Fact Extraction and Verification on FEVER leaderboard March 2019 (test)
77.7Evidence F1QFE
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| QFEsubmission_period=After Shared Task, ensemble=11 models2019.05 | 77.7 | 69.3 | 61.8 | |
| hz66pasasubmission_period=After Shared Task, rank_criteria=top-three F12019.05 | 71.4 | 33.3 | 22 | |
| aschernsubmission_period=After Shared Task, rank_criteria=top-three F12019.05 | 70.4 | 69.3 | 60.9 | |
| avonamilasubmission_period=After Shared Task, rank_criteria=top-three FEVER scores2019.05 | 60.3 | 71.4 | 65.3 | |
| Nie et al.submission_period=Shared Task2019.05 | 53 | 68.2 | 64.2 | |
| whosubmission_period=After Shared Task, rank_criteria=top-three FEVER scores2019.05 | 37.4 | 72.1 | 66.6 | |
| Kudosubmission_period=After Shared Task, rank_criteria=top-three FEVER scores2019.05 | 36.8 | 70.6 | 65.7 | |
| Yoneda et al.submission_period=Shared Task2019.05 | 35 | 67.6 | 62.5 |