MLQA (MultiLingual Question Answering)

Introduced by Lewis et al. in MLQA: Evaluating Cross-lingual Extractive Question Answering

MLQA (MultiLingual Question Answering) is a benchmark dataset for evaluating cross-lingual question answering performance. MLQA consists of over 5K extractive QA instances (12K in English) in SQuAD format in seven languages - English, Arabic, German, Spanish, Hindi, Vietnamese and Simplified Chinese. MLQA is highly parallel, with QA instances parallel between 4 different languages on average.

Source: Facebook Research


Paper Code Results Date Stars


Similar Datasets