XQuAD

XQuAD is a cross-lingual extractive QA benchmark of 1,190 SQuAD v1.1 question-answer pairs professionally translated into 11 languages.

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categoryknowledge
Subcategorycross-lingual extractive question answering
Page statusactive
MetricF1 / exact match
Directionhigher_is_better
Unitpercent
Dataset size1190
Dataset licenceCC BY-SA 4.0
PublisherGoogle DeepMind

What it measures

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.

Task format

Extractive question answering; given a paragraph and question, output the exact answer span from the paragraph.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub