19–23 Oct 2026
Lanthieri Mansion, Vipava
Europe/Ljubljana timezone

Toward the first syntactically annotated corpus of Slovenian dialects: an LLM-assisted pipeline from raw transcripts to Universal Dependencies

21 Oct 2026, 11:00
15m
Lanthieri Mansion, Vipava

Lanthieri Mansion, Vipava

Glavni trg 8, Vipava, SI 5271, Slovenia

Speaker

Varvara Magomedova (UNG)

Description

Slovenian dialects — among the most diverse in the Slavic world — remain almost invisible to language technology: no dialect corpus with morphosyntactic annotation exists, and standard NLP tools fail on dialect input. I present work toward the first Universal Dependencies (UD) annotated corpus of Slovenian dialects, built with a modular, LLM-assisted pipeline.
The pipeline has four stages. (1) Collection: merge and quality-filter heterogeneous sources (e.g., GOKO, Fran dialect dictionaries, and others smaller sources) and mine dialect–standard glossaries from inline glosses, dictionaries, and word-aligned transcriptions. (2) Normalization: dialect forms are mapped to standard Slovenian through a cascade of deterministic phonological rules, lexicon lookups expanded via Sloleks inflectional paradigms, and — only for unresolved tokens — the Slovenian generative model GaMS as a constrained word-level oracle, under a strict one-to-one token mapping that preserves alignment with the original forms. (3) Annotation: normalized text is parsed with CLASSLA-Stanza; dialect forms are retained and each token receives a variety tag (standard/non-standard/dialectal). (4) Gold data and fine-tuning: a manually corrected subcorpus feeds fine-tuning of SloBERTa and GaMS, closing the loop between rule-based and neural components.
I report first results on normalization accuracy and parser performance, discuss possible synthetic dialect data generation as an augmentation strategy, and argue that hybrid rule–LLM cascades are a realistic path to treebanks for non-standard varieties of low-resource languages.

Author

Presentation materials

There are no materials yet.