AI for Endangered Languages

Since 2012, Prof. Dr. Oliver Bendel (FHNW School of Business) has initiated and implemented a wide variety of chatbots and voice assistants. These systems have been covered by the media and have even attracted the interest of NASA. His theoretical foundation and practical expertise stem from his doctoral dissertation on this topic, which dates back a quarter of a century. Since 2022, his focus has been on dialogue systems for dead and endangered languages. This work has resulted in @ve, a chatbot for Latin (implemented by Karim N’Diaye), @llegra, a voice-enabled chatbot for Vallader, a variety of Romansh (implemented by Dalil Jabou), and kAIxo, a voice-enabled chatbot for Basque (implemented by Nicolas Lluis Araya). In addition, Oliver Bendel is experimenting with chatbots for extinct languages such as Egyptian and Akkadian. On April 8, 2026, his article „Chatbots for Dead, Endangered, and Extinct Languages: Possibilities and Limitations of Generative AI for Continuing Education“ was published in Wiley Industry News. The article focuses on the question of how chatbots based on generative AI can contribute to the preservation and promotion of dead, endangered, and extinct languages in continuing education, as well as in formal education. Oliver Bendel is also involved in the University of Applied Sciences of the Grisons‘ IdiomVoice project, which will be presented on June 17, 2026, at the GRdigital Project Showcase during an evening networking reception. Visitors to the showcase will have the opportunity to explore the current prototype and interact directly in Sursilvan with the two chatbot characters, Lina and Brida. With @llegra, Lina, and Brida, Graubünden has gained several digital ambassadors for its Romansh idioms.

Abb.: @llegra im Juli 2023 in Graubünden

Chatbots for Dead, Endangered, and Extinct Languages

On April 8, 2026, the article „Chatbots for Dead, Endangered, and Extinct Languages: Possibilities and Limitations of Generative AI for Continuing Education“ by Oliver Bendel was published in Wiley Industry News. The focus is on how chatbots based on generative AI can contribute to the preservation and promotion of dead, endangered, and extinct languages in continuing education (as well as in vocational training). Following an introduction to the technical and conceptual foundations, several projects at the FHNW School of Business are presented and discussed from technical, ethical, and didactic perspectives. These dimensions are revisited in the next section and expanded into general and overarching considerations. Finally, possible and necessary steps are outlined that go beyond the purely technological discourse. Additionally, an outlook is provided on future possibilities related to new versions of large language models. This article provides the first comprehensive overview of the projects initiated by Oliver Bendel that are dedicated to dead, endangered, and extinct languages, including @ve (for Latin), @llegra (for Vallader), and kAIxo (for Basque), as well as Cleop@tr@ (Egyptian). It can be accessed via the publisher’s website or downloaded here as a PDF.

Fig.: Oliver Bendel at the Karnak Temple (Photo: Stefanie Hauske)

With kAIxo You Can Chat in Basque

The final presentation of the „kAIxo“ project took place on January 9, 2025. Nicolas Lluis Araya was the project team member. The FHNW School of Business has been developing chatbots for dead, endangered, and extinct languages for several years. A well-known example is @llegra, a chatbot for Vallader. In the spring of 2024, Oliver Bendel tested the reach of GPTs for endangered languages such as Irish (Irish Gaelic), Maori, and Basque. According to ChatGPT, there is a relatively large amount of training material for them. On May 12, 2024 – after Irish Girl and Maori Girl – a first version of Adelina, a chatbot for Basque, was created. It was later improved in a second version. As part of the „kAIxo“ project (the Basque “kaixo” corresponds to the English „hello“), the chatbot kAIxo was built, which speaks Basque. Its purpose is to keep users practicing written or spoken language or to develop the desire to learn the endangered language. The chatbot is based on GPT-4o and Gemini 1.5 Flash, and the user can select his or her preferred large language model (LLM). Retrieval-augmented Generation (RAG) plays a central role. The ChatSubs dataset is used, which contains subtitles of movie dialogs in Basque. Thanks to a text-to-speech engine, the chatbot can also speak. At the final presentation, Nicolas Lluis Araya presented a working prototype that can be accessed via www.kaixo.ch.

Fig.: The kAIxo website