Discourse Parsing
Papers
Showing 1–10 of 189 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | Bottom-up (DeBERTa) | Standard Parseval (Nuclearity) | 60 | — | Unverified |
| 2 | Top-down (DeBERTa) | Standard Parseval (Nuclearity) | 57.9 | — | Unverified |
| 3 | Bottom-up (XLNet) | Standard Parseval (Nuclearity) | 56.4 | — | Unverified |
| 4 | Top-down (RoBERTa) | Standard Parseval (Nuclearity) | 56.1 | — | Unverified |
| 5 | Bottom-up (RoBERTa) | Standard Parseval (Nuclearity) | 55.5 | — | Unverified |
| 6 | Top-down (XLNet) | Standard Parseval (Nuclearity) | 55.2 | — | Unverified |
| 7 | Top-down (SpanBERT) | Standard Parseval (Nuclearity) | 54.5 | — | Unverified |
| 8 | Bottom-up (SpanBERT) | Standard Parseval (Nuclearity) | 53.8 | — | Unverified |
| 9 | Guz et al. (2020) (pretrained) | Standard Parseval (Nuclearity) | 46.59 | — | Unverified |
| 10 | Bottom-up (BERT) | Standard Parseval (Nuclearity) | 46.3 | — | Unverified |