Commit
•
1def43b
1
Parent(s):
be7df1f
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
language: de
|
| 3 |
datasets:
|
| 4 |
-
- germanquad
|
| 5 |
license: mit
|
| 6 |
thumbnail: https://thumb.tildacdn.com/tild3433-3637-4830-a533-353833613061/-/resize/720x/-/format/webp/germanquad.jpg
|
| 7 |
tags:
|
|
@@ -38,7 +38,7 @@ embeds_dropout_prob = 0.1
|
|
| 38 |
We evaluated the extractive question answering performance on our GermanQuAD test set.
|
| 39 |
Model types and training data are included in the model name.
|
| 40 |
For finetuning XLM-Roberta, we use the English SQuAD v2.0 dataset.
|
| 41 |
-
The GELECTRA models are warm started on the German translation of SQuAD v1.1 and finetuned on
|
| 42 |
The human baseline was computed for the 3-way test set by taking one answer as prediction and the other two as ground truth.
|
| 43 |
|
| 44 |
|
|
|
|
| 1 |
---
|
| 2 |
language: de
|
| 3 |
datasets:
|
| 4 |
+
- deepset/germanquad
|
| 5 |
license: mit
|
| 6 |
thumbnail: https://thumb.tildacdn.com/tild3433-3637-4830-a533-353833613061/-/resize/720x/-/format/webp/germanquad.jpg
|
| 7 |
tags:
|
|
|
|
| 38 |
We evaluated the extractive question answering performance on our GermanQuAD test set.
|
| 39 |
Model types and training data are included in the model name.
|
| 40 |
For finetuning XLM-Roberta, we use the English SQuAD v2.0 dataset.
|
| 41 |
+
The GELECTRA models are warm started on the German translation of SQuAD v1.1 and finetuned on \\\\\\\\germanquad.
|
| 42 |
The human baseline was computed for the 3-way test set by taking one answer as prediction and the other two as ground truth.
|
| 43 |
|
| 44 |
|