Commit
·
be92e91
1
Parent(s):
eca5c8a
Update spaCy pipeline
Browse files- LICENSES_SOURCES +3 -3
- README.md +29 -29
- accuracy.json +164 -164
- config.cfg +2 -1
- da_core_news_trf-any-py3-none-any.whl +2 -2
- lemmatizer/model +1 -1
- meta.json +172 -172
- morphologizer/cfg +1 -0
- morphologizer/model +1 -1
- ner/model +1 -1
- parser/model +1 -1
- transformer/model +2 -2
- vocab/strings.json +2 -2
LICENSES_SOURCES
CHANGED
|
@@ -878,10 +878,10 @@ Creative Commons may be contacted at creativecommons.org.
|
|
| 878 |
|
| 879 |
|
| 880 |
|
| 881 |
-
#
|
| 882 |
|
| 883 |
-
* Author:
|
| 884 |
-
* URL: https://huggingface.co/
|
| 885 |
* License: CC BY 4.0
|
| 886 |
|
| 887 |
```
|
|
|
|
| 878 |
|
| 879 |
|
| 880 |
|
| 881 |
+
# vesteinn/DanskBERT
|
| 882 |
|
| 883 |
+
* Author: Snæbjarnarson, Vésteinn and Simonsen, Annika and Glavaš, Goran and Vulić, Ivan
|
| 884 |
+
* URL: https://huggingface.co/vesteinn/DanskBERT
|
| 885 |
* License: CC BY 4.0
|
| 886 |
|
| 887 |
```
|
README.md
CHANGED
|
@@ -14,76 +14,76 @@ model-index:
|
|
| 14 |
metrics:
|
| 15 |
- name: NER Precision
|
| 16 |
type: precision
|
| 17 |
-
value: 0.
|
| 18 |
- name: NER Recall
|
| 19 |
type: recall
|
| 20 |
-
value: 0.
|
| 21 |
- name: NER F Score
|
| 22 |
type: f_score
|
| 23 |
-
value: 0.
|
| 24 |
- task:
|
| 25 |
name: TAG
|
| 26 |
type: token-classification
|
| 27 |
metrics:
|
| 28 |
- name: TAG (XPOS) Accuracy
|
| 29 |
type: accuracy
|
| 30 |
-
value: 0.
|
| 31 |
- task:
|
| 32 |
name: POS
|
| 33 |
type: token-classification
|
| 34 |
metrics:
|
| 35 |
- name: POS (UPOS) Accuracy
|
| 36 |
type: accuracy
|
| 37 |
-
value: 0.
|
| 38 |
- task:
|
| 39 |
name: MORPH
|
| 40 |
type: token-classification
|
| 41 |
metrics:
|
| 42 |
- name: Morph (UFeats) Accuracy
|
| 43 |
type: accuracy
|
| 44 |
-
value: 0.
|
| 45 |
- task:
|
| 46 |
name: LEMMA
|
| 47 |
type: token-classification
|
| 48 |
metrics:
|
| 49 |
- name: Lemma Accuracy
|
| 50 |
type: accuracy
|
| 51 |
-
value: 0.
|
| 52 |
- task:
|
| 53 |
name: UNLABELED_DEPENDENCIES
|
| 54 |
type: token-classification
|
| 55 |
metrics:
|
| 56 |
- name: Unlabeled Attachment Score (UAS)
|
| 57 |
type: f_score
|
| 58 |
-
value: 0.
|
| 59 |
- task:
|
| 60 |
name: LABELED_DEPENDENCIES
|
| 61 |
type: token-classification
|
| 62 |
metrics:
|
| 63 |
- name: Labeled Attachment Score (LAS)
|
| 64 |
type: f_score
|
| 65 |
-
value: 0.
|
| 66 |
- task:
|
| 67 |
name: SENTS
|
| 68 |
type: token-classification
|
| 69 |
metrics:
|
| 70 |
- name: Sentences F-Score
|
| 71 |
type: f_score
|
| 72 |
-
value: 0.
|
| 73 |
---
|
| 74 |
### Details: https://spacy.io/models/da#da_core_news_trf
|
| 75 |
|
| 76 |
-
Danish transformer pipeline (
|
| 77 |
|
| 78 |
| Feature | Description |
|
| 79 |
| --- | --- |
|
| 80 |
| **Name** | `da_core_news_trf` |
|
| 81 |
-
| **Version** | `3.
|
| 82 |
-
| **spaCy** | `>=3.
|
| 83 |
| **Default Pipeline** | `transformer`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
|
| 84 |
| **Components** | `transformer`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
|
| 85 |
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
|
| 86 |
-
| **Sources** | [UD Danish DDT v2.8](https://github.com/UniversalDependencies/UD_Danish-DDT) (Johannsen, Anders; Martínez Alonso, Héctor; Plank, Barbara)<br />[DaNE](https://github.com/alexandrainst/danlp/blob/master/docs/datasets.md#danish-dependency-treebank-dane) (Rasmus Hvingelby, Amalie B. Pauli, Maria Barrett, Christina Rosted, Lasse M. Lidegaard, Anders Søgaard)<br />[
|
| 87 |
| **License** | `CC BY-SA 4.0` |
|
| 88 |
| **Author** | [Explosion](https://explosion.ai) |
|
| 89 |
|
|
@@ -109,18 +109,18 @@ Danish transformer pipeline (Maltehb/danish-bert-botxo). Components: transformer
|
|
| 109 |
| `TOKEN_P` | 99.78 |
|
| 110 |
| `TOKEN_R` | 99.75 |
|
| 111 |
| `TOKEN_F` | 99.76 |
|
| 112 |
-
| `POS_ACC` |
|
| 113 |
-
| `MORPH_ACC` |
|
| 114 |
-
| `MORPH_MICRO_P` |
|
| 115 |
-
| `MORPH_MICRO_R` |
|
| 116 |
-
| `MORPH_MICRO_F` | 98.
|
| 117 |
-
| `SENTS_P` |
|
| 118 |
-
| `SENTS_R` |
|
| 119 |
-
| `SENTS_F` |
|
| 120 |
-
| `DEP_UAS` |
|
| 121 |
-
| `DEP_LAS` |
|
| 122 |
-
| `LEMMA_ACC` |
|
| 123 |
-
| `TAG_ACC` |
|
| 124 |
-
| `ENTS_P` |
|
| 125 |
-
| `ENTS_R` |
|
| 126 |
-
| `ENTS_F` |
|
|
|
|
| 14 |
metrics:
|
| 15 |
- name: NER Precision
|
| 16 |
type: precision
|
| 17 |
+
value: 0.8585657371
|
| 18 |
- name: NER Recall
|
| 19 |
type: recall
|
| 20 |
+
value: 0.8979166667
|
| 21 |
- name: NER F Score
|
| 22 |
type: f_score
|
| 23 |
+
value: 0.8778004073
|
| 24 |
- task:
|
| 25 |
name: TAG
|
| 26 |
type: token-classification
|
| 27 |
metrics:
|
| 28 |
- name: TAG (XPOS) Accuracy
|
| 29 |
type: accuracy
|
| 30 |
+
value: 0.9831444348
|
| 31 |
- task:
|
| 32 |
name: POS
|
| 33 |
type: token-classification
|
| 34 |
metrics:
|
| 35 |
- name: POS (UPOS) Accuracy
|
| 36 |
type: accuracy
|
| 37 |
+
value: 0.9831444348
|
| 38 |
- task:
|
| 39 |
name: MORPH
|
| 40 |
type: token-classification
|
| 41 |
metrics:
|
| 42 |
- name: Morph (UFeats) Accuracy
|
| 43 |
type: accuracy
|
| 44 |
+
value: 0.9809164003
|
| 45 |
- task:
|
| 46 |
name: LEMMA
|
| 47 |
type: token-classification
|
| 48 |
metrics:
|
| 49 |
- name: Lemma Accuracy
|
| 50 |
type: accuracy
|
| 51 |
+
value: 0.9515738499
|
| 52 |
- task:
|
| 53 |
name: UNLABELED_DEPENDENCIES
|
| 54 |
type: token-classification
|
| 55 |
metrics:
|
| 56 |
- name: Unlabeled Attachment Score (UAS)
|
| 57 |
type: f_score
|
| 58 |
+
value: 0.8842458101
|
| 59 |
- task:
|
| 60 |
name: LABELED_DEPENDENCIES
|
| 61 |
type: token-classification
|
| 62 |
metrics:
|
| 63 |
- name: Labeled Attachment Score (LAS)
|
| 64 |
type: f_score
|
| 65 |
+
value: 0.8566640599
|
| 66 |
- task:
|
| 67 |
name: SENTS
|
| 68 |
type: token-classification
|
| 69 |
metrics:
|
| 70 |
- name: Sentences F-Score
|
| 71 |
type: f_score
|
| 72 |
+
value: 0.9494232476
|
| 73 |
---
|
| 74 |
### Details: https://spacy.io/models/da#da_core_news_trf
|
| 75 |
|
| 76 |
+
Danish transformer pipeline (vesteinn/DanskBERT). Components: transformer, morphologizer, parser, lemmatizer (trainable_lemmatizer), ner, attribute_ruler.
