roberta-argument / README.md
chkla's picture
Update README.md
25022d1
|
raw
history blame
637 Bytes
Welcome to **RoBERTArg**!
πŸ€– **Training**: Model (RoBERTA_base_) fine-tuned on a heterogeneous argument corpus (~40K sentences, Stab et al. (2018) πŸ“š) corpus of several controversial topics (abortion etc.).
🏷 Using **NON-ARGUMENT** (0) and **ARGUMENT** (1) as labels.
**Performance**
| Model | Acc | F1 | R arg | R non | P arg | P non |
|----|----|----|----|----|----|----|
| robertArg | 0.80577 | 0.78407 | 0.8147 | 0.7989 | 0.7557 | 0.8496 |
**Confusion Matrix**
| | 1 | 0 |
|----|----|----|
| 1 | 2214 | 557 |
| 0 | 392 | 1723 |
πŸ‘‰πŸΎ Check out _chkla/argument-analyzer/_ for more details.
Enjoy and stay tuned! πŸš€