Universität Innsbruck



22/06/2020: IANLS Albacete Proceedings Published

In summer 2018 all our project members attended the big IANLS (International Association for Neo-Latin Studiens) congress in Albacete (Spain). Now the Acta Conventus Neolatini Albasitensis have been published by Brill, which, in addition to the five plenary papers, contains a further 49 essays on all areas of Neo-Latin Studies.

Our team member Irina Tautschnig  contributed to the new Acta with a paper on Carlo Noceti’s Iris: “The Weaver of Light: Divine Origin of Nature and Natural Science in Carlo Noceti’s Iris”. In her paper, Tautschnig examined the role of one specific strategy to promote science within the text, namely to present scientific discoveries as divinely ordained.


13/05/2020: Noscemus Transkribus Model released – UPDATE: Revised and extended version now available

A revised and extended version of our Transkribus model is now available. For the 2nd version a substantial amount of new pages was added, including prints from the 15th century, texts set in Fraktur and texts with a considerable amount of Greek passages.

The model is available for every registered user in Transkribus and called: Noscemus GM 2.2. Noscemus GM 2.2 is able to read texts set in Antiqua-based typefaces from the 15th, 16th, 17th and 18th century with a high level of accuracy and consistently outperforms most of the standard OCR engines. Although it is tailored towards transcribing (Neo-)Latin texts, Noscemus GM 2.2 also provides convincing results for other languages such as French, Italian and English. The Noscemus model is therefore able to offer help not only to Neo-Latinists, but to all kind of researchers dealing with larger text corpora from the Early Modern Period.

The model is based on training data from the project’s Digital Sourcebook and comprises at present (May 2020) around 1,600 fully corrected pages. In order to give the user a maximum of freedom, standardizations in the transcription process have been kept to a minimum. Normalizations have been implemented only in the following cases: ligatures (e.g. æ, œ, ct, ff) and abbreviations (e.g. -que, -us, -tur, …mm…, …nn…) have been expanded, long s (ſ) transcribed as a normal s, and small caps transcribed as majuscules.

In the model’s current state there remain a handful of known issues: There are occasional inconsistencies in the transcription of quotation marks and diacritics; the error rate for the transcription of Greek words or passages is still high.

Make sure you use the model “Noscemus GM 2.2” when you run the Text Recognition on your document!


29/02/2020: Talk by Irina Tautschnig at “Schönheit vor Weisheit”

Created in celebration of the 350th anniversary of the University of Innsbruck, the exhibition “Schönheit vor Weisheit. Das Wissen der Kunst und die Kunst der Wissenschaft” in the Tyrolean State Museum “Ferdinandeum” explored the relationship between art and science. On the last weekend of its run, a series of talks showcased the range of young research at the university. Our colleague Irina Tautschnig was invited to present her work on Neo-Latin scientific poetry to a wider audience.

The event on the University Homepage


06–07/02/2020: Noscemus at the Transkribus User Conference 2020

From 6 to 7 February 2020 the Transkribus User Conference 2020 took place in Innsbruck. The TUC is an annual gathering of the Transkribus community, where the latest developements in Automated Text Recognition are discussed. Our colleague Stefan Zathammer was invited to present our Transkribus model “Noscemus GM v1” in the public model session.



[news archive]


Funding: European Research Council Advanced Grant
Principal Investigator: Martin Korenjak
Host Institution: Leopold-Franzens-Universität Innsbruck
Duration: 10/2017–09/2022
Project No. 741374
More information on ERC and CORDIS




Nach oben scrollen