When the Dictionary Strikes Back: A Case Study on Slovak Migration Location Term Extraction and NER via Rule-Based vs. LLM Methods

This study explores the task of automatically extracting migration-related locations (source and destination) from media articles, focusing on the challenges posed by Slovak, a low-resource and morphologically complex language. We present the first comparative analysis of rule-based dictionary approaches (NLP4SK) versus Large Language Models (LLMs, e.g. SlovakBERT, GPT-4o) for both geographical relevance classification (Slovakia-focused migration) and specific source/target location extraction. To facilitate this research and future work, we introduce the first manually annotated Slovak dataset tailored for migration-focused locality detection. Our results show that while a fine-tuned SlovakBERT model achieves high accuracy for classification, specialized rule-based methods still have the potential to outperform LLMs for specific extraction tasks, though improved LLM performance with few-shot examples suggests future competitiveness as research in this area continues to evolve.

Cite: Miroslav Blšták, Jaroslav Kopčan, Marek Suppa, Samuel Havran, Andrej Findor, Martin Takac, and Marian Simko. 2025. When the Dictionary Strikes Back: A Case Study on Slovak Migration Location Term Extraction and NER via Rule-Based vs. LLM Methods. In Proceedings of the 10th Workshop on Slavic Natural Language Processing (Slavic NLP 2025), pages 91–100, Vienna, Austria. Association for Computational Linguistics. DOI: https://doi.org/10.18653/v1/2025.bsnlp-1.11