|
| 77 |
|
| 78 |
| Feature | Description |
|
| 79 |
| --- | --- |
|
| 80 |
| **Name** | `da_core_news_trf` |
|
| 81 |
+
| **Version** | `3.6.1` |
|
| 82 |
+
| **spaCy** | `>=3.6.0,<3.7.0` |
|
| 83 |
| **Default Pipeline** | `transformer`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
|
| 84 |
| **Components** | `transformer`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
|
| 85 |
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
|
| 86 |
+
| **Sources** | [UD Danish DDT v2.8](https://github.com/UniversalDependencies/UD_Danish-DDT) (Johannsen, Anders; Martínez Alonso, Héctor; Plank, Barbara)<br />[DaNE](https://github.com/alexandrainst/danlp/blob/master/docs/datasets.md#danish-dependency-treebank-dane) (Rasmus Hvingelby, Amalie B. Pauli, Maria Barrett, Christina Rosted, Lasse M. Lidegaard, Anders Søgaard)<br />[vesteinn/DanskBERT](https://huggingface.co/vesteinn/DanskBERT) (Snæbjarnarson, Vésteinn and Simonsen, Annika and Glavaš, Goran and Vulić, Ivan) |
|
| 87 |
| **License** | `CC BY-SA 4.0` |
|
| 88 |
| **Author** | [Explosion](https://explosion.ai) |
|
| 89 |
|
|
|
|
| 109 |
| `TOKEN_P` | 99.78 |
|
| 110 |
| `TOKEN_R` | 99.75 |
|
| 111 |
| `TOKEN_F` | 99.76 |
|
| 112 |
+
| `POS_ACC` | 98.31 |
|
| 113 |
+
| `MORPH_ACC` | 98.09 |
|
| 114 |
+
| `MORPH_MICRO_P` | 99.07 |
|
| 115 |
+
| `MORPH_MICRO_R` | 98.72 |
|
| 116 |
+
| `MORPH_MICRO_F` | 98.90 |
|
| 117 |
+
| `SENTS_P` | 95.03 |
|
| 118 |
+
| `SENTS_R` | 94.86 |
|
| 119 |
+
| `SENTS_F` | 94.94 |
|
| 120 |
+
| `DEP_UAS` | 88.42 |
|
| 121 |
+
| `DEP_LAS` | 85.67 |
|
| 122 |
+
| `LEMMA_ACC` | 95.16 |
|
| 123 |
+
| `TAG_ACC` | 98.31 |
|
| 124 |
+
| `ENTS_P` | 85.86 |
|
| 125 |
+
| `ENTS_R` | 89.79 |
|
| 126 |
+
| `ENTS_F` | 87.78 |
|
accuracy.json
CHANGED
|
@@ -3,81 +3,81 @@
|
|
| 3 |
"token_p": 0.9977732598,
|
| 4 |
"token_r": 0.9974835463,
|
| 5 |
"token_f": 0.997628382,
|
| 6 |
-
"pos_acc": 0.
|
| 7 |
-
"morph_acc": 0.
|
| 8 |
-
"morph_micro_p": 0.
|
| 9 |
-
"morph_micro_r": 0.
|
| 10 |
-
"morph_micro_f": 0.
|
| 11 |
"morph_per_feat": {
|
| 12 |
"Mood": {
|
| 13 |
-
"p": 0.
|
| 14 |
-
"r": 0.
|
| 15 |
-
"f": 0.
|
| 16 |
},
|
| 17 |
"Tense": {
|
| 18 |
-
"p": 0.
|
| 19 |
-
"r": 0.
|
| 20 |
-
"f": 0.
|
| 21 |
},
|
| 22 |
"VerbForm": {
|
| 23 |
-
"p": 0.
|
| 24 |
-
"r": 0.
|
| 25 |
-
"f": 0.
|
| 26 |
},
|
| 27 |
"Voice": {
|
| 28 |
-
"p": 0.
|
| 29 |
-
"r": 0.
|
| 30 |
-
"f": 0.
|
| 31 |
},
|
| 32 |
"Definite": {
|
| 33 |
-
"p": 0.
|
| 34 |
-
"r": 0.
|
| 35 |
-
"f": 0.
|
| 36 |
},
|
| 37 |
"Gender": {
|
| 38 |
-
"p": 0.
|
| 39 |
-
"r": 0.
|
| 40 |
-
"f": 0.
|
| 41 |
},
|
| 42 |
"Number": {
|
| 43 |
-
"p": 0.
|
| 44 |
-
"r": 0.
|
| 45 |
-
"f": 0.
|
| 46 |
},
|
| 47 |
"AdpType": {
|
| 48 |
-
"p": 0.
|
| 49 |
-
"r": 0.
|
| 50 |
-
"f": 0.
|
| 51 |
},
|
| 52 |
"PartType": {
|
| 53 |
"p": 1.0,
|
| 54 |
-
"r": 0
|
| 55 |
-
"f": 0
|
| 56 |
},
|
| 57 |
"Case": {
|
| 58 |
-
"p": 0.
|
| 59 |
-
"r": 0.
|
| 60 |
-
"f": 0.
|
| 61 |
},
|
| 62 |
"Person": {
|
| 63 |
-
"p": 0.
|
| 64 |
-
"r": 0.
|
| 65 |
-
"f": 0.
|
| 66 |
},
|
| 67 |
"PronType": {
|
| 68 |
-
"p": 0.
|
| 69 |
-
"r": 0.
|
| 70 |
-
"f": 0.
|
| 71 |
},
|
| 72 |
"NumType": {
|
| 73 |
-
"p": 0.
|
| 74 |
-
"r": 0.
|
| 75 |
-
"f": 0.
|
| 76 |
},
|
| 77 |
"Degree": {
|
| 78 |
-
"p": 0.
|
| 79 |
-
"r": 0.
|
| 80 |
-
"f": 0.
|
| 81 |
},
|
| 82 |
"Reflex": {
|
| 83 |
"p": 1.0,
|
|
@@ -85,14 +85,14 @@
|
|
| 85 |
"f": 1.0
|
| 86 |
},
|
| 87 |
"Number[psor]": {
|
| 88 |
-
"p": 0.
|
| 89 |
"r": 0.988372093,
|
| 90 |
-
"f": 0.
|
| 91 |
},
|
| 92 |
"Poss": {
|
| 93 |
-
"p":
|
| 94 |
"r": 0.9886363636,
|
| 95 |
-
"f": 0.
|
| 96 |
},
|
| 97 |
"Foreign": {
|
| 98 |
"p": 0.8571428571,
|
|
@@ -110,146 +110,146 @@
|
|
| 110 |
"f": 1.0
|
| 111 |
},
|
| 112 |
"Polite": {
|
| 113 |
-
"p":
|
| 114 |
-
"r":
|
| 115 |
-
"f":
|
| 116 |
}
|
| 117 |
},
|
| 118 |
-
"sents_p": 0.
|
| 119 |
-
"sents_r": 0.
|
| 120 |
-
"sents_f": 0.
|
| 121 |
-
"dep_uas": 0.
|
| 122 |
-
"dep_las": 0.
|
| 123 |
"dep_las_per_type": {
|
| 124 |
"advmod": {
|
| 125 |
-
"p": 0.
|
| 126 |
-
"r": 0.
|
| 127 |
-
"f": 0.
|
| 128 |
},
|
| 129 |
"root": {
|
| 130 |
-
"p": 0.
|
| 131 |
-
"r": 0.
|
| 132 |
-
"f": 0.
|
| 133 |
},
|
| 134 |
"nsubj": {
|
| 135 |
-
"p": 0.
|
| 136 |
-
"r": 0.
|
| 137 |
-
"f": 0.
|
| 138 |
},
|
| 139 |
"case": {
|
| 140 |
-
"p": 0.
