Spaces:
Running
Running
Update Space (evaluate main: 05209ece)
Browse files
README.md
CHANGED
@@ -10,6 +10,12 @@ pinned: false
|
|
10 |
tags:
|
11 |
- evaluate
|
12 |
- metric
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
---
|
14 |
|
15 |
# Metric Card for BLEURT
|
|
|
10 |
tags:
|
11 |
- evaluate
|
12 |
- metric
|
13 |
+
description: >-
|
14 |
+
BLEURT a learnt evaluation metric for Natural Language Generation. It is built using multiple phases of transfer learning starting from a pretrained BERT model (Devlin et al. 2018)
|
15 |
+
and then employing another pre-training phrase using synthetic data. Finally it is trained on WMT human annotations. You may run BLEURT out-of-the-box or fine-tune
|
16 |
+
it for your specific application (the latter is expected to perform better).
|
17 |
+
|
18 |
+
See the project's README at https://github.com/google-research/bleurt#readme for more information.
|
19 |
---
|
20 |
|
21 |
# Metric Card for BLEURT
|