Named Entity Recognition on CoNLL04 (test)
90.2F1 ScoreTablERT
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| TablERT2020.10 | 90.2 | 89.7 | 90.6 | |
| Table-Sequence EncodersAveraging=micro-averaged2020.10 | 90.1 | — | — | |
| Eberts and UlgesAveraging=micro-averaged2020.10 | 88.9 | — | — | |
| SpERT (Eberts and Ulges, 2020)2020.10 | 88.9 | 88.3 | 89.6 | |
| Li et al.2020.10 | 87.8 | — | — | |
| Multi-turn QA (Li et al., 2019)2020.10 | 87.8 | 89 | 86.6 | |
| Table-Sequence EncodersAveraging=macro-averaged2020.10 | 86.9 | — | — | |
| Eberts and UlgesAveraging=macro-averaged2020.10 | 86.3 | — | — | |
| Nguyen and VerspoorAveraging=macro-averaged2020.10 | 86.2 | — | — | |
| Zhang et al.Averaging=micro-averaged2020.10 | 85.6 | — | — | |
| Zhang et al. (2017)2020.10 | 85.6 | — | — | |
| Tran and KavuluruAveraging=macro-averaged2020.10 | 84.2 | — | — | |
| Bekoulis et al.Averaging=macro-averaged2020.10 | 83.9 | — | — | |
| Bekoulis et al.Averaging=macro-averaged2020.10 | 83.6 | — | — | |
| Miwa and SasakiAveraging=micro-averaged2020.10 | 80.7 | — | — | |
| Miwa and Sasaki (2014)2020.10 | 80.7 | 81.2 | 80.2 |