Intent Classification on MASSIVE
Intent Accuracy
- 2022-04-18 — mT5 Base (encoder-only): Intent Accuracy 86.1
| Rank | Model | Intent Accuracy | Paper | Code | Year |
|---|---|---|---|---|---|
| 1 | mT5 Base (encoder-only) | 86.1 | MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages | alexa/massive · pswietojanski/slurp · ai4bharat/indicbert · +3 | 2022 |
| 2 | mT5 Base (text-to-text) | 85.3 | MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages | alexa/massive · pswietojanski/slurp · ai4bharat/indicbert · +3 | 2022 |
| 3 | XLM-R Base | 85.1 | MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages | alexa/massive · pswietojanski/slurp · ai4bharat/indicbert · +3 | 2022 |