Digital resources in the Social Sciences and Humanities OpenEdition Our platforms OpenEdition Books OpenEdition Journals Hypotheses Calenda Libraries OpenEdition Freemium Follow us

DiDip @ TPDL2024

Exactly one week ago, we presented a short paper as a poster at the 2024 edition of TPDL (International Conference on Theory and Practice of Digital Libraries) in Ljubljana, Slovenia (September 24-27).

In essence, we showcase that (historical) language normalization is often not necessary in the face of specific classification tasks. We do so using the example of Middle High German charters. For tackling the task, we test multiple models; we find results are very solid just by just using 30 year old techniques, such as SVMs, and NOT transformers. Looking back, we argue for being more thoughtful about where to allocate time resources of domain experts.

A remark on the venue: TPDL, although insiders say the venue has become decreasingly technical over the years, this trend is obviously mitigated by the introduction of extra strands for document analysis and information retrieval, to which we had submitted our work accordingly.

From the viewpoint of DiDip’s interest, we found several other contributions noteworthy, the most striking being the keynote by Maud Ehrmann, who delivered some updates on the Impresso project. Its team does foundational work to pushing the boundaries of integrated research environments, aka Data Labs.

Other honorable mentions, timely, and whose titles are self-explanatory, go to Alex Ghiriti et al., Nicolò Pratelli & Valentina Bartalesi, and Carlos González et al..

References
Atzenhofer-Baumgartner, F., Kovács, T. (2024). Is Text Normalization Relevant for Classifying Medieval Charters?. In: Antonacopoulos, A., et al. Linking Theory and Practice of Digital Libraries. TPDL 2024. Lecture Notes in Computer Science, vol 15178. Springer, Cham. https://doi.org/10.1007/978-3-031-72440-4_12

Ehrmann, M. (2024). Keynote. Impresso Beyond Borders: Connecting Historical Newspapers and Radio. In: Antonacopoulos, A., et al. Linking Theory and Practice of Digital Libraries. TPDL 2024. Lecture Notes in Computer Science, vol 15178. Springer, Cham.

Ghiriti, A., Göderle, W., Kern, R. (2024). Exploring the Capabilities of GPT4-Vision as OCR Engine. In: Antonacopoulos, A., et al. Linking Theory and Practice of Digital Libraries. TPDL 2024. Lecture Notes in Computer Science, vol 15178. Springer, Cham. https://doi.org/10.1007/978-3-031-72440-4_1

Pratelli, N., Bartalesi, V. (2024). Using Geospatial Semantic Web for Exploring Geographic Knowledge in Medieval Manuscripts. In: Antonacopoulos, A., et al. Linking Theory and Practice of Digital Libraries. TPDL 2024. Lecture Notes in Computer Science, vol 15178. Springer, Cham. https://doi.org/10.1007/978-3-031-72440-4_7

González-Gallardo, CE., Tran, H.T.H., Hamdi, A., Doucet, A. (2024). Leveraging Open Large Language Models for Historical Named Entity Recognition. In: Antonacopoulos, A., et al. Linking Theory and Practice of Digital Libraries. TPDL 2024. Lecture Notes in Computer Science, vol 15177. Springer, Cham. https://doi.org/10.1007/978-3-031-72437-4_22


OpenEdition suggests that you cite this post as follows:
atzenhofer (October 3, 2024). DiDip @ TPDL2024. DiDip. Retrieved March 26, 2025 from https://didip.hypotheses.org/3009


You may also like...