Spaces:
Running
Running
Commit
·
41f36bc
1
Parent(s):
4e587fd
Upload folder using huggingface_hub
Browse files- data/datasets/lilac/opus100-en-us-validation/config.yml +26 -0
- data/datasets/lilac/opus100-en-us-validation/data-00000-of-00001.parquet +0 -0
- data/datasets/lilac/opus100-en-us-validation/manifest.json +22 -0
- data/datasets/lilac/opus100-en-us-validation/translation/en/lang_detection/data-00000-of-00001.parquet +0 -0
- data/datasets/lilac/opus100-en-us-validation/translation/en/lang_detection/signal_manifest.json +33 -0
- data/datasets/lilac/opus100-en-us-validation/translation/en/near_dup/data-00000-of-00001.parquet +0 -0
- data/datasets/lilac/opus100-en-us-validation/translation/en/near_dup/signal_manifest.json +38 -0
- data/datasets/lilac/opus100-en-us-validation/translation/en/pii/data-00000-of-00001.parquet +0 -0
- data/datasets/lilac/opus100-en-us-validation/translation/en/pii/signal_manifest.json +47 -0
- data/datasets/lilac/opus100-en-us-validation/translation/en/text_statistics/data-00000-of-00001.parquet +0 -0
- data/datasets/lilac/opus100-en-us-validation/translation/en/text_statistics/signal_manifest.json +61 -0
- data/datasets/lilac/opus100-en-us-validation/translation/es/lang_detection/data-00000-of-00001.parquet +0 -0
- data/datasets/lilac/opus100-en-us-validation/translation/es/lang_detection/signal_manifest.json +33 -0
- data/datasets/lilac/opus100-en-us-validation/translation/es/near_dup/data-00000-of-00001.parquet +0 -0
- data/datasets/lilac/opus100-en-us-validation/translation/es/near_dup/signal_manifest.json +38 -0
- data/datasets/lilac/opus100-en-us-validation/translation/es/pii/data-00000-of-00001.parquet +0 -0
- data/datasets/lilac/opus100-en-us-validation/translation/es/pii/signal_manifest.json +47 -0
- data/datasets/lilac/opus100-en-us-validation/translation/es/text_statistics/data-00000-of-00001.parquet +0 -0
- data/datasets/lilac/opus100-en-us-validation/translation/es/text_statistics/signal_manifest.json +61 -0
data/datasets/lilac/opus100-en-us-validation/config.yml
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
name: opus100-en-us-validation
|
2 |
+
namespace: lilac
|
3 |
+
settings:
|
4 |
+
ui:
|
5 |
+
media_paths:
|
6 |
+
- [translation, es]
|
7 |
+
- [translation, en]
|
8 |
+
signals:
|
9 |
+
- path: [translation, es]
|
10 |
+
signal: {signal_name: near_dup}
|
11 |
+
- path: [translation, es]
|
12 |
+
signal: {signal_name: pii}
|
13 |
+
- path: [translation, es]
|
14 |
+
signal: {signal_name: lang_detection}
|
15 |
+
- path: [translation, es]
|
16 |
+
signal: {signal_name: text_statistics}
|
17 |
+
- path: [translation, en]
|
18 |
+
signal: {signal_name: near_dup}
|
19 |
+
- path: [translation, en]
|
20 |
+
signal: {signal_name: text_statistics}
|
21 |
+
- path: [translation, en]
|
22 |
+
signal: {signal_name: pii}
|
23 |
+
- path: [translation, en]
|
24 |
+
signal: {signal_name: lang_detection}
|
25 |
+
source: {config_name: en-es, dataset_name: opus100, source_name: huggingface, split: validation}
|
26 |
+
tags: [machine-learning]
|
data/datasets/lilac/opus100-en-us-validation/data-00000-of-00001.parquet
ADDED
Binary file (304 kB). View file
|
|
data/datasets/lilac/opus100-en-us-validation/manifest.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"files": [
