Update README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,8 @@ An NLI model to detect stance (Positive, Neutral, Negative) towards a given grou
|
|
| 2 |
Model is tuned on a corpus of political manifestos from the UK, Ireland, Germany and Austria. The specific hypotheses tested by the model is if
|
| 3 |
the mention of a given group is positive, negative or neutral, where the model is flexible and can take any named group.
|
| 4 |
|
|
|
|
|
|
|
| 5 |
Accuracy: 86%
|
| 6 |
F1 Macro: 0.78
|
| 7 |
Balanced Accuracy: 76%
|
|
|
|
| 2 |
Model is tuned on a corpus of political manifestos from the UK, Ireland, Germany and Austria. The specific hypotheses tested by the model is if
|
| 3 |
the mention of a given group is positive, negative or neutral, where the model is flexible and can take any named group.
|
| 4 |
|
| 5 |
+
Finetuned by Will Horne, Alona Dolinsky and Lena Huber.
|
| 6 |
+
|
| 7 |
Accuracy: 86%
|
| 8 |
F1 Macro: 0.78
|
| 9 |
Balanced Accuracy: 76%
|