Towards corpora of underdocumented Saami Languages: Ter and Ume Saami
Ilya Egorov, Letizia Hroß, Alexander Veselov, Réka Mizsei (LMU Munich)
01.12.2025, 14:15–15:45
Geschw.-Scholl-Pl. 1 (Hauptgebäude), A 016
https://lmu-munich.zoom-x.de/j/93938720682?pwd=ZnRCV1JnL2w4SVdvMHlCTEtWL2NjZz09
Meeting ID: 939 3872 0682
Passcode: 284661
In this talk, we will share our experience of creating electronic corpora for two low-resource Saami languages: Ume Saami and Ter Saami. Ume Saami is currently spoken by around 20 people in Sweden, and several revitalisation efforts are underway. There has been no active everyday communication in Ter Saami for over two decades, and it appears that there are no longer any speakers. The main sources of linguistic data on both languages are publications containing speech samples from the late 19th and 20th centuries. Until now, these texts have only been available in traditional printed form, making them difficult to use for linguistic research. Our project therefore aims to convert these materials into formats suitable for corpus-based studies. In this talk, we will present preliminary results and discuss the challenges associated with digitising historical text collections, including optical character recognition (OCR), alignment, translation and annotation.