|
3 |
+
"data-00000-of-00001.parquet"
|
4 |
+
],
|
5 |
+
"data_schema": {
|
6 |
+
"fields": {
|
7 |
+
"translation": {
|
8 |
+
"fields": {
|
9 |
+
"en": {
|
10 |
+
"dtype": "string"
|
11 |
+
},
|
12 |
+
"es": {
|
13 |
+
"dtype": "string"
|
14 |
+
}
|
15 |
+
}
|
16 |
+
},
|
17 |
+
"__hfsplit__": {
|
18 |
+
"dtype": "string"
|
19 |
+
}
|
20 |
+
}
|
21 |
+
}
|
22 |
+
}
|
data/datasets/lilac/opus100-en-us-validation/translation/en/lang_detection/data-00000-of-00001.parquet
ADDED
Binary file (70 kB). View file
|
|
data/datasets/lilac/opus100-en-us-validation/translation/en/lang_detection/signal_manifest.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"files": [
|
3 |
+
"data-00000-of-00001.parquet"
|
4 |
+
],
|
5 |
+
"parquet_id": "translation.en.lang_detection",
|
6 |
+
"data_schema": {
|
7 |
+
"fields": {
|
8 |
+
"translation": {
|
9 |
+
"fields": {
|
10 |
+
"en": {
|
11 |
+
"fields": {
|
12 |
+
"lang_detection": {
|
13 |
+
"dtype": "string",
|
14 |
+
"signal": {
|
15 |
+
"split_by_paragraph": false,
|
16 |
+
"signal_name": "lang_detection"
|
17 |
+
}
|
18 |
+
}
|
19 |
+
}
|
20 |
+
}
|
21 |
+
}
|
22 |
+
}
|
23 |
+
}
|
24 |
+
},
|
25 |
+
"signal": {
|
26 |
+
"split_by_paragraph": false,
|
27 |
+
"signal_name": "lang_detection"
|
28 |
+
},
|
29 |
+
"enriched_path": [
|
30 |
+
"translation",
|
31 |
+
"en"
|
32 |
+
]
|
33 |
+
}
|
data/datasets/lilac/opus100-en-us-validation/translation/en/near_dup/data-00000-of-00001.parquet
ADDED
Binary file (80 kB). View file
|
|
data/datasets/lilac/opus100-en-us-validation/translation/en/near_dup/signal_manifest.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"files": [
|
3 |
+
"data-00000-of-00001.parquet"
|
4 |
+
],
|
5 |
+
"parquet_id": "translation.en.near_dup",
|
6 |
+
"data_schema": {
|
7 |
+
"fields": {
|
8 |
+
"translation": {
|
9 |
+
"fields": {
|
10 |
+
"en": {
|
11 |
+
"fields": {
|
12 |
+
"near_dup": {
|
13 |
+
"fields": {
|
14 |
+
"cluster_id": {
|
15 |
+
"dtype": "uint32",
|
16 |
+
"categorical": true
|
17 |
+
}
|
18 |
+
},
|
19 |
+
"signal": {
|
20 |
+
"threshold": 0.85,
|
21 |
+
"signal_name": "near_dup"
|
22 |
+
}
|
23 |
+
}
|
24 |
+
}
|
25 |
+
}
|
26 |
+
}
|
27 |
+
}
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"signal": {
|
31 |
+
"threshold": 0.85,
|
32 |
+
"signal_name": "near_dup"
|
33 |
+
},
|
34 |
+
"enriched_path": [
|
35 |
+
"translation",
|
36 |
+
"en"
|
37 |
+
]
|
38 |
+
}
|
data/datasets/lilac/opus100-en-us-validation/translation/en/pii/data-00000-of-00001.parquet
ADDED
Binary file (71.7 kB). View file
|
|
data/datasets/lilac/opus100-en-us-validation/translation/en/pii/signal_manifest.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"files": [
|
3 |
+
"data-00000-of-00001.parquet"
|
4 |
+
],
|
5 |
+
"parquet_id": "translation.en.pii",
|
6 |
+
"data_schema": {
|
7 |
+
"fields": {
|
8 |
+
"translation": {
|
9 |
+
"fields": {
|
10 |
+
"en": {
|
11 |
+
"fields": {
|
12 |
+
"pii": {
|
13 |
+
"fields": {
|
14 |
+
"emails": {
|
15 |
+
"repeated_field": {
|
16 |
+
"dtype": "string_span"
|
17 |
+
}
|
18 |
+
},
|
19 |
+
"ip_addresses": {
|
20 |
+
"repeated_field": {
|
21 |
+
"dtype": "string_span"
|
22 |
+
}
|
23 |
+
},
|
24 |
+
"secrets": {
|
25 |
+
"repeated_field": {
|
26 |