|
| 141 |
-
"r": 0.
|
| 142 |
-
"f": 0.
|
| 143 |
},
|
| 144 |
"obl": {
|
| 145 |
-
"p": 0.
|
| 146 |
-
"r": 0.
|
| 147 |
-
"f": 0.
|
| 148 |
},
|
| 149 |
"cc": {
|
| 150 |
-
"p": 0.
|
| 151 |
-
"r": 0.
|
| 152 |
-
"f": 0.
|
| 153 |
},
|
| 154 |
"conj": {
|
| 155 |
-
"p": 0.
|
| 156 |
-
"r": 0.
|
| 157 |
-
"f": 0.
|
| 158 |
},
|
| 159 |
"obj": {
|
| 160 |
-
"p": 0.
|
| 161 |
-
"r": 0.
|
| 162 |
-
"f": 0.
|
| 163 |
},
|
| 164 |
"aux": {
|
| 165 |
-
"p": 0.
|
| 166 |
-
"r": 0.
|
| 167 |
-
"f": 0.
|
| 168 |
},
|
| 169 |
"acl:relcl": {
|
| 170 |
-
"p": 0.
|
| 171 |
-
"r": 0.
|
| 172 |
-
"f": 0.
|
| 173 |
},
|
| 174 |
"advmod:lmod": {
|
| 175 |
-
"p": 0.
|
| 176 |
-
"r": 0.
|
| 177 |
-
"f": 0.
|
| 178 |
},
|
| 179 |
"det": {
|
| 180 |
-
"p": 0.
|
| 181 |
-
"r": 0.
|
| 182 |
-
"f": 0.
|
| 183 |
},
|
| 184 |
"amod": {
|
| 185 |
-
"p": 0.
|
| 186 |
-
"r": 0.
|
| 187 |
-
"f": 0.
|
| 188 |
},
|
| 189 |
"nmod:poss": {
|
| 190 |
-
"p": 0.
|
| 191 |
-
"r": 0.
|
| 192 |
-
"f": 0.
|
| 193 |
},
|
| 194 |
"ccomp": {
|
| 195 |
-
"p": 0.
|
| 196 |
-
"r": 0.
|
| 197 |
-
"f": 0.
|
| 198 |
},
|
| 199 |
"nummod": {
|
| 200 |
-
"p": 0.
|
| 201 |
-
"r": 0.
|
| 202 |
-
"f": 0.
|
| 203 |
},
|
| 204 |
"flat": {
|
| 205 |
-
"p": 0.
|
| 206 |
"r": 0.9139072848,
|
| 207 |
-
"f": 0.
|
| 208 |
},
|
| 209 |
"compound:prt": {
|
| 210 |
-
"p": 0.
|
| 211 |
-
"r": 0.
|
| 212 |
-
"f": 0.
|
| 213 |
},
|
| 214 |
"advcl": {
|
| 215 |
-
"p": 0.
|
| 216 |
-
"r": 0.
|
| 217 |
-
"f": 0.
|
| 218 |
},
|
| 219 |
"mark": {
|
| 220 |
-
"p": 0.
|
| 221 |
-
"r": 0.
|
| 222 |
-
"f": 0.
|
| 223 |
},
|
| 224 |
"cop": {
|
| 225 |
-
"p": 0.
|
| 226 |
-
"r": 0.
|
| 227 |
-
"f": 0.
|
| 228 |
},
|
| 229 |
"dep": {
|
| 230 |
-
"p": 0.
|
| 231 |
-
"r": 0.
|
| 232 |
-
"f": 0.
|
| 233 |
},
|
| 234 |
"nmod": {
|
| 235 |
-
"p": 0.
|
| 236 |
-
"r": 0.
|
| 237 |
-
"f": 0.
|
| 238 |
},
|
| 239 |
"iobj": {
|
| 240 |
-
"p": 0.
|
| 241 |
-
"r": 0.
|
| 242 |
-
"f": 0.
|
| 243 |
},
|
| 244 |
"xcomp": {
|
| 245 |
-
"p": 0.
|
| 246 |
-
"r": 0.
|
| 247 |
-
"f": 0.
|
| 248 |
},
|
| 249 |
"list": {
|
| 250 |
-
"p": 0.
|
| 251 |
-
"r": 0.
|
| 252 |
-
"f": 0.
|
| 253 |
},
|
| 254 |
"vocative": {
|
| 255 |
"p": 0.0,
|
|
@@ -257,24 +257,24 @@
|
|
| 257 |
"f": 0.0
|
| 258 |
},
|
| 259 |
"fixed": {
|
| 260 |
-
"p": 0.
|
| 261 |
-
"r": 0.
|
| 262 |
-
"f": 0.
|
| 263 |
},
|
| 264 |
"expl": {
|
| 265 |
-
"p": 0.
|
| 266 |
"r": 0.9117647059,
|
| 267 |
-
"f": 0.
|
| 268 |
},
|
| 269 |
"appos": {
|
| 270 |
-
"p": 0.
|
| 271 |
-
"r": 0.
|
| 272 |
-
"f": 0.
|
| 273 |
},
|
| 274 |
"obl:tmod": {
|
| 275 |
-
"p": 0.
|
| 276 |
-
"r": 0.
|
| 277 |
-
"f": 0.
|
| 278 |
},
|
| 279 |
"discourse": {
|
| 280 |
"p": 0.0,
|
|
@@ -287,32 +287,32 @@
|
|
| 287 |
"f": 0.0
|
| 288 |
}
|
| 289 |
},
|
| 290 |
-
"lemma_acc": 0.
|
| 291 |
-
"tag_acc": 0.
|
| 292 |
-
"ents_p": 0.
|
| 293 |
-
"ents_r": 0.
|
| 294 |
-
"ents_f": 0.
|
| 295 |
"ents_per_type": {
|
| 296 |
"PER": {
|
| 297 |
-
"p": 0.
|
| 298 |
-
"r": 0.
|
| 299 |
-
"f": 0.
|
| 300 |
},
|
| 301 |
"ORG": {
|
| 302 |
-
"p": 0.
|
| 303 |
-
"r": 0.
|
| 304 |
-
"f": 0.
|
| 305 |
},
|
| 306 |
"MISC": {
|
| 307 |
-
"p": 0.
|
| 308 |
-
"r": 0.
|
| 309 |
-
"f": 0.
|
| 310 |
},
|
| 311 |
"LOC": {
|
| 312 |
-
"p": 0.
|
| 313 |
-
"r": 0.
|
| 314 |
-
"f": 0.
