Spaces:
Running
Running
Add description to card metadata (#1)
Browse files- Add description to card metadata (20ad646d6acf36bd25f5fd77615b543b7cdc860b)
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
title: chrF
|
3 |
-
emoji: 🤗
|
4 |
colorFrom: blue
|
5 |
colorTo: red
|
6 |
sdk: gradio
|
@@ -8,10 +8,31 @@ sdk_version: 3.0.2
|
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
tags:
|
11 |
-
- evaluate
|
12 |
-
- metric
|
13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
# Metric Card for chrF(++)
|
16 |
|
17 |
|
|
|
1 |
---
|
2 |
title: chrF
|
3 |
+
emoji: 🤗
|
4 |
colorFrom: blue
|
5 |
colorTo: red
|
6 |
sdk: gradio
|
|
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
tags:
|
11 |
+
- evaluate
|
12 |
+
- metric
|
13 |
+
description: >-
|
14 |
+
ChrF and ChrF++ are two MT evaluation metrics. They both use the F-score
|
15 |
+
statistic for character n-gram matches,
|
16 |
+
|
17 |
+
and ChrF++ adds word n-grams as well which correlates more strongly with
|
18 |
+
direct assessment. We use the implementation
|
19 |
+
|
20 |
+
that is already present in sacrebleu.
|
21 |
+
|
22 |
+
|
23 |
+
The implementation here is slightly different from sacrebleu in terms of the
|
24 |
+
required input format. The length of
|
25 |
|
26 |
+
the references and hypotheses lists need to be the same, so you may need to
|
27 |
+
transpose your references compared to
|
28 |
+
|
29 |
+
sacrebleu's required input format. See
|
30 |
+
https://github.com/huggingface/datasets/issues/3154#issuecomment-950746534
|
31 |
+
|
32 |
+
|
33 |
+
See the README.md file at https://github.com/mjpost/sacreBLEU#chrf--chrf for
|
34 |
+
more information.
|
35 |
+
---
|
36 |
# Metric Card for chrF(++)
|
37 |
|
38 |
|