+
"dtype": "string_span"
|
27 |
+
}
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"signal": {
|
31 |
+
"signal_name": "pii"
|
32 |
+
}
|
33 |
+
}
|
34 |
+
}
|
35 |
+
}
|
36 |
+
}
|
37 |
+
}
|
38 |
+
}
|
39 |
+
},
|
40 |
+
"signal": {
|
41 |
+
"signal_name": "pii"
|
42 |
+
},
|
43 |
+
"enriched_path": [
|
44 |
+
"translation",
|
45 |
+
"en"
|
46 |
+
]
|
47 |
+
}
|
data/datasets/lilac/opus100-en-us-validation/translation/en/text_statistics/data-00000-of-00001.parquet
ADDED
Binary file (84.2 kB). View file
|
|
data/datasets/lilac/opus100-en-us-validation/translation/en/text_statistics/signal_manifest.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"files": [
|
3 |
+
"data-00000-of-00001.parquet"
|
4 |
+
],
|
5 |
+
"parquet_id": "translation.en.text_statistics",
|
6 |
+
"data_schema": {
|
7 |
+
"fields": {
|
8 |
+
"translation": {
|
9 |
+
"fields": {
|
10 |
+
"en": {
|
11 |
+
"fields": {
|
12 |
+
"text_statistics": {
|
13 |
+
"fields": {
|
14 |
+
"num_characters": {
|
15 |
+
"dtype": "int32"
|
16 |
+
},
|
17 |
+
"readability": {
|
18 |
+
"dtype": "float32"
|
19 |
+
},
|
20 |
+
"log(type_token_ratio)": {
|
21 |
+
"dtype": "float32"
|
22 |
+
},
|
23 |
+
"frac_non_ascii": {
|
24 |
+
"dtype": "float32",
|
25 |
+
"bins": [
|
26 |
+
[
|
27 |
+
"Low",
|
28 |
+
null,
|
29 |
+
0.15
|
30 |
+
],
|
31 |
+
[
|
32 |
+
"Medium",
|
33 |
+
0.15,
|
34 |
+
0.3
|
35 |
+
],
|
36 |
+
[
|
37 |
+
"High",
|
38 |
+
0.3,
|
39 |
+
null
|
40 |
+
]
|
41 |
+
]
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"signal": {
|
45 |
+
"signal_name": "text_statistics"
|
46 |
+
}
|
47 |
+
}
|
48 |
+
}
|
49 |
+
}
|
50 |
+
}
|
51 |
+
}
|
52 |
+
}
|
53 |
+
},
|
54 |
+
"signal": {
|
55 |
+
"signal_name": "text_statistics"
|
56 |
+
},
|
57 |
+
"enriched_path": [
|
58 |
+
"translation",
|
59 |
+
"en"
|
60 |
+
]
|
61 |
+
}
|
data/datasets/lilac/opus100-en-us-validation/translation/es/lang_detection/data-00000-of-00001.parquet
ADDED
Binary file (69.9 kB). View file
|
|
data/datasets/lilac/opus100-en-us-validation/translation/es/lang_detection/signal_manifest.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"files": [
|
3 |
+
"data-00000-of-00001.parquet"
|
4 |
+
],
|
5 |
+
"parquet_id": "translation.es.lang_detection",
|
6 |
+
"data_schema": {
|
7 |
+
"fields": {
|
8 |
+
"translation": {
|
9 |
+
"fields": {
|
10 |
+
"es": {
|
11 |
+
"fields": {
|
12 |
+
"lang_detection": {
|
13 |
+
"dtype": "string",
|
14 |
+
"signal": {
|
15 |
+
"split_by_paragraph": false,
|
16 |
+
"signal_name": "lang_detection"
|
17 |
+
}
|
18 |
+
}
|
19 |
+
}
|
20 |
+
}
|
21 |
+
}
|
22 |
+
}
|
23 |
+
}
|
24 |
+
},
|
25 |
+
"signal": {
|
26 |
+
"split_by_paragraph": false,
|
27 |
+
"signal_name": "lang_detection"
|
28 |
+
},
|
29 |
+
"enriched_path": [
|
30 |
+
"translation",
|
31 |
+
"es"
|
32 |
+
]
|
33 |
+
}
|
data/datasets/lilac/opus100-en-us-validation/translation/es/near_dup/data-00000-of-00001.parquet
ADDED
Binary file (80 kB). View file
|
|
data/datasets/lilac/opus100-en-us-validation/translation/es/near_dup/signal_manifest.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"files": [
|
3 |
+
"data-00000-of-00001.parquet"
|
4 |
+
],
|
5 |
+
"parquet_id": "translation.es.near_dup",
|
6 |
+
"data_schema": {
|
7 |
+
"fields": {
|
8 |
