulreich, Berthold, Villegas, Mauricio, Vidal, Enrique, Walcher, Johanna, Weidemann, Max, Wurster, Herbert, Zagoris, Konstantinos

Publikováno v: Journal of Documentation, 2019, Vol. 75, Issue 5, pp. 954-976.

Externí odkaz: http://www.emeraldinsight.com/doi/10.1108/JD-07-2018-0114

Pre-Modern Data: Applying Language Modeling and Named Entity Recognition on Criminal Records in the City of Bern

Autor: Hodel, Tobias, Prada Ziegler, Ismail, Schneider, Christa

Publikováno v: Hodel, Tobias; Prada Ziegler, Ismail; Schneider, Christa (2023). Pre-Modern Data: Applying Language Modeling and Named Entity Recognition on Criminal Records in the City of Bern. In: Digital Humanities 2023. Collaboration as Opportunity (DH2023). Graz. 13.07.2023. 10.5281/zenodo.8107616

How can NLP technologies be applied and measured on pre-modern documents? Based on a large handwritten dataset from the tower of Bern, we tested available language models and taggers, showcasing that specific forms of representation and identificatio

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0741b870b63e72965f2b8efe4c5f7740

20 Years of Digital Medievalist – A Reflection on the Development of a Community

Autor: Bleier, Roman, Borek, Luise, Campagnolo, Alberto, Fischer, Franz, Gengnagel, Tessa, Hodel, Tobias

Initially, Digital Medievalist was understood to be a group of supportive scholars, that wanted to test digital methods for their research projects. Since then, it has developed into a scholarly community with 1500 members and has become an integral

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::40f95fa2dabae536c30d6a82b71ad8f3