adrianeboyd
commited on
Commit
•
166d982
1
Parent(s):
d871683
Update spaCy pipeline
Browse files- README.md +4 -4
- accuracy.json +2 -2
- config.cfg +1 -0
- es_core_news_sm-any-py3-none-any.whl +2 -2
- lemmatizer/lookups/lookups.bin +2 -2
- meta.json +5 -5
README.md
CHANGED
@@ -48,7 +48,7 @@ model-index:
|
|
48 |
metrics:
|
49 |
- name: Lemma Accuracy
|
50 |
type: accuracy
|
51 |
-
value: 0.
|
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_sm` |
|
81 |
-
| **Version** | `3.
|
82 |
-
| **spaCy** | `>=3.
|
83 |
| **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
|
84 |
| **Components** | `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |
|
85 |
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
|
@@ -120,7 +120,7 @@ Spanish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser,
|
|
120 |
| `DEP_UAS` | 90.38 |
|
121 |
| `DEP_LAS` | 86.85 |
|
122 |
| `TAG_ACC` | 95.81 |
|
123 |
-
| `LEMMA_ACC` | 96.
|
124 |
| `ENTS_P` | 89.10 |
|
125 |
| `ENTS_R` | 89.18 |
|
126 |
| `ENTS_F` | 89.14 |
|
|
|
48 |
metrics:
|
49 |
- name: Lemma Accuracy
|
50 |
type: accuracy
|
51 |
+
value: 0.9629594135
|
52 |
- task:
|
53 |
name: UNLABELED_DEPENDENCIES
|
54 |
type: token-classification
|
|
|
78 |
| Feature | Description |
|
79 |
| --- | --- |
|
80 |
| **Name** | `es_core_news_sm` |
|
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** | 0 keys, 0 unique vectors (0 dimensions) |
|
|
|
120 |
| `DEP_UAS` | 90.38 |
|
121 |
| `DEP_LAS` | 86.85 |
|
122 |
| `TAG_ACC` | 95.81 |
|
123 |
+
| `LEMMA_ACC` | 96.30 |
|
124 |
| `ENTS_P` | 89.10 |
|
125 |
| `ENTS_R` | 89.18 |
|
126 |
| `ENTS_F` | 89.14 |
|
accuracy.json
CHANGED
@@ -293,7 +293,7 @@
|
|
293 |
}
|
294 |
},
|
295 |
"tag_acc": 0.9581496108,
|
296 |
-
"lemma_acc": 0.
|
297 |
"ents_p": 0.8910285087,
|
298 |
"ents_r": 0.8918264338,
|
299 |
"ents_f": 0.8914272927,
|
@@ -319,5 +319,5 @@
|
|
319 |
"f": 0.8283256746
|
320 |
}
|
321 |
},
|
322 |
-
"speed":
|
323 |
}
|
|
|
293 |
}
|
294 |
},
|
295 |
"tag_acc": 0.9581496108,
|
296 |
+
"lemma_acc": 0.9629594135,
|
297 |
"ents_p": 0.8910285087,
|
298 |
"ents_r": 0.8918264338,
|
299 |
"ents_f": 0.8914272927,
|
|
|
319 |
"f": 0.8283256746
|
320 |
}
|
321 |
},
|
322 |
+
"speed": 7753.3136813991
|
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_sm-any-py3-none-any.whl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61e6e5530941f5880166855f09f60d7e6ba79ec1e8e45f96244bdb1eb169eb1d
|
3 |
+
size 12885532
|
lemmatizer/lookups/lookups.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
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_sm",
|
4 |
-
"version":"3.
|
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.
|
11 |
-
"spacy_git_version":"
|
12 |
"vectors":{
|
13 |
"width":0,
|
14 |
"vectors":0,
|
@@ -815,7 +815,7 @@
|
|
815 |
}
|
816 |
},
|
817 |
"tag_acc":0.9581496108,
|
818 |
-
"lemma_acc":0.
|
819 |
"ents_p":0.8910285087,
|
820 |
"ents_r":0.8918264338,
|
821 |
"ents_f":0.8914272927,
|
@@ -841,7 +841,7 @@
|
|
841 |
"f":0.8283256746
|
842 |
}
|
843 |
},
|
844 |
-
"speed":
|
845 |
},
|
846 |
"sources":[
|
847 |
{
|
|
|
1 |
{
|
2 |
"lang":"es",
|
3 |
"name":"core_news_sm",
|
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":0,
|
14 |
"vectors":0,
|
|
|
815 |
}
|
816 |
},
|
817 |
"tag_acc":0.9581496108,
|
818 |
+
"lemma_acc":0.9629594135,
|
819 |
"ents_p":0.8910285087,
|
820 |
"ents_r":0.8918264338,
|
821 |
"ents_f":0.8914272927,
|
|
|
841 |
"f":0.8283256746
|
842 |
}
|
843 |
},
|
844 |
+
"speed":7753.3136813991
|
845 |
},
|
846 |
"sources":[
|
847 |
{
|