Semantic Parsing on SMCalFlow-CS v1 & v2 (i.i.d.)
83.3Accuracy (v2)T5 Large (fine tuned w/o prompts)
Evaluation results
| Method | Links | ||
|---|---|---|---|
| T5 Large (fine tuned w/o prompts)2022.12 | 83.3 | 85.3 | |
| T5 11B (Prompt Tuning)Source=Qiu et al. 2022b2022.12 | 83.1 | — | |
| T5 Base (FT)Source=Qiu et al. 2022b2022.12 | 82.8 | — | |
| PaLM 62B (FT)Source=Qiu et al. 2022b2022.12 | 82.2 | — | |
| Cover-LS (NoFT)2022.12 | 73.6 | 82.2 | |
| Top-K (NoFT)2022.12 | 69.7 | 79.3 | |
| PaLM 540B (ICL)Source=Qiu et al. 2022b2022.12 | 58.3 | — | |
| T5 Base (FT)Source=Qiu et al. 2022a2022.12 | — | 84.7 | |
| T5 Base + CSL-Aug (FT)Source=Qiu et al. 2022a2022.12 | — | 83.5 |