Spaces:
Running
Running
Update Space (evaluate main: 05209ece)
Browse files
README.md
CHANGED
@@ -10,6 +10,17 @@ pinned: false
|
|
10 |
tags:
|
11 |
- evaluate
|
12 |
- metric
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
---
|
14 |
|
15 |
# Metric Card for TER
|
|
|
10 |
tags:
|
11 |
- evaluate
|
12 |
- metric
|
13 |
+
description: >-
|
14 |
+
TER (Translation Edit Rate, also called Translation Error Rate) is a metric to quantify the edit operations that a
|
15 |
+
hypothesis requires to match a reference translation. We use the implementation that is already present in sacrebleu
|
16 |
+
(https://github.com/mjpost/sacreBLEU#ter), which in turn is inspired by the TERCOM implementation, which can be found
|
17 |
+
here: https://github.com/jhclark/tercom.
|
18 |
+
|
19 |
+
The implementation here is slightly different from sacrebleu in terms of the required input format. The length of
|
20 |
+
the references and hypotheses lists need to be the same, so you may need to transpose your references compared to
|
21 |
+
sacrebleu's required input format. See https://github.com/huggingface/datasets/issues/3154#issuecomment-950746534
|
22 |
+
|
23 |
+
See the README.md file at https://github.com/mjpost/sacreBLEU#ter for more information.
|
24 |
---
|
25 |
|
26 |
# Metric Card for TER
|