|
| 315 |
}
|
| 316 |
},
|
| 317 |
-
"speed":
|
| 318 |
}
|
|
|
|
| 3 |
"token_p": 0.9977732598,
|
| 4 |
"token_r": 0.9974835463,
|
| 5 |
"token_f": 0.997628382,
|
| 6 |
+
"pos_acc": 0.9831444348,
|
| 7 |
+
"morph_acc": 0.9809164003,
|
| 8 |
+
"morph_micro_p": 0.9907294833,
|
| 9 |
+
"morph_micro_r": 0.98717884,
|
| 10 |
+
"morph_micro_f": 0.9889509747,
|
| 11 |
"morph_per_feat": {
|
| 12 |
"Mood": {
|
| 13 |
+
"p": 0.9961795606,
|
| 14 |
+
"r": 0.9942802669,
|
| 15 |
+
"f": 0.9952290076
|
| 16 |
},
|
| 17 |
"Tense": {
|
| 18 |
+
"p": 0.9872372372,
|
| 19 |
+
"r": 0.9902108434,
|
| 20 |
+
"f": 0.9887218045
|
| 21 |
},
|
| 22 |
"VerbForm": {
|
| 23 |
+
"p": 0.9883792049,
|
| 24 |
+
"r": 0.9889840881,
|
| 25 |
+
"f": 0.988681554
|
| 26 |
},
|
| 27 |
"Voice": {
|
| 28 |
+
"p": 0.996257485,
|
| 29 |
+
"r": 0.9947683109,
|
| 30 |
+
"f": 0.9955123411
|
| 31 |
},
|
| 32 |
"Definite": {
|
| 33 |
+
"p": 0.9912490056,
|
| 34 |
+
"r": 0.9845910707,
|
| 35 |
+
"f": 0.9879088206
|
| 36 |
},
|
| 37 |
"Gender": {
|
| 38 |
+
"p": 0.9859906604,
|
| 39 |
+
"r": 0.9823861748,
|
| 40 |
+
"f": 0.9841851174
|
| 41 |
},
|
| 42 |
"Number": {
|
| 43 |
+
"p": 0.9895260539,
|
| 44 |
+
"r": 0.9856546688,
|
| 45 |
+
"f": 0.9875865674
|
| 46 |
},
|
| 47 |
"AdpType": {
|
| 48 |
+
"p": 0.9982190561,
|
| 49 |
+
"r": 0.991158267,
|
| 50 |
+
"f": 0.9946761313
|
| 51 |
},
|
| 52 |
"PartType": {
|
| 53 |
"p": 1.0,
|
| 54 |
+
"r": 1.0,
|
| 55 |
+
"f": 1.0
|
| 56 |
},
|
| 57 |
"Case": {
|
| 58 |
+
"p": 0.9952305246,
|
| 59 |
+
"r": 0.9889415482,
|
| 60 |
+
"f": 0.9920760697
|
| 61 |
},
|
| 62 |
"Person": {
|
| 63 |
+
"p": 0.9946808511,
|
| 64 |
+
"r": 0.9964476021,
|
| 65 |
+
"f": 0.9955634428
|
| 66 |
},
|
| 67 |
"PronType": {
|
| 68 |
+
"p": 0.9942434211,
|
| 69 |
+
"r": 0.9942434211,
|
| 70 |
+
"f": 0.9942434211
|
| 71 |
},
|
| 72 |
"NumType": {
|
| 73 |
+
"p": 0.972972973,
|
| 74 |
+
"r": 0.9536423841,
|
| 75 |
+
"f": 0.9632107023
|
| 76 |
},
|
| 77 |
"Degree": {
|
| 78 |
+
"p": 0.9853836784,
|
| 79 |
+
"r": 0.9746987952,
|
| 80 |
+
"f": 0.9800121139
|
| 81 |
},
|
| 82 |
"Reflex": {
|
| 83 |
"p": 1.0,
|
|
|
|
| 85 |
"f": 1.0
|
| 86 |
},
|
| 87 |
"Number[psor]": {
|
| 88 |
+
"p": 0.988372093,
|
| 89 |
"r": 0.988372093,
|
| 90 |
+
"f": 0.988372093
|
| 91 |
},
|
| 92 |
"Poss": {
|
| 93 |
+
"p": 0.9886363636,
|
| 94 |
"r": 0.9886363636,
|
| 95 |
+
"f": 0.9886363636
|
| 96 |
},
|
| 97 |
"Foreign": {
|
| 98 |
"p": 0.8571428571,
|
|
|
|
| 110 |
"f": 1.0
|
| 111 |
},
|
| 112 |
"Polite": {
|
| 113 |
+
"p": 1.0,
|
| 114 |
+
"r": 1.0,
|
| 115 |
+
"f": 1.0
|
| 116 |
}
|
| 117 |
},
|
| 118 |
+
"sents_p": 0.9502664298,
|
| 119 |
+
"sents_r": 0.9485815603,
|
| 120 |
+
"sents_f": 0.9494232476,
|
| 121 |
+
"dep_uas": 0.8842458101,
|
| 122 |
+
"dep_las": 0.8566640599,
|
| 123 |
"dep_las_per_type": {
|
| 124 |
"advmod": {
|
| 125 |
+
"p": 0.8081232493,
|
| 126 |
+
"r": 0.8149717514,
|
| 127 |
+
"f": 0.811533052
|
| 128 |
},
|
| 129 |
"root": {
|
| 130 |
+
"p": 0.8989361702,
|
| 131 |
+
"r": 0.8989361702,
|
| 132 |
+
"f": 0.8989361702
|
| 133 |
},
|
| 134 |
"nsubj": {
|
| 135 |
+
"p": 0.9171907757,
|
| 136 |
+
"r": 0.9229957806,
|
| 137 |
+
"f": 0.920084122
|
| 138 |
},
|
| 139 |
"case": {
|
| 140 |
+
"p": 0.9323383085,
|
| 141 |
+
"r": 0.9240631164,
|
| 142 |
+
"f": 0.9281822684
|
| 143 |
},
|
| 144 |
"obl": {
|
| 145 |
+
"p": 0.7925696594,
|
| 146 |
+
"r": 0.7950310559,
|
| 147 |
+
"f": 0.7937984496
|
| 148 |
},
|
| 149 |
"cc": {
|
| 150 |
+
"p": 0.8746355685,
|
| 151 |
+
"r": 0.8720930233,
|
| 152 |
+
"f": 0.8733624454
|
| 153 |
},
|
| 154 |
"conj": {
|
| 155 |
+
"p": 0.7639257294,
|
| 156 |
+
"r": 0.768,
|
| 157 |
+
"f": 0.7659574468
|
| 158 |
},
|
| 159 |
"obj": {
|
| 160 |
+
"p": 0.9013282732,
|
| 161 |
+
"r": 0.9223300971,
|
| 162 |
+
"f": 0.9117082534
|
| 163 |
},
|
| 164 |
"aux": {
|
| 165 |
+
"p": 0.9104046243,
|
| 166 |
+
"r": 0.9183673469,
|
| 167 |
+
"f": 0.9143686502
|
| 168 |
},
|
| 169 |
"acl:relcl": {
|
| 170 |
+
"p": 0.7,
|
| 171 |
+
"r": 0.6810810811,
|
| 172 |
+
"f": 0.6904109589
|
| 173 |
},
|
| 174 |
"advmod:lmod": {
|
| 175 |
+
"p": 0.8153846154,
|
| 176 |
+
"r": 0.7910447761,
|
| 177 |
+
"f": 0.803030303
|
| 178 |
},
|
| 179 |
"det": {
|
| 180 |
+
"p": 0.9363784666,
|
| 181 |
+
"r": 0.9456342669,
|
| 182 |
+
"f": 0.9409836066
|
| 183 |
},
|
| 184 |
"amod": {
|
| 185 |
+
"p": 0.8798646362,
|
| 186 |
+
"r": 0.8873720137,
|
| 187 |
+
"f": 0.8836023789
|
| 188 |
},
|
| 189 |
"nmod:poss": {
|
| 190 |
+
"p": 0.7745098039,
|
| 191 |
+
"r": 0.7821782178,
|
| 192 |
+
"f": 0.7783251232
|
| 193 |
},
|
| 194 |
"ccomp": {
|
| 195 |
+
"p": 0.7301587302,
|
| 196 |
+
"r": 0.7419354839,
|
| 197 |
+
"f": 0.736
|
| 198 |
},
|
| 199 |
"nummod": {
|
| 200 |
+
"p": 0.8429752066,
|
| 201 |
+
"r": 0.85,
|
| 202 |
+
"f": 0.846473029
|
| 203 |
},
|
| 204 |
"flat": {
|
| 205 |
+
"p": 0.8625,
|
| 206 |
"r": 0.9139072848,
|
| 207 |
+
"f": 0.8874598071
|
| 208 |
},
|
| 209 |
"compound:prt": {
|
| 210 |
+
"p": 0.6764705882,
|
| 211 |
+
"r": 0.5609756098,
|
| 212 |
+
"f": 0.6133333333
|
| 213 |
},
|
| 214 |
"advcl": {
|
| 215 |
+
"p": 0.7413793103,
|
| 216 |
+
"r": 0.7413793103,
|
| 217 |
+
"f": 0.7413793103
|
| 218 |
},
|
| 219 |
"mark": {
|
| 220 |
+
"p": 0.9173553719,
|
| 221 |
+
"r": 0.9117043121,
|
| 222 |
+
"f": 0.9145211123
|
| 223 |
},
|
| 224 |
"cop": {
|
| 225 |
+
"p": 0.901734104,
|
| 226 |
+
"r": 0.8914285714,
|
| 227 |
+
"f": 0.8965517241
|
| 228 |
},
|
| 229 |
"dep": {
|
| 230 |
+
"p": 0.2307692308,
|
| 231 |
+
"r": 0.3396226415,
|
| 232 |
+
"f": 0.2748091603
|
| 233 |
},
|
| 234 |
