Highlighting Tswana language news articles sourced from the Daily News Dikgang, specifically formatted for the Massive Text Embedding Benchmark (MTEB). It provides labeled examples within the written news domain to support text-to-classification (t2c) tasks for low-resource language evaluation.
Use Cases
- Evaluate the quality of text embeddings for Tswana using the mteb.get_task('TswanaNewsClassification') method
- Fine-tune classification models to categorize news articles based on the underlying label structure
- Compare the performance of multilingual versus language-specific embedding models on Tswana news text
Strengths
- Sourced from the dsfsi/daily-news-dikgang repository
- Classified under the t2c (text-to-classification) task category in MTEB
- Focuses on written news content in the Tswana language
- Referenced in Springer research regarding African language processing (ISBN 978-3-031-49002-6_17)