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 ResearchBenchmarks
| Trend | Task | Dataset Variant | Best Model | Paper | Code |
|---|---|---|---|---|---|
|
MLQA
|
ByT5 XXL
|
Papers
| Paper | Code | Results | Date | Stars |
|---|
