Home | News

02.09.2026

Teaser image to Barbara Plank Featured in Tagesschau on AI and Bavarian Dialects

Barbara Plank Featured in Tagesschau on AI and Bavarian Dialects

Teaching AI to Understand Regional Languages

MCML PI Barbara Plank is featured in a recent Tagesschau report on the challenges artificial intelligence faces when processing Bavarian dialects. The report highlights a research project collecting dialect recordings to help improve speech recognition and make AI more accessible to regional language communities.

Plank explains that most AI systems are trained primarily on standard German, while dialects can differ significantly in vocabulary, grammar, and pronunciation—even between neighboring regions. Better dialect recognition could benefit everyday applications such as navigation and voice assistants, as well as more critical settings including communication with doctors and healthcare professionals.

#media #research #plank

Related

Link to Teaching Language Models to Express Uncertainty

29.10.2026

Teaching Language Models to Express Uncertainty

An ICLR 2026 paper shows how reinforcement learning improves confidence estimates from language models.

Read more
Link to Runner-Up Prize at AutoML 2026 for Tabular-DC-Bench

27.10.2026

Runner-Up Prize at AutoML 2026 for Tabular-DC-Bench

Tabular-DC-Bench, by MCML Junior Member Mamdouh Aljoud and MCML Director Thomas Seidl, among others, won a runner-up prize at AutoML 2026.

Read more
Link to Welcoming Ewa Szczurek to MCML

27.10.2026

Welcoming Ewa Szczurek to MCML

Ewa Szczurek joins MCML as Professor of AI in Life Sciences at LMU, focusing on probabilistic and generative models for medicine.

Read more
Link to Best Paper Award at AIES 2026 for Work on Algorithmic Contestability

26.10.2026

Best Paper Award at AIES 2026 for Work on Algorithmic Contestability

MCML Junior Member Timo Freiesleben received the Best Paper Award at AIES 2026 for his work on algorithmic contestability.

Read more
Tiny logo
Link to MCML at EMNLP 2026

23.10.2026

MCML at EMNLP 2026

MCML researchers are represented with 47 papers at EMNLP 2026 (31 Main, 11 Findings, and 5 Workshops).

Read more
Back to Top