Merge branch 'main' of https://huggingface.co/Unbabel/wmt22-comet-da into main
Browse files
README.md
CHANGED
|
@@ -104,7 +104,11 @@ This is a [COMET](https://github.com/Unbabel/COMET) evaluation model: It receive
|
|
| 104 |
|
| 105 |
[COMET-22: Unbabel-IST 2022 Submission for the Metrics Shared Task](https://aclanthology.org/2022.wmt-1.52) (Rei et al., WMT 2022)
|
| 106 |
|
| 107 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 108 |
|
| 109 |
Using this model requires unbabel-comet to be installed:
|
| 110 |
|
|
@@ -136,13 +140,13 @@ model_output = model.predict(data, batch_size=8, gpus=1)
|
|
| 136 |
print (model_output)
|
| 137 |
```
|
| 138 |
|
| 139 |
-
|
| 140 |
|
| 141 |
Our model is intented to be used for **MT evaluation**.
|
| 142 |
|
| 143 |
Given a a triplet with (source sentence, translation, reference translation) outputs a single score between 0 and 1 where 1 represents a perfect translation.
|
| 144 |
|
| 145 |
-
|
| 146 |
|
| 147 |
This model builds on top of XLM-R which cover the following languages:
|
| 148 |
|
|
|
|
| 104 |
|
| 105 |
[COMET-22: Unbabel-IST 2022 Submission for the Metrics Shared Task](https://aclanthology.org/2022.wmt-1.52) (Rei et al., WMT 2022)
|
| 106 |
|
| 107 |
+
# License
|
| 108 |
+
|
| 109 |
+
Apache-2.0
|
| 110 |
+
|
| 111 |
+
# Usage (unbabel-comet)
|
| 112 |
|
| 113 |
Using this model requires unbabel-comet to be installed:
|
| 114 |
|
|
|
|
| 140 |
print (model_output)
|
| 141 |
```
|
| 142 |
|
| 143 |
+
# Intended uses
|
| 144 |
|
| 145 |
Our model is intented to be used for **MT evaluation**.
|
| 146 |
|
| 147 |
Given a a triplet with (source sentence, translation, reference translation) outputs a single score between 0 and 1 where 1 represents a perfect translation.
|
| 148 |
|
| 149 |
+
# Languages Covered:
|
| 150 |
|
| 151 |
This model builds on top of XLM-R which cover the following languages:
|
| 152 |
|