"nmod": {
|
| 235 |
+
"p": 0.7693920335,
|
| 236 |
+
"r": 0.716796875,
|
| 237 |
+
"f": 0.7421638018
|
| 238 |
},
|
| 239 |
"iobj": {
|
| 240 |
+
"p": 0.9285714286,
|
| 241 |
+
"r": 0.5909090909,
|
| 242 |
+
"f": 0.7222222222
|
| 243 |
},
|
| 244 |
"xcomp": {
|
| 245 |
+
"p": 0.6595744681,
|
| 246 |
+
"r": 0.5254237288,
|
| 247 |
+
"f": 0.5849056604
|
| 248 |
},
|
| 249 |
"list": {
|
| 250 |
+
"p": 0.5,
|
| 251 |
+
"r": 0.4444444444,
|
| 252 |
+
"f": 0.4705882353
|
| 253 |
},
|
| 254 |
"vocative": {
|
| 255 |
"p": 0.0,
|
|
|
|
| 257 |
"f": 0.0
|
| 258 |
},
|
| 259 |
"fixed": {
|
| 260 |
+
"p": 0.9210526316,
|
| 261 |
+
"r": 0.8536585366,
|
| 262 |
+
"f": 0.8860759494
|
| 263 |
},
|
| 264 |
"expl": {
|
| 265 |
+
"p": 0.9393939394,
|
| 266 |
"r": 0.9117647059,
|
| 267 |
+
"f": 0.9253731343
|
| 268 |
},
|
| 269 |
"appos": {
|
| 270 |
+
"p": 0.6315789474,
|
| 271 |
+
"r": 0.7272727273,
|
| 272 |
+
"f": 0.676056338
|
| 273 |
},
|
| 274 |
"obl:tmod": {
|
| 275 |
+
"p": 0.7272727273,
|
| 276 |
+
"r": 0.4444444444,
|
| 277 |
+
"f": 0.5517241379
|
| 278 |
},
|
| 279 |
"discourse": {
|
| 280 |
"p": 0.0,
|
|
|
|
| 287 |
"f": 0.0
|
| 288 |
}
|
| 289 |
},
|
| 290 |
+
"lemma_acc": 0.9515738499,
|
| 291 |
+
"tag_acc": 0.9831444348,
|
| 292 |
+
"ents_p": 0.8585657371,
|
| 293 |
+
"ents_r": 0.8979166667,
|
| 294 |
+
"ents_f": 0.8778004073,
|
| 295 |
"ents_per_type": {
|
| 296 |
"PER": {
|
| 297 |
+
"p": 0.9493670886,
|
| 298 |
+
"r": 0.9036144578,
|
| 299 |
+
"f": 0.9259259259
|
| 300 |
},
|
| 301 |
"ORG": {
|
| 302 |
+
"p": 0.8720930233,
|
| 303 |
+
"r": 0.8333333333,
|
| 304 |
+
"f": 0.8522727273
|
| 305 |
},
|
| 306 |
"MISC": {
|
| 307 |
+
"p": 0.7163120567,
|
| 308 |
+
"r": 0.8938053097,
|
| 309 |
+
"f": 0.7952755906
|
| 310 |
},
|
| 311 |
"LOC": {
|
| 312 |
+
"p": 0.8974358974,
|
| 313 |
+
"r": 0.9459459459,
|
| 314 |
+
"f": 0.9210526316
|
| 315 |
}
|
| 316 |
},
|
| 317 |
+
"speed": 655.5887888543
|
| 318 |
}
|
config.cfg
CHANGED
|
@@ -47,6 +47,7 @@ pooling = {"@layers":"reduce_mean.v1"}
|
|
| 47 |
[components.morphologizer]
|
| 48 |
factory = "morphologizer"
|
| 49 |
extend = false
|
|
|
|
| 50 |
overwrite = true
|
| 51 |
scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
|
| 52 |
|
|
@@ -112,8 +113,8 @@ max_batch_items = 4096
|
|
| 112 |
set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
|
| 113 |
|
| 114 |
[components.transformer.model]
|
|
|
|
| 115 |
@architectures = "spacy-transformers.TransformerModel.v3"
|
| 116 |
-
name = "Maltehb/danish-bert-botxo"
|
| 117 |
mixed_precision = false
|
| 118 |
|
| 119 |
[components.transformer.model.get_spans]
|
|
|
|
| 47 |
[components.morphologizer]
|
| 48 |
factory = "morphologizer"
|
| 49 |
extend = false
|
| 50 |
+
label_smoothing = 0.0
|
| 51 |
overwrite = true
|
| 52 |
scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
|
| 53 |
|
|
|
|
| 113 |
set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
|
| 114 |
|
| 115 |
[components.transformer.model]
|
| 116 |
+
name = "vesteinn/DanskBERT"
|
| 117 |
@architectures = "spacy-transformers.TransformerModel.v3"
|
|
|
|
| 118 |
mixed_precision = false
|
| 119 |
|
| 120 |
[components.transformer.model.get_spans]
|
da_core_news_trf-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 sha256:46cbd7cbcfa6a575e98ffd709ff7479612d2881978bc276576553dc47fd2fe72
|
| 3 |
+
size 444187820
|
lemmatizer/model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1391005
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15284a67182922c447cf06f6058ce3fcaedc76b663173da4c7e726727647cea0
|
| 3 |
size 1391005
|
meta.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"lang":"da",
|
| 3 |
"name":"core_news_trf",
|
| 4 |
-
"version":"3.
|
| 5 |
-
"description":"Danish transformer pipeline (
|
| 6 |
"author":"Explosion",
|
| 7 |
"email":"[email protected]",
|
| 8 |
"url":"https://explosion.ai",
|
| 9 |
"license":"CC BY-SA 4.0",
|
| 10 |
-
"spacy_version":">=3.
|
| 11 |
-
"spacy_git_version":"
|
| 12 |
"vectors":{
|
| 13 |
"width":0,
|
| 14 |
"vectors":0,
|
|
@@ -246,81 +246,81 @@
|
|
| 246 |
"token_p":0.9977732598,
|
| 247 |
"token_r":0.9974835463,
|
| 248 |
"token_f":0.997628382,
|
| 249 |
-
"pos_acc":0.
|
| 250 |
-
"morph_acc":0.
|
| 251 |
-
"morph_micro_p":0.
|
| 252 |
-
"morph_micro_r":0.
|
| 253 |
-
"morph_micro_f":0.
|
| 254 |
"morph_per_feat":{
|
| 255 |
"Mood":{
|
| 256 |
-
"p":0.
|
| 257 |
-
"r":0.
|
| 258 |
-
"f":0.
|
| 259 |
},
|
| 260 |
"Tense":{
|
| 261 |
-
"p":0.
|
| 262 |
-
"r":0.
|
| 263 |
-
"f":0.
|
| 264 |
},
|
| 265 |
"VerbForm":{
|
| 266 |
-
"p":0.
|
| 267 |
-
"r":0.
|
| 268 |
-
"f":0.
|
| 269 |
},
|
| 270 |
"Voice":{
|
| 271 |
-
"p":0.
|
| 272 |
-
"r":0.
|
| 273 |
-
"f":0.
|
| 274 |
},
|
| 275 |
"Definite":{
|
| 276 |
-
"p":0.
|
| 277 |
-
"r":0.
|
| 278 |
-
"f":0.
|
| 279 |
},
|
| 280 |
"Gender":{
|
| 281 |
-
"p":0.
|
| 282 |
-
"r":0.
|
| 283 |
-
"f":0.
|
| 284 |
},
|
| 285 |
"Number":{
|
| 286 |
-
"p":0.
|
| 287 |
-
"r":0.
|
| 288 |
-
"f":0.
|
| 289 |
},
|
| 290 |
"AdpType":{
|
| 291 |
-
"p":0.
|
| 292 |
-
"r":0.
|
| 293 |
-
"f":0.
|
| 294 |
},
|
| 295 |
"PartType":{
|
| 296 |
"p":1.0,
|
| 297 |
-
"r":0
|
| 298 |
-
"f":0
|
| 299 |
},
|
| 300 |
"Case":{
|
| 301 |
-
"p":0.
|
| 302 |
-
"r":0.
|
| 303 |
-
"f":0.
|
| 304 |
},
|
| 305 |
"Person":{
|
| 306 |
-
"p":0.
|
| 307 |
-
"r":0.
|
| 308 |
-
"f":0.
|
| 309 |
},
|
| 310 |
"PronType":{
|
| 311 |
-
"p":0.
|
| 312 |
-
"r":0.
|
| 313 |
-
"f":0.
|
| 314 |
},
|
| 315 |
"NumType":{
|
| 316 |
-
"p":0.
|
| 317 |
-
"r":0.
|
| 318 |
-
"f":0.
|
| 319 |
},
|
| 320 |
"Degree":{
|
| 321 |
-
"p":0.
