# A Modular Part-of-Speech Tagger for Scottish Gaelic using spaCy

arXiv: https://arxiv.org/abs/2608.04808 · HTML: https://mlsanity.com/paper/2608.04808/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 25 references that are in the map.
- First posted on arXiv 5 Aug 2026.

## Builds on (most cited first, 6 of 6)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios](https://mlsanity.com/paper/2010.12309/) (2020)
- [Low-resource Languages: A Review of Past Work and Future Challenges](https://mlsanity.com/paper/2006.07264/) (2020)
- [Data Augmentation via Dependency Tree Morphing for Low-Resource Languages](https://mlsanity.com/paper/1903.09460/) (2019)
- [A Practitioner's Guide to Building ASR Models for Low-Resource Languages: A Case Study on Scottish Gaelic](https://mlsanity.com/paper/2506.04915/) (2025)
- [A Rule-based Computational Model for Gaidhlig Morphology](https://mlsanity.com/paper/2602.12132/) (2026)

## Abstract (arXiv)

Part-of-speech tagging for low-resource languages remains challenging due to limited annotated data, especially for linguistically complex languages. Gaidhlig (Scottish Gaelic) is a morphologically rich and endangered language with limited digital resources, making it suitable for examining a lightweight language processing approach. This paper describes using the modular spaCy Natural Language Processing framework to build part-of-speech taggers for Gaidhlig using the Annotated Reference Corpus of Scottish Gaelic. We train two models with minimal pre-processing and configuration: one using a fine-grained tagset and another using a reduced coarse-grained tagset. Both models are trained without external embeddings or pre-trained language models, using only supervised learning from the available corpus. The fine-grained model achieves 88.6% tagging accuracy, while the coarse-grained model achieves 93.7%. The results are comparable to those of the two previously published Gaidhlig taggers, indicating that simple, off-the-shelf language processing pipelines can demonstrate good performance in low-resource and morphologically complex linguistic settings.