adrianeboyd commited on
Commit
c004b3f
1 Parent(s): aaf8333

Update spaCy pipeline

Browse files
README.md CHANGED
@@ -13,7 +13,7 @@ model-index:
13
  metrics:
14
  - name: Sentences F-Score
15
  type: f_score
16
- value: 0.8588287584
17
  ---
18
  ### Details: https://spacy.io/models/xx#xx_sent_ud_sm
19
 
@@ -22,10 +22,10 @@ Multi-language pipeline optimized for CPU. Components: senter.
22
  | Feature | Description |
23
  | --- | --- |
24
  | **Name** | `xx_sent_ud_sm` |
25
- | **Version** | `3.3.0` |
26
- | **spaCy** | `>=3.3.0.dev0,<3.4.0` |
27
- | **Default Pipeline** | `senter`, `attribute_ruler` |
28
- | **Components** | `senter`, `attribute_ruler` |
29
  | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
30
  | **Sources** | [Universal Dependencies v2.8 (UD_Afrikaans-AfriBooms, UD_Croatian-SET, UD_Czech-CAC, UD_Czech-CLTT, UD_Danish-DDT, UD_Dutch-Alpino, UD_Dutch-LassySmall, UD_English-EWT, UD_Finnish-FTB, UD_Finnish-TDT, UD_French-GSD, UD_French-Spoken, UD_German-GSD, UD_Indonesian-GSD, UD_Irish-IDT, UD_Italian-TWITTIRO, UD_Korean-GSD, UD_Korean-Kaist, UD_Latvian-LVTB, UD_Lithuanian-ALKSNIS, UD_Lithuanian-HSE, UD_Marathi-UFAL, UD_Norwegian-Bokmaal, UD_Norwegian-Nynorsk, UD_Norwegian-NynorskLIA, UD_Persian-Seraji, UD_Portuguese-Bosque, UD_Portuguese-GSD, UD_Romanian-Nonstandard, UD_Romanian-RRT, UD_Russian-GSD, UD_Russian-Taiga, UD_Serbian-SET, UD_Slovak-SNK, UD_Spanish-GSD, UD_Swedish-Talbanken, UD_Telugu-MTG, UD_Vietnamese-VTB)](https://universaldependencies.org/) (Zeman, Daniel; Nivre, Joakim; Abrams, Mitchell; et al.) |
31
  | **License** | `CC BY-SA 3.0` |
@@ -43,6 +43,6 @@ Multi-language pipeline optimized for CPU. Components: senter.
43
  | `TOKEN_P` | 95.31 |
44
  | `TOKEN_R` | 95.72 |
45
  | `TOKEN_F` | 95.52 |
46
- | `SENTS_P` | 90.62 |
47
- | `SENTS_R` | 81.62 |
48
- | `SENTS_F` | 85.88 |
13
  metrics:
14
  - name: Sentences F-Score
15
  type: f_score
16
+ value: 0.8580767932
17
  ---
18
  ### Details: https://spacy.io/models/xx#xx_sent_ud_sm
19
 
22
  | Feature | Description |
23
  | --- | --- |
24
  | **Name** | `xx_sent_ud_sm` |
25
+ | **Version** | `3.4.0` |
26
+ | **spaCy** | `>=3.4.0,<3.5.0` |
27
+ | **Default Pipeline** | `senter` |
28
+ | **Components** | `senter` |
29
  | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
30
  | **Sources** | [Universal Dependencies v2.8 (UD_Afrikaans-AfriBooms, UD_Croatian-SET, UD_Czech-CAC, UD_Czech-CLTT, UD_Danish-DDT, UD_Dutch-Alpino, UD_Dutch-LassySmall, UD_English-EWT, UD_Finnish-FTB, UD_Finnish-TDT, UD_French-GSD, UD_French-Spoken, UD_German-GSD, UD_Indonesian-GSD, UD_Irish-IDT, UD_Italian-TWITTIRO, UD_Korean-GSD, UD_Korean-Kaist, UD_Latvian-LVTB, UD_Lithuanian-ALKSNIS, UD_Lithuanian-HSE, UD_Marathi-UFAL, UD_Norwegian-Bokmaal, UD_Norwegian-Nynorsk, UD_Norwegian-NynorskLIA, UD_Persian-Seraji, UD_Portuguese-Bosque, UD_Portuguese-GSD, UD_Romanian-Nonstandard, UD_Romanian-RRT, UD_Russian-GSD, UD_Russian-Taiga, UD_Serbian-SET, UD_Slovak-SNK, UD_Spanish-GSD, UD_Swedish-Talbanken, UD_Telugu-MTG, UD_Vietnamese-VTB)](https://universaldependencies.org/) (Zeman, Daniel; Nivre, Joakim; Abrams, Mitchell; et al.) |
31
  | **License** | `CC BY-SA 3.0` |
43
  | `TOKEN_P` | 95.31 |
44
  | `TOKEN_R` | 95.72 |
45
  | `TOKEN_F` | 95.52 |
46
+ | `SENTS_P` | 90.67 |
47
+ | `SENTS_R` | 81.44 |
48
+ | `SENTS_F` | 85.81 |
accuracy.json CHANGED
@@ -3,8 +3,8 @@
3
  "token_p": 0.9530830451,
4
  "token_r": 0.9572374635,
5
  "token_f": 0.955155737,
6
- "sents_p": 0.906203506,
7
- "sents_r": 0.8161612631,
8
- "sents_f": 0.8588287584,
9
- "speed": 145246.3943469636
10
  }
3
  "token_p": 0.9530830451,
4
  "token_r": 0.9572374635,
5
  "token_f": 0.955155737,
6
+ "sents_p": 0.9067233159,
7
+ "sents_r": 0.8143843398,
8
+ "sents_f": 0.8580767932,
9
+ "speed": 174049.2099894174
10
  }
config.cfg CHANGED
@@ -10,7 +10,7 @@ seed = 0
10
 
