NollySentiBitextMining
An MTEB dataset
Massive Text Embedding Benchmark
NollySenti is Nollywood movie reviews for five languages widely spoken in Nigeria (English, Hausa, Igbo, Nigerian-Pidgin, and Yoruba.
Task category
t2t
Domains
Social, Reviews, Written
Reference
NollySenti: Leveraging Tran…
You can evaluate an embedding model on this dataset using the following code:
import mteb