Coreference Resolution on CoNLL12
| Rank | Model | Average F1 | B3 | CEAFϕ4 | MUC | Paper | Code | Year |
|---|---|---|---|---|---|---|---|---|
| 1 | DeepStruct multi-task w/ finetune | 73.1 | 71.3 | 73.1 | 74.9 | DeepStruct: Pretraining of Language Models for Structure Prediction | cgraywang/deepstruct | 2022 |
| 2 | DeepStruct multi-task | 60.6 | 57.7 | 60.2 | 63.9 | DeepStruct: Pretraining of Language Models for Structure Prediction | cgraywang/deepstruct | 2022 |