Neural pos tagging improves saraiki language processing accuracy
Neural POS Tagging for the Low-Resource Saraiki
Computation and Language
Summary
Saraiki is a language spoken by nearly 29 million people but lacks enough data for computers to understand it well. The authors created a new dataset where they labeled words with their parts of speech, like nouns or verbs, to help computers learn Saraiki better. They tested three advanced language models to see which tagged words the best and found the XLM-RoBERTa model worked most accurately. This work provides a useful starting point for others wanting to build language tools for Saraiki.
What this means in practice
- •For language technology developers: Build more accurate Saraiki language models by fine-tuning transformer-based POS taggers using the new annotated dataset.
- •For multilingual nlp engineers: Integrate related-script pretrained models to improve processing of Saraiki and similar languages with limited resources.
Authors
Usman Nawaz, Muhammad Junaid Iqbal, Muhammad Asaf, Mariam Munsif Mir, Faisal Rehman, Tahir Alyas, Muhammad Hasnain
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.