Off-the-shelf spaCy pipelines trained from scratch on the ARCOSG corpus reach 88.6% (fine-grained) and 93.7% (coarse-grained) POS tagging accuracy for Scottish Gaelic, comparable to prior custom-built taggers.
Developing au- tomatic speech recognition for Scottish Gaelic
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Modular Part-of-Speech Tagger for Scottish Gaelic using spaCy
Off-the-shelf spaCy pipelines trained from scratch on the ARCOSG corpus reach 88.6% (fine-grained) and 93.7% (coarse-grained) POS tagging accuracy for Scottish Gaelic, comparable to prior custom-built taggers.