Data-to-text generation on RotoWire (test)
7.57Factual Support Score
Templ
Updated 4d ago
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
2021.02 | 7.57 | 0.08 | -61.67 | -52.92 | -36.67 | |
2022.02 | 7.57 | 0.08 | -57.33 | -55.33 | -34.67 | |
2018.09 | 6.98 | 0.21 | -0.89 | -4.89 | 1.33 | |
2019.06 | 6.98 | 0.21 | -3.7 | -3.33 | 17.78 | |
2021.02 | 5.08 | 0.67 | 13.33 | 4.58 | 3.75 | |
2022.02 | 5.08 | 0.67 | 6 | 1.33 | -0.67 | |
2018.09 | 4.9 | 0.9 | -2.44 | -2.44 | -3.55 | |
2019.06 | 4.9 | 0.9 | -3.33 | -3.7 | -3.7 | |
2022.02 | 4.84 | 0.17 | 4 | 20.67 | 10.67 | |
2019.06 | 4.77 | 0.8 | 2.96 | 3.7 | -3.33 | |
2021.02 | 4 | 0.27 | 5 | 10.42 | 6.67 | |
2022.02 | 4 | 0.27 | 0.67 | 7.33 | 10 | |
2021.02 | 3.92 | 0.91 | 5 | -8.33 | -4.58 | |
2022.02 | 3.92 | 0.91 | 4 | -14.67 | -13.33 | |
2021.02 | 3.63 | 0.07 | 38.33 | 46.25 | 30.83 | |
2022.02 | 3.63 | 0.07 | 42.67 | 40.67 | 28 | |
2018.09 | 3.19 | 1.09 | -4.22 | -4.89 | -6.44 | |
2018.09 | 2.98 | 0.28 | 11.78 | 16 | 13.78 | |
2019.06 | 2.98 | 0.28 | 4.07 | 3.33 | -10.74 |