Slovak
A West Slavic language spoken by approximately five million people. In the field of NLP it is regarded as a medium-to-low-resource language and is frequently used as a case study in low-resource language research.
Timeline (last 90 days)
The study takes Slovak migratory media discourse as its theme and designs three tasks: topic relevance classification, geographic relevance classification, and extraction of migration origin/destination location terms.
Prompts written in Slovak (the native language) yield some performance improvement over prompts in other languages such as English, but the gain is moderate and highly task-dependent.
Slovak belongs to the West Slavic branch, has about 5 million speakers, and is regarded as a medium-to-low-resource language in NLP.
English typically accounts for 40%–70% of mainstream LLM training data, while Czech and Slovak may each account for less than 1%.
All Facts (4)
The study takes Slovak migratory media discourse as its theme and designs three tasks: topic relevance classification, geographic relevance classification, and extraction of migration origin/destination location terms.
50%UnverifiedPrompts written in Slovak (the native language) yield some performance improvement over prompts in other languages such as English, but the gain is moderate and highly task-dependent.
50%UnverifiedSlovak belongs to the West Slavic branch, has about 5 million speakers, and is regarded as a medium-to-low-resource language in NLP.
50%UnverifiedEnglish typically accounts for 40%–70% of mainstream LLM training data, while Czech and Slovak may each account for less than 1%.
50%