|
| 322 |
-
"r":0.
|
| 323 |
-
"f":0.
|
| 324 |
},
|
| 325 |
"Reflex":{
|
| 326 |
"p":1.0,
|
|
@@ -328,14 +328,14 @@
|
|
| 328 |
"f":1.0
|
| 329 |
},
|
| 330 |
"Number[psor]":{
|
| 331 |
-
"p":0.
|
| 332 |
"r":0.988372093,
|
| 333 |
-
"f":0.
|
| 334 |
},
|
| 335 |
"Poss":{
|
| 336 |
-
"p":
|
| 337 |
"r":0.9886363636,
|
| 338 |
-
"f":0.
|
| 339 |
},
|
| 340 |
"Foreign":{
|
| 341 |
"p":0.8571428571,
|
|
@@ -353,146 +353,146 @@
|
|
| 353 |
"f":1.0
|
| 354 |
},
|
| 355 |
"Polite":{
|
| 356 |
-
"p":
|
| 357 |
-
"r":
|
| 358 |
-
"f":
|
| 359 |
}
|
| 360 |
},
|
| 361 |
-
"sents_p":0.
|
| 362 |
-
"sents_r":0.
|
| 363 |
-
"sents_f":0.
|
| 364 |
-
"dep_uas":0.
|
| 365 |
-
"dep_las":0.
|
| 366 |
"dep_las_per_type":{
|
| 367 |
"advmod":{
|
| 368 |
-
"p":0.
|
| 369 |
-
"r":0.
|
| 370 |
-
"f":0.
|
| 371 |
},
|
| 372 |
"root":{
|
| 373 |
-
"p":0.
|
| 374 |
-
"r":0.
|
| 375 |
-
"f":0.
|
| 376 |
},
|
| 377 |
"nsubj":{
|
| 378 |
-
"p":0.
|
| 379 |
-
"r":0.
|
| 380 |
-
"f":0.
|
| 381 |
},
|
| 382 |
"case":{
|
| 383 |
-
"p":0.
|
| 384 |
-
"r":0.
|
| 385 |
-
"f":0.
|
| 386 |
},
|
| 387 |
"obl":{
|
| 388 |
-
"p":0.
|
| 389 |
-
"r":0.
|
| 390 |
-
"f":0.
|
| 391 |
},
|
| 392 |
"cc":{
|
| 393 |
-
"p":0.
|
| 394 |
-
"r":0.
|
| 395 |
-
"f":0.
|
| 396 |
},
|
| 397 |
"conj":{
|
| 398 |
-
"p":0.
|
| 399 |
-
"r":0.
|
| 400 |
-
"f":0.
|
| 401 |
},
|
| 402 |
"obj":{
|
| 403 |
-
"p":0.
|
| 404 |
-
"r":0.
|
| 405 |
-
"f":0.
|
| 406 |
},
|
| 407 |
"aux":{
|
| 408 |
-
"p":0.
|
| 409 |
-
"r":0.
|
| 410 |
-
"f":0.
|
| 411 |
},
|
| 412 |
"acl:relcl":{
|
| 413 |
-
"p":0.
|
| 414 |
-
"r":0.
|
| 415 |
-
"f":0.
|
| 416 |
},
|
| 417 |
"advmod:lmod":{
|
| 418 |
-
"p":0.
|
| 419 |
-
"r":0.
|
| 420 |
-
"f":0.
|
| 421 |
},
|
| 422 |
"det":{
|
| 423 |
-
"p":0.
|
| 424 |
-
"r":0.
|
| 425 |
-
"f":0.
|
| 426 |
},
|
| 427 |
"amod":{
|
| 428 |
-
"p":0.
|
| 429 |
-
"r":0.
|
| 430 |
-
"f":0.
|
| 431 |
},
|
| 432 |
"nmod:poss":{
|
| 433 |
-
"p":0.
|
| 434 |
-
"r":0.
|
| 435 |
-
"f":0.
|
| 436 |
},
|
| 437 |
"ccomp":{
|
| 438 |
-
"p":0.
|
| 439 |
-
"r":0.
|
| 440 |
-
"f":0.
|
| 441 |
},
|
| 442 |
"nummod":{
|
| 443 |
-
"p":0.
|
| 444 |
-
"r":0.
|
| 445 |
-
"f":0.
|
| 446 |
},
|
| 447 |
"flat":{
|
| 448 |
-
"p":0.
|
| 449 |
"r":0.9139072848,
|
| 450 |
-
"f":0.
|
| 451 |
},
|
| 452 |
"compound:prt":{
|
| 453 |
-
"p":0.
|
| 454 |
-
"r":0.
|
| 455 |
-
"f":0.
|
| 456 |
},
|
| 457 |
"advcl":{
|
| 458 |
-
"p":0.
|
| 459 |
-
"r":0.
|
| 460 |
-
"f":0.
|
| 461 |
},
|
| 462 |
"mark":{
|
| 463 |
-
"p":0.
|
| 464 |
-
"r":0.
|
| 465 |
-
"f":0.
|
| 466 |
},
|
| 467 |
"cop":{
|
| 468 |
-
"p":0.
|
| 469 |
-
"r":0.
|
| 470 |
-
"f":0.
|
| 471 |
},
|
| 472 |
"dep":{
|
| 473 |
-
"p":0.
|
| 474 |
-
"r":0.
|
| 475 |
-
"f":0.
|
| 476 |
},
|
| 477 |
"nmod":{
|
| 478 |
-
"p":0.
|
| 479 |
-
"r":0.
|
| 480 |
-
"f":0.
|
| 481 |
},
|
| 482 |
"iobj":{
|
| 483 |
-
"p":0.
|
| 484 |
-
"r":0.
|
| 485 |
-
"f":0.
|
| 486 |
},
|
| 487 |
"xcomp":{
|
| 488 |
-
"p":0.
|
| 489 |
-
"r":0.
|
| 490 |
-
"f":0.
|
| 491 |
},
|
| 492 |
"list":{
|
| 493 |
-
"p":0.
|
| 494 |
-
"r":0.
|
| 495 |
-
"f":0.
|
| 496 |
},
|
| 497 |
"vocative":{
|
| 498 |
"p":0.0,
|
|
@@ -500,24 +500,24 @@
|
|
| 500 |
"f":0.0
|
| 501 |
},
|
| 502 |
"fixed":{
|
| 503 |
-
"p":0.
|
| 504 |
-
"r":0.
|
| 505 |
-
"f":0.
|
| 506 |
},
|
| 507 |
"expl":{
|
| 508 |
-
"p":0.
|
| 509 |
"r":0.9117647059,
|
| 510 |
-
"f":0.
|
| 511 |
},
|
| 512 |
"appos":{
|
| 513 |
-
"p":0.
|
| 514 |
-
"r":0.
|
| 515 |
-
"f":0.
|
| 516 |
},
|
| 517 |
"obl:tmod":{
|
| 518 |
-
"p":0.
|
| 519 |
-
"r":0.
|
| 520 |
-
"f":0.
|
| 521 |
},
|
| 522 |
"discourse":{
|
| 523 |
"p":0.0,
|
|
@@ -530,34 +530,34 @@
|
|
| 530 |
"f":0.0
|
| 531 |
}
|
| 532 |
},
|
| 533 |
-
"lemma_acc":0.
|
| 534 |
-
"tag_acc":0.
|
| 535 |
-
"ents_p":0.
|
| 536 |
-
"ents_r":0.
|
| 537 |
-
"ents_f":0.
|
| 538 |
"ents_per_type":{
|
| 539 |
"PER":{
|
| 540 |
-
"p":0.
|
| 541 |
-
"r":0.
|
| 542 |
-
"f":0.
|
| 543 |
},
|
| 544 |
"ORG":{
|
| 545 |
-
"p":0.
|
| 546 |
-
"r":0.
|
| 547 |
-
"f":0.
|
| 548 |
},
|
| 549 |
"MISC":{
|
| 550 |
-
"p":0.
|
| 551 |
-
"r":0.
|
| 552 |
-
"f":0.
|
| 553 |
},
|
| 554 |
"LOC":{
|
| 555 |
-
"p":0.
|
| 556 |
-
"r":0.
|
| 557 |
-
"f":0.
