adrianeboyd commited on
Commit
b2fdfe5
1 Parent(s): 06106f2

Update spaCy pipeline

Browse files
README.md CHANGED
@@ -48,7 +48,7 @@ model-index:
48
  metrics:
49
  - name: Lemma Accuracy
50
  type: accuracy
51
- value: 0.9657578226
52
  - task:
53
  name: UNLABELED_DEPENDENCIES
54
  type: token-classification
@@ -78,8 +78,8 @@ Spanish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser,
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `es_core_news_lg` |
81
- | **Version** | `3.6.0` |
82
- | **spaCy** | `>=3.6.0,<3.7.0` |
83
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
84
  | **Components** | `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |
85
  | **Vectors** | 500000 keys, 500000 unique vectors (300 dimensions) |
@@ -120,7 +120,7 @@ Spanish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser,
120
  | `DEP_UAS` | 91.40 |
121
  | `DEP_LAS` | 88.19 |
122
  | `TAG_ACC` | 96.14 |
123
- | `LEMMA_ACC` | 96.58 |
124
  | `ENTS_P` | 89.67 |
125
  | `ENTS_R` | 89.78 |
126
  | `ENTS_F` | 89.72 |
48
  metrics:
49
  - name: Lemma Accuracy
50
  type: accuracy
51
+ value: 0.9661603335
52
  - task:
53
  name: UNLABELED_DEPENDENCIES
54
  type: token-classification
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `es_core_news_lg` |
81
+ | **Version** | `3.7.0` |
82
+ | **spaCy** | `>=3.7.0,<3.8.0` |
83
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
84
  | **Components** | `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |
85
  | **Vectors** | 500000 keys, 500000 unique vectors (300 dimensions) |
120
  | `DEP_UAS` | 91.40 |
121
  | `DEP_LAS` | 88.19 |
122
  | `TAG_ACC` | 96.14 |
123
+ | `LEMMA_ACC` | 96.62 |
124
  | `ENTS_P` | 89.67 |
125
  | `ENTS_R` | 89.78 |
126
  | `ENTS_F` | 89.72 |
accuracy.json CHANGED
@@ -293,7 +293,7 @@
293
  }
294
  },
295
  "tag_acc": 0.9614499866,
296
- "lemma_acc": 0.9657578226,
297
  "ents_p": 0.8966603655,
298
  "ents_r": 0.8978100704,
299
  "ents_f": 0.8972348496,
@@ -319,5 +319,5 @@
319
  "f": 0.8364063417
320
  }
321
  },
322
- "speed": 9264.6143815688
323
  }
293
  }
294
  },
295
  "tag_acc": 0.9614499866,
296
+ "lemma_acc": 0.9661603335,
297
  "ents_p": 0.8966603655,
298
  "ents_r": 0.8978100704,
299
  "ents_f": 0.8972348496,
319
  "f": 0.8364063417
320
  }
321
  },
322
+ "speed": 8278.9770789427
323
  }
config.cfg CHANGED
@@ -17,6 +17,7 @@ after_creation = null
17
  after_pipeline_creation = null
18
  batch_size = 256
19
  tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
 
20
 
21
  [components]
22
 
17
  after_pipeline_creation = null
18
  batch_size = 256
19
  tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
20
+ vectors = {"@vectors":"spacy.Vectors.v1"}
21
 
22
  [components]
23
 
es_core_news_lg-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:882bd0af2a5117acc17812e821133d8884cfaf4c93362a9ebac538548729de8d
3
- size 567975366
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08020b83e0c6da1584e567551a5e0de7b15dc0534eaaee21acc1ce908d1be742
3
+ size 567975431
lemmatizer/lookups/lookups.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be833a634de5b55fa529aceee97fcc09a193e2017b5e4b34bafe103ad97600aa
3
- size 165037
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee3740fdad2ebc1cf79a63a8e5b2d2f3dd47b33c3a7a0bc9351ba5a1246b6a07
3
+ size 165225
meta.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "lang":"es",
3
  "name":"core_news_lg",
4
- "version":"3.6.0",
5
  "description":"Spanish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"GNU GPL 3.0",
10
- "spacy_version":">=3.6.0,<3.7.0",
11
- "spacy_git_version":"cb4fdc83e",
12
  "vectors":{
13
  "width":300,
14
  "vectors":500000,
@@ -815,7 +815,7 @@
815
  }
816
  },
817
  "tag_acc":0.9614499866,
818
- "lemma_acc":0.9657578226,
819
  "ents_p":0.8966603655,
820
  "ents_r":0.8978100704,
821
  "ents_f":0.8972348496,
@@ -841,7 +841,7 @@
841
  "f":0.8364063417
842
  }
843
  },
844
- "speed":9264.6143815688
845
  },
846
  "sources":[
847
  {
1
  {
2
  "lang":"es",
3
  "name":"core_news_lg",
4
+ "version":"3.7.0",
5
  "description":"Spanish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"GNU GPL 3.0",
10
+ "spacy_version":">=3.7.0,<3.8.0",
11
+ "spacy_git_version":"6b4f77441",
12
  "vectors":{
13
  "width":300,
14
  "vectors":500000,
815
  }
816
  },
817
  "tag_acc":0.9614499866,
818
+ "lemma_acc":0.9661603335,
819
  "ents_p":0.8966603655,
820
  "ents_r":0.8978100704,
821
  "ents_f":0.8972348496,
841
  "f":0.8364063417
842
  }
843
  },
844
+ "speed":8278.9770789427
845
  },
846
  "sources":[
847
  {