XGLUE benchmark dataset

XGLUE is a new benchmark dataset to evaluate the performance of cross-lingual pre-trained models with respect to cross-lingual natural language understanding and generation. XGLUE is composed of 11 tasks spans 19 languages. For each task, the training data is only available in English. This me...

Resource Type:Corpus
Media Type:Text
Languages:Arabic
Bulgarian
Chinese
Dutch; Flemish
English
French
German
Greek, Modern (1453-)
Hindi
Italian
Polish
Portuguese
Russian
Spanish; Castilian
Swahili
Thai
Turkish
Urdu
Vietnamese

Order by:

Filter by:

English (41)
French (30)
German (27)
Italian (20)
Czech (18)
Bulgarian (17)
Polish (13)
Romanian (12)
Finnish (11)
Swedish (11)
Basque (10)
Latvian (9)
Slovak (7)
Danish (6)
Irish (6)
Maltese (6)
Arabic (2)
Chinese (2)
Latin (2)
Hindi (1)
Russian (1)
Swahili (1)
Thai (1)
Turkish (1)
Urdu (1)