arXiv：cs.CL· Usman Nawaz, Muhammad Junaid Iqbal, Muhammad Asaf, Mariam Munsif Mir, Faisal Rehman, Tahir Alyas, Muhammad Hasnain·· 10 小时前
面向低资源 Saraiki 的神经 POS 标注
Neural POS Tagging for the Low-Resource Saraiki
AI 导读
研究者构建了首个手工标注的 Saraiki 通用 POS 数据集，包含 17 个词性类别，用于这一约 2889 万人使用、资源匮乏的印欧语系语言。
正文
Abstract:Part-of-speech tagging is a fundamental sequence labeling task and an important component for many downstream natural language processing applications. However, Saraiki, written from right to left in a Perso-Arabic script, remains an under-resourced Indo-Aryan language, despite being spoken as a mother tongue by 28,849,579 people (approximately 28.9 million) according to Pakistan 7th Population and Housing Census 2023. This paper presents a manually annotated Saraiki Universal POS tagging dataset developed from plain-text. We annotated the text with 17 POS categories. We evaluate three pretrained transformer encoders under the same fine-tuning setup: XLM-RoBERTa base, Urdu RoBERTa small, and multilingual DistilBERT. Experimental results over five random seeds show that XLM-RoBERTa base achieves the best performance, with 87.29% +/- 0.21% development accuracy and 88.60% +/- 0.21% test accuracy. Urdu RoBERTa small and multilingual DistilBERT also provide competitive results, suggesting that multilingual and related-script pretrained encoders are effective for Saraiki UPOS tagging. The dataset, evaluation setup, and baseline results introduced in this work provide a benchmark for future research on Saraiki NLP and low-resource sequence labeling.
| Comments: | Accepted for publication in ICALP 2026 |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.20279 [cs.CL] |
| (or arXiv:2610.20279v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20279 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Usman Nawaz [view email]
[v1]
Wed, 14 Oct 2026 14:38:17 UTC (16 KB)
来源：arXiv：cs.CL · arxiv.org