Natural Language Processing for Dialects and Low-Resource Language Varieties

MCML Authors

Verena Blaschke

Dr.

* Former Member

→ Group Barbara Plank
 AI and Computational Linguistics

Abstract

This dissertation advances NLP for non-standardized dialects and other low-resource language varieties, with a particular focus on Upper German dialects. It investigates community needs and cross-lingual transfer, identifies factors that limit model robustness to linguistic variation, and develops strategies to improve transfer from standard languages. The work also releases new annotated dialect datasets, including resources for previously underrepresented Bavarian. (Shortened).

phdthesis Bla26

---

Dissertation

LMU München. Jun. 2026

---

Authors

V. Blaschke

---

Links

DOI

---

Research Area

 B2 | Natural Language Processing