Update spacy pipeline to 3.4.1
Browse files- README.md +17 -17
- config.cfg +3 -3
- hu_core_news_lg-any-py3-none-any.whl +2 -2
- lookup_lemmatizer/lookups.bin +2 -2
- meta.json +3 -3
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
|
@@ -76,7 +76,7 @@ Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morpholog
|
|
76 |
| Feature | Description |
|
77 |
| --- | --- |
|
78 |
| **Name** | `hu_core_news_lg` |
|
79 |
-
| **Version** | `3.4.
|
80 |
| **spaCy** | `>=3.4.1,<3.5.0` |
|
81 |
| **Default Pipeline** | `tok2vec`, `senter`, `tagger`, `morphologizer`, `lookup_lemmatizer`, `lemmatizer`, `lemma_smoother`, `parser`, `ner` |
|
82 |
| **Components** | `tok2vec`, `senter`, `tagger`, `morphologizer`, `lookup_lemmatizer`, `lemmatizer`, `lemma_smoother`, `parser`, `ner` |
|
@@ -108,18 +108,18 @@ Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morpholog
|
|
108 |
| `TOKEN_P` | 99.86 |
|
109 |
| `TOKEN_R` | 99.93 |
|
110 |
| `TOKEN_F` | 99.89 |
|
111 |
-
| `SENTS_P` |
|
112 |
-
| `SENTS_R` |
|
113 |
-
| `SENTS_F` |
|
114 |
-
| `TAG_ACC` | 96.
|
115 |
-
| `POS_ACC` | 96.
|
116 |
-
| `MORPH_ACC` | 93.
|
117 |
-
| `MORPH_MICRO_P` | 96.
|
118 |
-
| `MORPH_MICRO_R` |
|
119 |
-
| `MORPH_MICRO_F` | 96.
|
120 |
-
| `LEMMA_ACC` | 97.
|
121 |
-
| `DEP_UAS` |
|
122 |
-
| `DEP_LAS` |
|
123 |
-
| `ENTS_P` |
|
124 |
-
| `ENTS_R` |
|
125 |
-
| `ENTS_F` | 85.
|
|
|
48 |
metrics:
|
49 |
- name: Lemma Accuracy
|
50 |
type: accuracy
|
51 |
+
value: 0.9725385131
|
52 |
- task:
|
53 |
name: UNLABELED_DEPENDENCIES
|
54 |
type: token-classification
|
|
|
76 |
| Feature | Description |
|
77 |
| --- | --- |
|
78 |
| **Name** | `hu_core_news_lg` |
|
79 |
+
| **Version** | `3.4.1` |
|
80 |
| **spaCy** | `>=3.4.1,<3.5.0` |
|
81 |
| **Default Pipeline** | `tok2vec`, `senter`, `tagger`, `morphologizer`, `lookup_lemmatizer`, `lemmatizer`, `lemma_smoother`, `parser`, `ner` |
|
82 |
| **Components** | `tok2vec`, `senter`, `tagger`, `morphologizer`, `lookup_lemmatizer`, `lemmatizer`, `lemma_smoother`, `parser`, `ner` |
|
|
|
108 |
| `TOKEN_P` | 99.86 |
|
109 |
| `TOKEN_R` | 99.93 |
|
110 |
| `TOKEN_F` | 99.89 |
|
111 |
+
| `SENTS_P` | 97.33 |
|
112 |
+
| `SENTS_R` | 97.33 |
|
113 |
+
| `SENTS_F` | 97.33 |
|
114 |
+
| `TAG_ACC` | 96.51 |
|
115 |
+
| `POS_ACC` | 96.40 |
|
116 |
+
| `MORPH_ACC` | 93.21 |
|
117 |
+
| `MORPH_MICRO_P` | 96.46 |
|
118 |
+
| `MORPH_MICRO_R` | 95.71 |
|
119 |
+
| `MORPH_MICRO_F` | 96.08 |
|
120 |
+
| `LEMMA_ACC` | 97.25 |
|
121 |
+
| `DEP_UAS` | 82.19 |
|
122 |
+
| `DEP_LAS` | 75.36 |
|
123 |
+
| `ENTS_P` | 87.11 |
|
124 |
+
| `ENTS_R` | 83.86 |
|
125 |
+
| `ENTS_F` | 85.45 |
|
config.cfg
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
[paths]
|
2 |
-
parser_model = "models/hu_core_news_lg-parser-3.4.
|
3 |
-
ner_model = "models/hu_core_news_lg-ner-3.4.
|
4 |
-
lemmatizer_lookups = "models/hu_core_news_lg-lookup-lemmatizer-3.4.
|
5 |
train = null
|
6 |
dev = null
|
7 |
vectors = null
|
|
|
1 |
[paths]
|
2 |
+
parser_model = "models/hu_core_news_lg-parser-3.4.1/model-best"
|
3 |
+
ner_model = "models/hu_core_news_lg-ner-3.4.1/model-best"
|
4 |
+
lemmatizer_lookups = "models/hu_core_news_lg-lookup-lemmatizer-3.4.1"
|
5 |
train = null
|
6 |
dev = null
|
7 |
vectors = null
|
hu_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:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f079abed131fecaa24aed633d39282234d375428e37d4cc83cc6c44c201d6db4
|
3 |
+
size 403677948
|
lookup_lemmatizer/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:feec80a6080dae4271271b47126eeed546a7ab6b77025ecbca8f35fd8e5fb161
|
3 |
+
size 8992457
|
meta.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"lang":"hu",
|
3 |
"name":"core_news_lg",
|
4 |
-
"version":"3.4.
|
5 |
"description":"Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morphologizer, lemmatizer, parser, ner",
|
6 |
"author":"SzegedAI, MILAB",
|
7 |
"email":"gyorgy@orosz.link",
|
@@ -1370,7 +1370,7 @@
|
|
1370 |
"f":0.0
|
1371 |
}
|
1372 |
},
|
1373 |
-
"lemma_acc":0.
|
1374 |
"dep_uas":0.8218578007,
|
1375 |
"dep_las":0.7535662136,
|
1376 |
"dep_las_per_type":{
|
@@ -1625,7 +1625,7 @@
|
|
1625 |
"f":0.645316253
|
1626 |
}
|
1627 |
},
|
1628 |
-
"speed":
|
1629 |
},
|
1630 |
"sources":[
|
1631 |
{
|
|
|
1 |
{
|
2 |
"lang":"hu",
|
3 |
"name":"core_news_lg",
|
4 |
+
"version":"3.4.1",
|
5 |
"description":"Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morphologizer, lemmatizer, parser, ner",
|
6 |
"author":"SzegedAI, MILAB",
|
7 |
"email":"gyorgy@orosz.link",
|
|
|
1370 |
"f":0.0
|
1371 |
}
|
1372 |
},
|
1373 |
+
"lemma_acc":0.9725385131,
|
1374 |
"dep_uas":0.8218578007,
|
1375 |
"dep_las":0.7535662136,
|
1376 |
"dep_las_per_type":{
|
|
|
1625 |
"f":0.645316253
|
1626 |
}
|
1627 |
},
|
1628 |
+
"speed":622.2586431165
|
1629 |
},
|
1630 |
"sources":[
|
1631 |
{
|