mGPT

Reported on 6 benchmarks across 5 tasks · 1 paper · 3 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing6 results

Part-Of-Speech TaggingonXGLUE
Avg. F1· 2022-04-15
0.56
SOTA
mGPT: Few-Shot Learners Go Multilingual arXiv:2204.07580
Natural Language InferenceonXWINO
Accuracy· 2022-04-15
0.562
SOTA
mGPT: Few-Shot Learners Go Multilingual arXiv:2204.07580
Named Entity Recognition (NER)onXGLUE
Avg F1· 2022-04-15
0.85
SOTA
mGPT: Few-Shot Learners Go Multilingual arXiv:2204.07580
Natural Language InferenceonXNLI
Accuracy· 2022-04-15
40.6
best: 83.7 (ByT5 XXL)
mGPT: Few-Shot Learners Go Multilingual arXiv:2204.07580
Cross-LingualonXCOPA
Accuracy· 2022-04-15
55.5
best: 94.4 (PaLM 2 (few-shot))
mGPT: Few-Shot Learners Go Multilingual arXiv:2204.07580
Cross-Lingual TransferonXCOPA
Accuracy· 2022-04-15
55.5
best: 94.4 (PaLM 2 (few-shot))
mGPT: Few-Shot Learners Go Multilingual arXiv:2204.07580