added dataset information to README.md
Browse files
README.md
CHANGED
@@ -37,6 +37,16 @@ print(classifier("uneasy mishmash of styles and genres ."))
|
|
37 |
print(classifier("by the end of no such thing the audience , like beatrice , has a watchful affection for the monster ."))
|
38 |
```
|
39 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
## Metric
|
41 |
|
42 |
Accuracy on the `'validation'` split of SST-2: 0.9278
|
|
|
37 |
print(classifier("by the end of no such thing the audience , like beatrice , has a watchful affection for the monster ."))
|
38 |
```
|
39 |
|
40 |
+
## Dataset
|
41 |
+
|
42 |
+
From the dataset page:
|
43 |
+
|
44 |
+
> "The Stanford Sentiment Treebank is a corpus with fully labeled parse trees that allows for a complete analysis of the compositional effects of sentiment in language.
|
45 |
+
> ...
|
46 |
+
> Binary classification experiments on full sentences (negative or somewhat negative vs somewhat positive or positive with neutral sentences discarded) refer to the dataset as SST-2 or SST binary."
|
47 |
+
|
48 |
+
Examples: https://huggingface.co/datasets/sst2/viewer
|
49 |
+
|
50 |
## Metric
|
51 |
|
52 |
Accuracy on the `'validation'` split of SST-2: 0.9278
|