|
| 558 |
}
|
| 559 |
},
|
| 560 |
-
"speed":
|
| 561 |
},
|
| 562 |
"sources":[
|
| 563 |
{
|
|
@@ -573,13 +573,13 @@
|
|
| 573 |
"author":"Rasmus Hvingelby, Amalie B. Pauli, Maria Barrett, Christina Rosted, Lasse M. Lidegaard, Anders S\u00f8gaard"
|
| 574 |
},
|
| 575 |
{
|
| 576 |
-
"name":"
|
| 577 |
-
"author":"
|
| 578 |
-
"url":"https://huggingface.co/
|
| 579 |
"license":"CC BY 4.0"
|
| 580 |
}
|
| 581 |
],
|
| 582 |
"requirements":[
|
| 583 |
-
"spacy-transformers>=1.2.
|
| 584 |
]
|
| 585 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"lang":"da",
|
| 3 |
"name":"core_news_trf",
|
| 4 |
+
"version":"3.6.1",
|
| 5 |
+
"description":"Danish transformer pipeline (vesteinn/DanskBERT). Components: transformer, morphologizer, parser, lemmatizer (trainable_lemmatizer), ner, attribute_ruler.",
|
| 6 |
"author":"Explosion",
|
| 7 |
"email":"[email protected]",
|
| 8 |
"url":"https://explosion.ai",
|
| 9 |
"license":"CC BY-SA 4.0",
|
| 10 |
+
"spacy_version":">=3.6.0,<3.7.0",
|
| 11 |
+
"spacy_git_version":"c067b5264",
|
| 12 |
"vectors":{
|
| 13 |
"width":0,
|
| 14 |
"vectors":0,
|
|
|
|
| 246 |
"token_p":0.9977732598,
|
| 247 |
"token_r":0.9974835463,
|
| 248 |
"token_f":0.997628382,
|
| 249 |
+
"pos_acc":0.9831444348,
|
| 250 |
+
"morph_acc":0.9809164003,
|
| 251 |
+
"morph_micro_p":0.9907294833,
|
| 252 |
+
"morph_micro_r":0.98717884,
|
| 253 |
+
"morph_micro_f":0.9889509747,
|
| 254 |
"morph_per_feat":{
|
| 255 |
"Mood":{
|
| 256 |
+
"p":0.9961795606,
|
| 257 |
+
"r":0.9942802669,
|
| 258 |
+
"f":0.9952290076
|
| 259 |
},
|
| 260 |
"Tense":{
|
| 261 |
+
"p":0.9872372372,
|
| 262 |
+
"r":0.9902108434,
|
| 263 |
+
"f":0.9887218045
|
| 264 |
},
|
| 265 |
"VerbForm":{
|
| 266 |
+
"p":0.9883792049,
|
| 267 |
+
"r":0.9889840881,
|
| 268 |
+
"f":0.988681554
|
| 269 |
},
|
| 270 |
"Voice":{
|
| 271 |
+
"p":0.996257485,
|
| 272 |
+
"r":0.9947683109,
|
| 273 |
+
"f":0.9955123411
|
| 274 |
},
|
| 275 |
"Definite":{
|
| 276 |
+
"p":0.9912490056,
|
| 277 |
+
"r":0.9845910707,
|
| 278 |
+
"f":0.9879088206
|
| 279 |
},
|
| 280 |
"Gender":{
|
| 281 |
+
"p":0.9859906604,
|
| 282 |
+
"r":0.9823861748,
|
| 283 |
+
"f":0.9841851174
|
| 284 |
},
|
| 285 |
"Number":{
|
| 286 |
+
"p":0.9895260539,
|
| 287 |
+
"r":0.9856546688,
|
| 288 |
+
"f":0.9875865674
|
| 289 |
},
|
| 290 |
"AdpType":{
|
| 291 |
+
"p":0.9982190561,
|
| 292 |
+
"r":0.991158267,
|
| 293 |
+
"f":0.9946761313
|
| 294 |
},
|
| 295 |
"PartType":{
|
| 296 |
"p":1.0,
|
| 297 |
+
"r":1.0,
|
| 298 |
+
"f":1.0
|
| 299 |
},
|
| 300 |
"Case":{
|
| 301 |
+
"p":0.9952305246,
|
| 302 |
+
"r":0.9889415482,
|
| 303 |
+
"f":0.9920760697
|
| 304 |
},
|
| 305 |
"Person":{
|
| 306 |
+
"p":0.9946808511,
|
| 307 |
+
"r":0.9964476021,
|
| 308 |
+
"f":0.9955634428
|
| 309 |
},
|
| 310 |
"PronType":{
|
| 311 |
+
"p":0.9942434211,
|
| 312 |
+
"r":0.9942434211,
|
| 313 |
+
"f":0.9942434211
|
| 314 |
},
|
| 315 |
"NumType":{
|
| 316 |
+
"p":0.972972973,
|
| 317 |
+
"r":0.9536423841,
|
| 318 |
+
"f":0.9632107023
|
| 319 |
},
|
| 320 |
"Degree":{
|
| 321 |
+
"p":0.9853836784,
|
| 322 |
+
"r":0.9746987952,
|
| 323 |
+
"f":0.9800121139
|
| 324 |
},
|
| 325 |
"Reflex":{
|
| 326 |
"p":1.0,
|
|
|
|
| 328 |
"f":1.0
|
| 329 |
},
|
| 330 |
"Number[psor]":{
|
| 331 |
+
"p":0.988372093,
|
| 332 |
"r":0.988372093,
|
| 333 |
+
"f":0.988372093
|
| 334 |
},
|
| 335 |
"Poss":{
|
| 336 |
+
"p":0.9886363636,
|
| 337 |
"r":0.9886363636,
|
| 338 |
+
"f":0.9886363636
|
| 339 |
},
|
| 340 |
"Foreign":{
|
| 341 |
"p":0.8571428571,
|
|
|
|
| 353 |
"f":1.0
|
| 354 |
},
|
| 355 |
"Polite":{
|
| 356 |
+
"p":1.0,
|
| 357 |
+
"r":1.0,
|
| 358 |
+
"f":1.0
|
| 359 |
}
|
| 360 |
},
|
| 361 |
+
"sents_p":0.9502664298,
|
| 362 |
+
"sents_r":0.9485815603,
|
| 363 |
+
"sents_f":0.9494232476,
|
| 364 |
+
"dep_uas":0.8842458101,
|
| 365 |
+
"dep_las":0.8566640599,
|
| 366 |
"dep_las_per_type":{
|
| 367 |
"advmod":{
|
| 368 |
+
"p":0.8081232493,
|
| 369 |
+
"r":0.8149717514,
|
| 370 |
+
"f":0.811533052
|
| 371 |
},
|
| 372 |
"root":{
|
| 373 |
+
"p":0.8989361702,
|
| 374 |
+
"r":0.8989361702,
|
| 375 |
+
"f":0.8989361702
|
| 376 |
},
|
| 377 |
"nsubj":{
|
| 378 |
+
"p":0.9171907757,
|
| 379 |
+
"r":0.9229957806,
|
| 380 |
+
"f":0.920084122
|
| 381 |
},
|
| 382 |
"case":{
|
| 383 |
+
"p":0.9323383085,
|
| 384 |
+
"r":0.9240631164,
|
| 385 |
+
"f":0.9281822684
|
| 386 |
},
|
| 387 |
"obl":{
|
| 388 |
+
"p":0.7925696594,
|
| 389 |
+
"r":0.7950310559,
|
| 390 |
+
"f":0.7937984496
|
| 391 |
},
|
| 392 |
"cc":{
|
| 393 |
+
"p":0.8746355685,
|
| 394 |
+
"r":0.8720930233,
|
| 395 |
+
"f":0.8733624454
|
| 396 |
},
|
| 397 |
"conj":{
|
| 398 |
+
"p":0.7639257294,
|
| 399 |
+
"r":0.768,
|
| 400 |
+
"f":0.7659574468
|
| 401 |
},
|
| 402 |
"obj":{
|
| 403 |
+
"p":0.9013282732,
|
| 404 |
+
"r":0.9223300971,
|
| 405 |
+
"f":0.9117082534
|
| 406 |
},
|
| 407 |
"aux":{
|
| 408 |
+
"p":0.9104046243,
|
| 409 |
+
"r":0.9183673469,
|
| 410 |
+
"f":0.9143686502
|
| 411 |
},
|
| 412 |
"acl:relcl":{
|
| 413 |
+
"p":0.7,
|
| 414 |
+
"r":0.6810810811,
|
| 415 |
+
"f":0.6904109589
|
| 416 |
},
|
| 417 |
"advmod:lmod":{
|
| 418 |
+
"p":0.8153846154,
|
| 419 |
+
"r":0.7910447761,
|
| 420 |
+
"f":0.803030303
|
| 421 |
},
|
| 422 |
"det":{
|
| 423 |
+
