Update README.md
Browse files
README.md
CHANGED
@@ -129,12 +129,6 @@ The fine-tuning script can be accessed [here](https://github.com/jgrosjean-mathe
|
|
129 |
|
130 |
<!-- This section describes the evaluation protocols and provides the results. -->
|
131 |
|
132 |
-
#### Baseline
|
133 |
-
|
134 |
-
The first baseline is [distiluse-base-multilingual-cased](https://www.sbert.net/examples/training/multilingual/README.html), a high-performing Sentence Transformer model that is able to process German, French and Italian (and more).
|
135 |
-
|
136 |
-
The second baseline uses mean pooling embeddings from the last hidden state of the original swissbert model.
|
137 |
-
|
138 |
#### Testing Data
|
139 |
|
140 |
<!-- This should link to a Dataset Card if possible. -->
|
@@ -170,4 +164,10 @@ Making use of an unsupervised training approach, Swissbert for Sentence Embeddin
|
|
170 |
| Semantic Similarity IT | 83.00 | - ` | 84.00 | - |**89.80** | - |
|
171 |
| Text Classification DE | 95.76 |**91.99**| 94.70 | 89.43 | 95.61 | 91.20 |
|
172 |
| Text Classification FR | 94.55 | 88.52 | 95.30 |**89.91**| 94.55 | 89.82 |
|
173 |
-
| Text Classification IT | 93.48 | 88.29 | 94.85 | 90.36 | 95.91 |**92.05**|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
129 |
|
130 |
<!-- This section describes the evaluation protocols and provides the results. -->
|
131 |
|
|
|
|
|
|
|
|
|
|
|
|
|
132 |
#### Testing Data
|
133 |
|
134 |
<!-- This should link to a Dataset Card if possible. -->
|
|
|
164 |
| Semantic Similarity IT | 83.00 | - ` | 84.00 | - |**89.80** | - |
|
165 |
| Text Classification DE | 95.76 |**91.99**| 94.70 | 89.43 | 95.61 | 91.20 |
|
166 |
| Text Classification FR | 94.55 | 88.52 | 95.30 |**89.91**| 94.55 | 89.82 |
|
167 |
+
| Text Classification IT | 93.48 | 88.29 | 94.85 | 90.36 | 95.91 |**92.05**|
|
168 |
+
|
169 |
+
#### Baselines
|
170 |
+
|
171 |
+
The first baseline uses mean pooling embeddings from the last hidden state of the original swissbert model.
|
172 |
+
|
173 |
+
The second baseline is [distiluse-base-multilingual-cased](https://www.sbert.net/examples/training/multilingual/README.html), a high-performing Sentence Transformer model that is able to process German, French and Italian (and more).
|