julien-c HF staff commited on
Commit
02d56d6
1 Parent(s): c4d4540

Add description to card metadata (#1)

Browse files

- Add description to card metadata (0565ca7ccc67588af6cbecb0c127b26f0a31650a)

Files changed (1) hide show
  1. README.md +35 -4
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  title: METEOR
3
- emoji: 🤗
4
  colorFrom: blue
5
  colorTo: red
6
  sdk: gradio
@@ -8,10 +8,41 @@ 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 METEOR
16
 
17
  ## Metric description
 
1
  ---
2
  title: METEOR
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
+ METEOR, an automatic metric for machine translation evaluation
15
+
16
+ that is based on a generalized concept of unigram matching between the
17
+
18
+ machine-produced translation and human-produced reference translations.
19
+
20
+ Unigrams can be matched based on their surface forms, stemmed forms,
21
+
22
+ and meanings; furthermore, METEOR can be easily extended to include more
23
+
24
+ advanced matching strategies. Once all generalized unigram matches
25
+
26
+ between the two strings have been found, METEOR computes a score for
27
+
28
+ this matching using a combination of unigram-precision, unigram-recall, and
29
 
30
+ a measure of fragmentation that is designed to directly capture how
31
+
32
+ well-ordered the matched words in the machine translation are in relation
33
+
34
+ to the reference.
35
+
36
+
37
+ METEOR gets an R correlation value of 0.347 with human evaluation on the
38
+ Arabic
39
+
40
+ data and 0.331 on the Chinese data. This is shown to be an improvement on
41
+
42
+ using simply unigram-precision, unigram-recall and their harmonic F1
43
+
44
+ combination.
45
+ ---
46
  # Metric Card for METEOR
47
 
48
  ## Metric description