"p":0.9363784666,
|
| 424 |
+
"r":0.9456342669,
|
| 425 |
+
"f":0.9409836066
|
| 426 |
},
|
| 427 |
"amod":{
|
| 428 |
+
"p":0.8798646362,
|
| 429 |
+
"r":0.8873720137,
|
| 430 |
+
"f":0.8836023789
|
| 431 |
},
|
| 432 |
"nmod:poss":{
|
| 433 |
+
"p":0.7745098039,
|
| 434 |
+
"r":0.7821782178,
|
| 435 |
+
"f":0.7783251232
|
| 436 |
},
|
| 437 |
"ccomp":{
|
| 438 |
+
"p":0.7301587302,
|
| 439 |
+
"r":0.7419354839,
|
| 440 |
+
"f":0.736
|
| 441 |
},
|
| 442 |
"nummod":{
|
| 443 |
+
"p":0.8429752066,
|
| 444 |
+
"r":0.85,
|
| 445 |
+
"f":0.846473029
|
| 446 |
},
|
| 447 |
"flat":{
|
| 448 |
+
"p":0.8625,
|
| 449 |
"r":0.9139072848,
|
| 450 |
+
"f":0.8874598071
|
| 451 |
},
|
| 452 |
"compound:prt":{
|
| 453 |
+
"p":0.6764705882,
|
| 454 |
+
"r":0.5609756098,
|
| 455 |
+
"f":0.6133333333
|
| 456 |
},
|
| 457 |
"advcl":{
|
| 458 |
+
"p":0.7413793103,
|
| 459 |
+
"r":0.7413793103,
|
| 460 |
+
"f":0.7413793103
|
| 461 |
},
|
| 462 |
"mark":{
|
| 463 |
+
"p":0.9173553719,
|
| 464 |
+
"r":0.9117043121,
|
| 465 |
+
"f":0.9145211123
|
| 466 |
},
|
| 467 |
"cop":{
|
| 468 |
+
"p":0.901734104,
|
| 469 |
+
"r":0.8914285714,
|
| 470 |
+
"f":0.8965517241
|
| 471 |
},
|
| 472 |
"dep":{
|
| 473 |
+
"p":0.2307692308,
|
| 474 |
+
"r":0.3396226415,
|
| 475 |
+
"f":0.2748091603
|
| 476 |
},
|
| 477 |
"nmod":{
|
| 478 |
+
"p":0.7693920335,
|
| 479 |
+
"r":0.716796875,
|
| 480 |
+
"f":0.7421638018
|
| 481 |
},
|
| 482 |
"iobj":{
|
| 483 |
+
"p":0.9285714286,
|
| 484 |
+
"r":0.5909090909,
|
| 485 |
+
"f":0.7222222222
|
| 486 |
},
|
| 487 |
"xcomp":{
|
| 488 |
+
"p":0.6595744681,
|
| 489 |
+
"r":0.5254237288,
|
| 490 |
+
"f":0.5849056604
|
| 491 |
},
|
| 492 |
"list":{
|
| 493 |
+
"p":0.5,
|
| 494 |
+
"r":0.4444444444,
|
| 495 |
+
"f":0.4705882353
|
| 496 |
},
|
| 497 |
"vocative":{
|
| 498 |
"p":0.0,
|
|
|
|
| 500 |
"f":0.0
|
| 501 |
},
|
| 502 |
"fixed":{
|
| 503 |
+
"p":0.9210526316,
|
| 504 |
+
"r":0.8536585366,
|
| 505 |
+
"f":0.8860759494
|
| 506 |
},
|
| 507 |
"expl":{
|
| 508 |
+
"p":0.9393939394,
|
| 509 |
"r":0.9117647059,
|
| 510 |
+
"f":0.9253731343
|
| 511 |
},
|
| 512 |
"appos":{
|
| 513 |
+
"p":0.6315789474,
|
| 514 |
+
"r":0.7272727273,
|
| 515 |
+
"f":0.676056338
|
| 516 |
},
|
| 517 |
"obl:tmod":{
|
| 518 |
+
"p":0.7272727273,
|
| 519 |
+
"r":0.4444444444,
|
| 520 |
+
"f":0.5517241379
|
| 521 |
},
|
| 522 |
"discourse":{
|
| 523 |
"p":0.0,
|
|
|
|
| 530 |
"f":0.0
|
| 531 |
}
|
| 532 |
},
|
| 533 |
+
"lemma_acc":0.9515738499,
|
| 534 |
+
"tag_acc":0.9831444348,
|
| 535 |
+
"ents_p":0.8585657371,
|
| 536 |
+
"ents_r":0.8979166667,
|
| 537 |
+
"ents_f":0.8778004073,
|
| 538 |
"ents_per_type":{
|
| 539 |
"PER":{
|
| 540 |
+
"p":0.9493670886,
|
| 541 |
+
"r":0.9036144578,
|
| 542 |
+
"f":0.9259259259
|
| 543 |
},
|
| 544 |
"ORG":{
|
| 545 |
+
"p":0.8720930233,
|
| 546 |
+
"r":0.8333333333,
|
| 547 |
+
"f":0.8522727273
|
| 548 |
},
|
| 549 |
"MISC":{
|
| 550 |
+
"p":0.7163120567,
|
| 551 |
+
"r":0.8938053097,
|
| 552 |
+
"f":0.7952755906
|
| 553 |
},
|
| 554 |
"LOC":{
|
| 555 |
+
"p":0.8974358974,
|
| 556 |
+
"r":0.9459459459,
|
| 557 |
+
"f":0.9210526316
|
| 558 |
}
|
| 559 |
},
|
| 560 |
+
"speed":655.5887888543
|
| 561 |
},
|
| 562 |
"sources":[
|
| 563 |
{
|
|
|
|
| 573 |
"author":"Rasmus Hvingelby, Amalie B. Pauli, Maria Barrett, Christina Rosted, Lasse M. Lidegaard, Anders S\u00f8gaard"
|
| 574 |
},
|
| 575 |
{
|
| 576 |
+
"name":"vesteinn/DanskBERT",
|
| 577 |
+
"author":"Sn\u00e6bjarnarson, V\u00e9steinn and Simonsen, Annika and Glava\u0161, Goran and Vuli\u0107, Ivan",
|
| 578 |
+
"url":"https://huggingface.co/vesteinn/DanskBERT",
|
| 579 |
"license":"CC BY 4.0"
|
| 580 |
}
|
| 581 |
],
|
| 582 |
"requirements":[
|
| 583 |
+
"spacy-transformers>=1.2.2,<1.3.0"
|
| 584 |
]
|
| 585 |
}
|
morphologizer/cfg
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"extend":false,
|
|
|
|
| 3 |
"labels_morph":{
|
| 4 |
"AdpType=Prep|POS=ADP":"AdpType=Prep",
|
| 5 |
"Definite=Ind|Gender=Com|Number=Sing|POS=NOUN":"Definite=Ind|Gender=Com|Number=Sing",
|
|
|
|
| 1 |
{
|
| 2 |
"extend":false,
|
| 3 |
+
"label_smoothing":0.0,
|
| 4 |
"labels_morph":{
|
| 5 |
"AdpType=Prep|POS=ADP":"AdpType=Prep",
|
| 6 |
"Definite=Ind|Gender=Com|Number=Sing|POS=NOUN":"Definite=Ind|Gender=Com|Number=Sing",
|
morphologizer/model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 483580
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:574f46da8f1a3e229a7cc9e36b94f7553a485f7f2ff7c2ae299e650beeba5f65
|
| 3 |
size 483580
|
ner/model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 225962
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:144da1fbd0e2108b31ba352085a97cb53d27216ca31e9108fae176886094c057
|
| 3 |
size 225962
|
parser/model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 460325
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eeb64c4f7210ff479c0dc4bb40e88cf49bf44f156de24544d0b6194894c421dc
|
| 3 |
size 460325
|
transformer/model
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:e3fd9206ed262fb41dd70f4c1b6ee884c247f8026afffe7c7bda4bedf8d992dd
|
| 3 |
+
size 502755332
|
vocab/strings.json
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 sha256:5018aa5b5adda3620458714f53e1e93eca15eb04c8c7c0ae534adeb7541bf917
|
| 3 |
+
size 471010
|