11
  [nlp]
12
  lang = "xx"
13
- pipeline = ["senter","attribute_ruler"]
14
  disabled = []
15
  before_creation = null
16
  after_creation = null
@@ -20,11 +20,6 @@ tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
20
 
21
  [components]
22
 
23
- [components.attribute_ruler]
24
- factory = "attribute_ruler"
25
- scorer = {"@scorers":"spacy.attribute_ruler_scorer.v1"}
26
- validate = false
27
-
28
  [components.senter]
29
  factory = "senter"
30
  overwrite = false
10
 
11
  [nlp]
12
  lang = "xx"
13
+ pipeline = ["senter"]
14
  disabled = []
15
  before_creation = null
16
  after_creation = null
20
 
21
  [components]
22
 
 
 
 
 
 
23
  [components.senter]
24
  factory = "senter"
25
  overwrite = false
meta.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "lang":"xx",
3
  "name":"sent_ud_sm",
4
- "version":"3.3.0",
5
  "description":"Multi-language pipeline optimized for CPU. Components: senter.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"CC BY-SA 3.0",
10
- "spacy_version":">=3.3.0.dev0,<3.4.0",
11
- "spacy_git_version":"849bef2de",
12
  "vectors":{
13
  "width":0,
14
  "vectors":0,
@@ -16,17 +16,13 @@
16
  "name":null
17
  },
18
  "labels":{
19
- "attribute_ruler":[
20
 
21
- ]
22
  },
23
  "pipeline":[
24
- "senter",
25
- "attribute_ruler"
26
  ],
27
  "components":[
28
- "senter",
29
- "attribute_ruler"
30
  ],
31
  "disabled":[
32
 
@@ -36,10 +32,10 @@
36
  "token_p":0.9530830451,
37
  "token_r":0.9572374635,
38
  "token_f":0.955155737,
39
- "sents_p":0.906203506,
40
- "sents_r":0.8161612631,
41
- "sents_f":0.8588287584,
42
- "speed":145246.3943469636
43
  },
44
  "sources":[
45
  {
1
  {
2
  "lang":"xx",
3
  "name":"sent_ud_sm",
4
+ "version":"3.4.0",
5
  "description":"Multi-language pipeline optimized for CPU. Components: senter.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"CC BY-SA 3.0",
10
+ "spacy_version":">=3.4.0,<3.5.0",
11
+ "spacy_git_version":"dd038b536",
12
  "vectors":{
13
  "width":0,
14
  "vectors":0,
16
  "name":null
17
  },
18
  "labels":{
 
19
 
 
20
  },
21
  "pipeline":[
22
+ "senter"
 
23
  ],
24
  "components":[
25
+ "senter"
 
26
  ],
27
  "disabled":[
28
 
32
  "token_p":0.9530830451,
33
  "token_r":0.9572374635,
34
  "token_f":0.955155737,
35
+ "sents_p":0.9067233159,
36
+ "sents_r":0.8143843398,
37
+ "sents_f":0.8580767932,
38
+ "speed":174049.2099894174
39
  },
40
  "sources":[
41
  {
senter/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:379396469b9a2633d32c550e0ee22d4006d1b5a23721bf4d8055becd09c61a92
3
  size 197089
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:246adc5eaf65c874096bcbc872fe05e102f19e7f1f9fd1e3adce173f1b9a32be
3
  size 197089
vocab/strings.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a6ea05faef8d756b8a8268be6ea6798dd4deb2729d3c1b456eb6045887fa80d
3
- size 22438359
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc7b2014c27f229fc1a30b1785a675047e7af79e4adf1c84e07521c7bf8b8ee9
3
+ size 22450815
xx_sent_ud_sm-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e6f59ab5356e3c839192008da6b32aeaf9b344e285da9aecc84f03b0a6d0127
3
- size 4322862
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e43437e2847e57d913e86f978e3c86d2cc74d1b8caf6091757cd856a6d9c771
3
+ size 4324474