This study presents the first fine-tuned Whisper model for the automatic translation of South Tyrolean dialectal speech into Standard German text. To address an unmet need for subtitling and translation, we introduce a small corpus of manually annotated and synthetic speech data compiled for this task. Through fine-tuning and hyperparameter optimisation, our model achieves a BLEU score of 86.18 significantly outperforming baseline error rates. Our findings highlight Whisper's effectiveness in handling dialectal speech, contributing to low-resource language research. The model is already being used in a heritage collaboration for large-scale translation of audiovisual archival material and is also being considered for application in news broadcasting and tourism promotion. Future directions include expanding the training data and extending hyperparameter optimisation to improve the model's performance and generalisation across South Tyrolean dialectal variations.

In this work, we explore the idea of designing a tool to augment the practice of closed-reading a literary text by employing end-user programming practices. The ultimate goal is to help young humanities students learn and appreciate computational thinking skills. The proposed approach is aligned with other methods of applying computer science techniques to explore literary texts (as in digital humanities) but with original goals and means. An initial design concept has been realised as a probe to prompt the discussion among humanities students and teachers. This short paper discusses the design ideas and the feedback from interviews and focus groups involving 25 participants (10 teachers in different humanities fields and 15 university students in humanities as prospective teachers and scholars).

In this paper, we introduce a tool aimed at supporting deep qualitative analysis of digital comics. The tool exploits language-based technologies to facilitate the exploration of relatively large sets of comics. The core idea is that the specific words used in the comics are both an important element of the analysis and an index to navigate and explore the dataset. The design concept has been validated in a pilot study and the findings provide evidence that the approach meets the needs of qualitative analysts with the potential of improving their practices.

We are witnessing a paradigm shift in Human Language Technology (HLT) that may well have an impact on the field comparable to the statistical revolution: acquiring large-scale resources by exploiting collective intelligence. An illustration of this new approach is Phrase Detectives , an interactive online game with a purpose for creating anaphorically annotated resources that makes use of a highly distributed population of contributors with different levels of expertise. The purpose of this article is to first of all give an overview of all aspects of Phrase Detectives, from the design of the game and the HLT methods we used to the results we have obtained so far. It furthermore summarizes the lessons that we have learned in developing this game which should help other researchers to design and implement similar games.