Onomasiological Sense Alignment Across Dialect Dictionaries. A Taxonomy-Constrained LLM Classification

Nathalie Mederake, Nico Urbach, Hanna Fischer, Alfred Lameli


Abstract
We propose a taxonomy-guided approach to semantic alignment that assigns lexicographic senses to an onomasiological taxonomy derived from the Hallig–Wartburg/Post system. Using an LLM under strict taxonomic constraints, short and heterogeneous meaning descriptions are assigned to a common conceptual space. Evaluation against expert annotation shows that run-to-run model agreement (kappa = 0.73) closely matches human agreement (kappa = 0.74), with robustness at coarse taxonomic levels and predictable degradation at finer granularity. A qualitative network analysis demonstrates the resulting potential for cross-dictionary exploration of dialectal variation in semantics.
Anthology ID:
2026.vardial-1.10
Volume:
Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects
Month:
March
Year:
2026
Address:
Rabat, Morocco
Venues:
VarDial | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
123–138
Language:
URL:
https://aclanthology.org/2026.vardial-1.10/
DOI:
Bibkey:
Cite (ACL):
Nathalie Mederake, Nico Urbach, Hanna Fischer, and Alfred Lameli. 2026. Onomasiological Sense Alignment Across Dialect Dictionaries. A Taxonomy-Constrained LLM Classification. In Proceedings of the 13th Workshop on NLP for Similar Languages, Varieties and Dialects, pages 123–138, Rabat, Morocco. Association for Computational Linguistics.
Cite (Informal):
Onomasiological Sense Alignment Across Dialect Dictionaries. A Taxonomy-Constrained LLM Classification (Mederake et al., VarDial 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.vardial-1.10.pdf