XQuAD is a cross-lingual extractive QA benchmark of 1,190 SQuAD v1.1 question-answer pairs professionally translated into 11 languages.
unassessed
| Category | knowledge |
|---|---|
| Subcategory | cross-lingual extractive question answering |
| Page status | active |
| Metric | F1 / exact match |
| Direction | higher_is_better |
| Unit | percent |
| Dataset size | 1190 |
| Dataset licence | CC BY-SA 4.0 |
| Publisher | Google DeepMind |
XQuAD tests whether a model's reading-comprehension ability transfers from English to other languages. Given a short paragraph and a question in one of 11 languages, the model must extract the exact answer span from the paragraph, the same format as SQuAD but run in parallel across languages.
Extractive question answering; given a paragraph and question, output the exact answer span from the paragraph.
No model card in ModelSpec reports this benchmark yet.