adrianeboyd
commited on
Commit
·
d8881d4
1
Parent(s):
0fd36d2
Update spaCy pipeline
Browse files- README.md +2 -2
- accuracy.json +1 -1
- config.cfg +2 -0
- de_core_news_md-any-py3-none-any.whl +2 -2
- meta.json +4 -4
- morphologizer/cfg +1 -0
- tagger/cfg +1 -0
README.md
CHANGED
@@ -78,8 +78,8 @@ German pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, p
|
|
78 |
| Feature | Description |
|
79 |
| --- | --- |
|
80 |
| **Name** | `de_core_news_md` |
|
81 |
-
| **Version** | `3.
|
82 |
-
| **spaCy** | `>=3.
|
83 |
| **Default Pipeline** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
|
84 |
| **Components** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `senter`, `attribute_ruler`, `ner` |
|
85 |
| **Vectors** | 500000 keys, 20000 unique vectors (300 dimensions) |
|
|
|
78 |
| Feature | Description |
|
79 |
| --- | --- |
|
80 |
| **Name** | `de_core_news_md` |
|
81 |
+
| **Version** | `3.6.0` |
|
82 |
+
| **spaCy** | `>=3.6.0,<3.7.0` |
|
83 |
| **Default Pipeline** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
|
84 |
| **Components** | `tok2vec`, `tagger`, `morphologizer`, `parser`, `lemmatizer`, `senter`, `attribute_ruler`, `ner` |
|
85 |
| **Vectors** | 500000 keys, 20000 unique vectors (300 dimensions) |
|
accuracy.json
CHANGED
@@ -289,7 +289,7 @@
|
|
289 |
}
|
290 |
},
|
291 |
"lemma_acc": 0.9769605349,
|
292 |
-
"speed":
|
293 |
"ents_p": 0.8439391945,
|
294 |
"ents_r": 0.8342856523,
|
295 |
"ents_f": 0.8390846587,
|
|
|
289 |
}
|
290 |
},
|
291 |
"lemma_acc": 0.9769605349,
|
292 |
+
"speed": 11831.800084006,
|
293 |
"ents_p": 0.8439391945,
|
294 |
"ents_r": 0.8342856523,
|
295 |
"ents_f": 0.8390846587,
|
config.cfg
CHANGED
@@ -46,6 +46,7 @@ upstream = "tok2vec"
|
|
46 |
[components.morphologizer]
|
47 |
factory = "morphologizer"
|
48 |
extend = false
|
|
|
49 |
overwrite = true
|
50 |
scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
|
51 |
|
@@ -143,6 +144,7 @@ maxout_pieces = 2
|
|
143 |
|
144 |
[components.tagger]
|
145 |
factory = "tagger"
|
|
|
146 |
neg_prefix = "!"
|
147 |
overwrite = false
|
148 |
scorer = {"@scorers":"spacy.tagger_scorer.v1"}
|
|
|
46 |
[components.morphologizer]
|
47 |
factory = "morphologizer"
|
48 |
extend = false
|
49 |
+
label_smoothing = 0.0
|
50 |
overwrite = true
|
51 |
scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
|
52 |
|
|
|
144 |
|
145 |
[components.tagger]
|
146 |
factory = "tagger"
|
147 |
+
label_smoothing = 0.0
|
148 |
neg_prefix = "!"
|
149 |
overwrite = false
|
150 |
scorer = {"@scorers":"spacy.tagger_scorer.v1"}
|
de_core_news_md-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:c289fe1bfcc3e3670f2e0e849e8b8c83ecb83cc70045522a1e06a56b291ed30d
|
3 |
+
size 44395071
|
meta.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
"lang":"de",
|
3 |
"name":"core_news_md",
|
4 |
-
"version":"3.
|
5 |
"description":"German pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, parser, lemmatizer (trainable_lemmatizer), senter, ner.",
|
6 |
"author":"Explosion",
|
7 |
"email":"[email protected]",
|
8 |
"url":"https://explosion.ai",
|
9 |
"license":"MIT",
|
10 |
-
"spacy_version":">=3.
|
11 |
-
"spacy_git_version":"
|
12 |
"vectors":{
|
13 |
"width":300,
|
14 |
"vectors":20000,
|
@@ -1116,7 +1116,7 @@
|
|
1116 |
}
|
1117 |
},
|
1118 |
"lemma_acc":0.9769605349,
|
1119 |
-
"speed":
|
1120 |
"ents_p":0.8439391945,
|
1121 |
"ents_r":0.8342856523,
|
1122 |
"ents_f":0.8390846587,
|
|
|
1 |
{
|
2 |
"lang":"de",
|
3 |
"name":"core_news_md",
|
4 |
+
"version":"3.6.0",
|
5 |
"description":"German pipeline optimized for CPU. Components: tok2vec, tagger, morphologizer, parser, lemmatizer (trainable_lemmatizer), senter, ner.",
|
6 |
"author":"Explosion",
|
7 |
"email":"[email protected]",
|
8 |
"url":"https://explosion.ai",
|
9 |
"license":"MIT",
|
10 |
+
"spacy_version":">=3.6.0,<3.7.0",
|
11 |
+
"spacy_git_version":"cb4fdc83e",
|
12 |
"vectors":{
|
13 |
"width":300,
|
14 |
"vectors":20000,
|
|
|
1116 |
}
|
1117 |
},
|
1118 |
"lemma_acc":0.9769605349,
|
1119 |
+
"speed":11831.800084006,
|
1120 |
"ents_p":0.8439391945,
|
1121 |
"ents_r":0.8342856523,
|
1122 |
"ents_f":0.8390846587,
|
morphologizer/cfg
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
{
|
2 |
"extend":false,
|
|
|
3 |
"labels_morph":{
|
4 |
"POS=PUNCT":"",
|
5 |
"Case=Nom|Gender=Masc|Number=Sing|POS=PROPN":"Case=Nom|Gender=Masc|Number=Sing",
|
|
|
1 |
{
|
2 |
"extend":false,
|
3 |
+
"label_smoothing":0.0,
|
4 |
"labels_morph":{
|
5 |
"POS=PUNCT":"",
|
6 |
"Case=Nom|Gender=Masc|Number=Sing|POS=PROPN":"Case=Nom|Gender=Masc|Number=Sing",
|
tagger/cfg
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"labels":[
|
3 |
"$(",
|
4 |
"$,",
|
|
|
1 |
{
|
2 |
+
"label_smoothing":0.0,
|
3 |
"labels":[
|
4 |
"$(",
|
5 |
"$,",
|