+
"translation": {
|
9 |
+
"fields": {
|
10 |
+
"es": {
|
11 |
+
"fields": {
|
12 |
+
"near_dup": {
|
13 |
+
"fields": {
|
14 |
+
"cluster_id": {
|
15 |
+
"dtype": "uint32",
|
16 |
+
"categorical": true
|
17 |
+
}
|
18 |
+
},
|
19 |
+
"signal": {
|
20 |
+
"threshold": 0.85,
|
21 |
+
"signal_name": "near_dup"
|
22 |
+
}
|
23 |
+
}
|
24 |
+
}
|
25 |
+
}
|
26 |
+
}
|
27 |
+
}
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"signal": {
|
31 |
+
"threshold": 0.85,
|
32 |
+
"signal_name": "near_dup"
|
33 |
+
},
|
34 |
+
"enriched_path": [
|
35 |
+
"translation",
|
36 |
+
"es"
|
37 |
+
]
|
38 |
+
}
|
data/datasets/lilac/opus100-en-us-validation/translation/es/pii/data-00000-of-00001.parquet
ADDED
Binary file (71.7 kB). View file
|
|
data/datasets/lilac/opus100-en-us-validation/translation/es/pii/signal_manifest.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"files": [
|
3 |
+
"data-00000-of-00001.parquet"
|
4 |
+
],
|
5 |
+
"parquet_id": "translation.es.pii",
|
6 |
+
"data_schema": {
|
7 |
+
"fields": {
|
8 |
+
"translation": {
|
9 |
+
"fields": {
|
10 |
+
"es": {
|
11 |
+
"fields": {
|
12 |
+
"pii": {
|
13 |
+
"fields": {
|
14 |
+
"emails": {
|
15 |
+
"repeated_field": {
|
16 |
+
"dtype": "string_span"
|
17 |
+
}
|
18 |
+
},
|
19 |
+
"ip_addresses": {
|
20 |
+
"repeated_field": {
|
21 |
+
"dtype": "string_span"
|
22 |
+
}
|
23 |
+
},
|
24 |
+
"secrets": {
|
25 |
+
"repeated_field": {
|
26 |
+
"dtype": "string_span"
|
27 |
+
}
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"signal": {
|
31 |
+
"signal_name": "pii"
|
32 |
+
}
|
33 |
+
}
|
34 |
+
}
|
35 |
+
}
|
36 |
+
}
|
37 |
+
}
|
38 |
+
}
|
39 |
+
},
|
40 |
+
"signal": {
|
41 |
+
"signal_name": "pii"
|
42 |
+
},
|
43 |
+
"enriched_path": [
|
44 |
+
"translation",
|
45 |
+
"es"
|
46 |
+
]
|
47 |
+
}
|
data/datasets/lilac/opus100-en-us-validation/translation/es/text_statistics/data-00000-of-00001.parquet
ADDED
Binary file (87.4 kB). View file
|
|
data/datasets/lilac/opus100-en-us-validation/translation/es/text_statistics/signal_manifest.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"files": [
|
3 |
+
"data-00000-of-00001.parquet"
|
4 |
+
],
|
5 |
+
"parquet_id": "translation.es.text_statistics",
|
6 |
+
"data_schema": {
|
7 |
+
"fields": {
|
8 |
+
"translation": {
|
9 |
+
"fields": {
|
10 |
+
"es": {
|
11 |
+
"fields": {
|
12 |
+
"text_statistics": {
|
13 |
+
"fields": {
|
14 |
+
"num_characters": {
|
15 |
+
"dtype": "int32"
|
16 |
+
},
|
17 |
+
"readability": {
|
18 |
+
"dtype": "float32"
|
19 |
+
},
|
20 |
+
"log(type_token_ratio)": {
|
21 |
+
"dtype": "float32"
|
22 |
+
},
|
23 |
+
"frac_non_ascii": {
|
24 |
+
"dtype": "float32",
|
25 |
+
"bins": [
|
26 |
+
[
|
27 |
+
"Low",
|
28 |
+
null,
|
29 |
+
0.15
|
30 |
+
],
|
31 |
+
[
|
32 |
+
"Medium",
|
33 |
+
0.15,
|
34 |
+
0.3
|
35 |
+
],
|
36 |
+
[
|
37 |
+
"High",
|
38 |
+
0.3,
|
39 |
+
null
|
40 |
+
]
|
41 |
+
]
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"signal": {
|
45 |
+
"signal_name": "text_statistics"
|
46 |
+
}
|
47 |
+
}
|
48 |
+
}
|
49 |
+
}
|
50 |
+
}
|
51 |
+
}
|
52 |
+
}
|
53 |
+
},
|
54 |
+
"signal": {
|
55 |
+
"signal_name": "text_statistics"
|
56 |
+
},
|
57 |
+
"enriched_path": [
|
58 |
+
"translation",
|
59 |
+
"es"
|
60 |
+
]
|
61 |
+
}
|