IndicQE-APE

IndicQE-APE A unified, test-first, difficulty-stratified Quality Estimation (QE) and Automatic Post-Editing (APE) benchmark for Indic and low-resource language pairs. One umbrella repo, sliceable by language pair, by task, everything at once, or just the diagnostic challenge suite. from datasets import load dataset load dataset(“surrey-nlp/IndicQE-APE”) “all” — curated En→Indic (default) load dataset(“surrey-nlp/IndicQE-APE”, “en-ml”) one pair… See the full description on the dataset page:

Source: Hugging Face Hub (surrey-nlp/IndicQE-APE). Metadata imported from the dataset’s Hub tags.