Dialogue Relation Extraction on DialogRE v2 (test)
75.5F1 ScoreGRASP_large
Evaluation results
| Method | Links | ||
|---|---|---|---|
| GRASP_largeApproach=Prompt-based fine-tuning, Setting=Full-shot, Backbone=RoBERTa-large2022.08 | 75.5 | 67.8 | |
| TUCORE-GCNApproach=Fine-tuning based, Setting=Full-shot2022.08 | 73.1 | 65.9 | |
| RoBERTa_sApproach=Fine-tuning based, Setting=Full-shot2022.08 | 71.3 | 63.7 | |
| SocAoGvariant=full2021.06 | 69.1 | 66.5 | |
| GRASP_baseApproach=Prompt-based fine-tuning, Setting=Full-shot, Backbone=RoBERTa-base2022.08 | 69 | 61.7 | |
| SocAoG_reducedvariant=reduced2021.06 | 68.6 | 65.4 | |
| Dualencoding=separate semantic structure encoding2021.05 | 67.1 | 61.1 | |
| DualApproach=Fine-tuning based, Setting=Full-shot2022.08 | 67.1 | 61.1 | |
| Hierencoding=semantic information in AMR2021.05 | 66.7 | 61 | |
| SimpleRE2021.06 | 66.7 | 63.3 | |
| SimpleREaveraging=5-run averaged2020.12 | 66.7 | — | |
| BERTcdescription=baseline with argument representations2021.05 | 65.1 | 59.8 | |
| GDPNet2021.06 | 64.3 | 60.1 | |
| GDPNetaveraging=5-run averaged2020.12 | 64.3 | — | |
| BERTsaveraging=5-run averaged2020.12 | 61.8 | — | |
| BERTaveraging=5-run averaged2020.12 | 60.6 | — | |
| BERTsspeaker_information=special tokens2021.05 | 59.5 | 54.2 | |
| BERTS2021.06 | 59.5 | 54.2 | |
| BERTbaseline=Yu et al. (2020)2021.05 | 57.9 | 53.1 | |
| BERT2021.06 | 57.9 | 53.1 |