Discourse Parsing on Instructional-DT (Instr-DT)
Metric: Standard Parseval (Relation) (higher is better)
Metric: Standard Parseval (Relation) (higher is better)
| # | Model↕ | Standard Parseval (Relation)▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | Bottom-up (DeBERTa) | 51.4 | No | A Simple and Strong Baseline for End-to-End Neur... | 2022-10-15 | Code |
| 2 | Top-down (DeBERTa) | 50 | No | A Simple and Strong Baseline for End-to-End Neur... | 2022-10-15 | Code |
| 3 | Top-down (RoBERTa) | 48.7 | No | A Simple and Strong Baseline for End-to-End Neur... | 2022-10-15 | Code |
| 4 | Bottom-up (RoBERTa) | 47.9 | No | A Simple and Strong Baseline for End-to-End Neur... | 2022-10-15 | Code |
| 5 | Bottom-up (XLNet) | 47.4 | No | A Simple and Strong Baseline for End-to-End Neur... | 2022-10-15 | Code |
| 6 | Top-down (XLNet) | 47 | No | A Simple and Strong Baseline for End-to-End Neur... | 2022-10-15 | Code |
| 7 | Bottom-up (SpanBERT) | 46 | No | A Simple and Strong Baseline for End-to-End Neur... | 2022-10-15 | Code |
| 8 | Top-down (SpanBERT) | 42.7 | No | A Simple and Strong Baseline for End-to-End Neur... | 2022-10-15 | Code |
| 9 | Bottom-up (BERT) | 39.5 | No | A Simple and Strong Baseline for End-to-End Neur... | 2022-10-15 | Code |
| 10 | Top-down (BERT) | 37.6 | No | A Simple and Strong Baseline for End-to-End Neur... | 2022-10-15 | Code |