mteb/

JaQuADRetrieval

JaQuADRetrieval An MTEB dataset Massive Text Embedding Benchmark

Human-annotated question-answer pairs for Japanese wikipedia pages.

Task category t2t

Domains Encyclopaedic, Non-fiction, Written

Reference https://arxiv.org/abs/2202.01764

You can evaluate an embedding model on this dataset using the following code: import mteb

task = mteb.get_tasks(["JaQuADRetrieval"]) evaluator = mteb.MTEB(task)

model =… See the full description on the dataset page: https://huggingface.co/datasets/mteb/JaQuADRetrieval.