IN22ConvBitextMining

IN22ConvBitextMining An MTEB dataset Massive Text Embedding Benchmark IN22-Conv is a n-way parallel conversation domain benchmark dataset for machine translation spanning English and 22 Indic languages. Task category t2t Domains Social, Spoken, Fiction, Spoken Reference Source datasets: mteb/IN22-Conv How to evaluate on this task You can evaluate an embedding model on this dataset using the following… See the full description on the dataset page:

Source: Hugging Face Hub (mteb/IN22ConvBitextMining). Metadata imported from the dataset’s Hub tags.