发表机构
School of Computing, Engineering, & the Built Environment, Edinburgh Napier University（爱丁堡龙比亚大学计算、工程与建成环境学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文基于spaCy框架，用苏格兰盖尔语标注参考语料库训练出两个形态标注模型，在低资源形态复杂的盖尔语上取得与现有模型相当的准确率，证明现成NLP流水线可用于该类语言处理。
AI 中文摘要
低资源语言的词性标注因标注数据有限而颇具挑战，对于语言结构复杂的语言更是如此。盖尔语（苏格兰盖尔语）是一种形态丰富且濒临消亡的语言，数字资源有限，适合研究轻量型语言处理方法。本文介绍使用模块化spaCy自然语言处理框架，基于苏格兰盖尔语标注参考语料库构建盖尔语词性标注器。我们仅用最少的预处理和配置训练了两个模型：一个使用细粒度标签集，另一个使用简化的粗粒度标签集。两个模型均未使用外部词嵌入或预训练语言模型，仅基于现有语料库进行监督学习训练。细粒度模型的标注准确率达88.6%，粗粒度模型的准确率达93.7%。该结果与之前发布的两个盖尔语标注器的结果相当，表明简单的现成语言处理流水线在低资源且形态复杂的语言环境中也能展现出良好性能。
英文摘要
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.
CommentsA revised version of this paper has been accepted for presentation at UKCI 2026 (https://ukci2026.coventry.ac.uk/home/) and will be published by Springer
