Papers by Lasitha Randunu Chandrakantha Uyangodage

Copied to clipboard

Challenge:	introducing large language models (LLMs) has advanced natural language processing (NLP), but their effectiveness is largely dependent on pre-training resources.
Approach:	They propose a large news corpus for Sinhala with a set of NLP tasks for the language . NSina is the largest news corpuse for Sinha, available up to date .
Outcome:	The proposed model outperforms existing models in many benchmarks and outperformed previous models in high-resource languages.