Update spaCy pipeline
Browse files- README.md +22 -22
- accuracy.json +114 -114
- attribute_ruler/patterns +0 -0
- config.cfg +2 -0
- grc_perseus_sm-any-py3-none-any.whl +2 -2
- lemmatizer/model +1 -1
- meta.json +120 -120
- morphologizer/cfg +1 -0
- morphologizer/model +0 -0
- parser/model +1 -1
- tagger/cfg +1 -0
- tagger/model +0 -0
- tok2vec/model +1 -1
- vocab/strings.json +2 -2
README.md
CHANGED
|
@@ -13,55 +13,55 @@ model-index:
|
|
| 13 |
metrics:
|
| 14 |
- name: TAG (XPOS) Accuracy
|
| 15 |
type: accuracy
|
| 16 |
-
value: 0.
|
| 17 |
- task:
|
| 18 |
name: POS
|
| 19 |
type: token-classification
|
| 20 |
metrics:
|
| 21 |
- name: POS (UPOS) Accuracy
|
| 22 |
type: accuracy
|
| 23 |
-
value: 0.
|
| 24 |
- task:
|
| 25 |
name: MORPH
|
| 26 |
type: token-classification
|
| 27 |
metrics:
|
| 28 |
- name: Morph (UFeats) Accuracy
|
| 29 |
type: accuracy
|
| 30 |
-
value: 0.
|
| 31 |
- task:
|
| 32 |
name: LEMMA
|
| 33 |
type: token-classification
|
| 34 |
metrics:
|
| 35 |
- name: Lemma Accuracy
|
| 36 |
type: accuracy
|
| 37 |
-
value: 0.
|
| 38 |
- task:
|
| 39 |
name: UNLABELED_DEPENDENCIES
|
| 40 |
type: token-classification
|
| 41 |
metrics:
|
| 42 |
- name: Unlabeled Attachment Score (UAS)
|
| 43 |
type: f_score
|
| 44 |
-
value: 0.
|
| 45 |
- task:
|
| 46 |
name: LABELED_DEPENDENCIES
|
| 47 |
type: token-classification
|
| 48 |
metrics:
|
| 49 |
- name: Labeled Attachment Score (LAS)
|
| 50 |
type: f_score
|
| 51 |
-
value: 0.
|
| 52 |
- task:
|
| 53 |
name: SENTS
|
| 54 |
type: token-classification
|
| 55 |
metrics:
|
| 56 |
- name: Sentences F-Score
|
| 57 |
type: f_score
|
| 58 |
-
value: 0.
|
| 59 |
---
|
| 60 |
| Feature | Description |
|
| 61 |
| --- | --- |
|
| 62 |
| **Name** | `grc_perseus_sm` |
|
| 63 |
-
| **Version** | `3.
|
| 64 |
-
| **spaCy** | `>=3.
|
| 65 |
| **Default Pipeline** | `tok2vec`, `morphologizer`, `tagger`, `parser`, `lemmatizer`, `attribute_ruler` |
|
| 66 |
| **Components** | `tok2vec`, `morphologizer`, `tagger`, `parser`, `lemmatizer`, `attribute_ruler` |
|
| 67 |
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
|
|
@@ -87,16 +87,16 @@ model-index:
|
|
| 87 |
|
| 88 |
| Type | Score |
|
| 89 |
| --- | --- |
|
| 90 |
-
| `POS_ACC` | 89.
|
| 91 |
-
| `MORPH_ACC` | 83.
|
| 92 |
-
| `TAG_ACC` | 89.
|
| 93 |
-
| `DEP_UAS` | 65.
|
| 94 |
-
| `DEP_LAS` |
|
| 95 |
-
| `SENTS_P` |
|
| 96 |
-
| `SENTS_R` |
|
| 97 |
-
| `SENTS_F` |
|
| 98 |
-
| `LEMMA_ACC` | 97.
|
| 99 |
-
| `TOK2VEC_LOSS` |
|
| 100 |
-
| `MORPHOLOGIZER_LOSS` |
|
| 101 |
-
| `TAGGER_LOSS` |
|
| 102 |
-
| `PARSER_LOSS` |
|
|
|
|
| 13 |
metrics:
|
| 14 |
- name: TAG (XPOS) Accuracy
|
| 15 |
type: accuracy
|
| 16 |
+
value: 0.895328876
|
| 17 |
- task:
|
| 18 |
name: POS
|
| 19 |
type: token-classification
|
| 20 |
metrics:
|
| 21 |
- name: POS (UPOS) Accuracy
|
| 22 |
type: accuracy
|
| 23 |
+
value: 0.8915542906
|
| 24 |
- task:
|
| 25 |
name: MORPH
|
| 26 |
type: token-classification
|
| 27 |
metrics:
|
| 28 |
- name: Morph (UFeats) Accuracy
|
| 29 |
type: accuracy
|
| 30 |
+
value: 0.8344251186
|
| 31 |
- task:
|
| 32 |
name: LEMMA
|
| 33 |
type: token-classification
|
| 34 |
metrics:
|
| 35 |
- name: Lemma Accuracy
|
| 36 |
type: accuracy
|
| 37 |
+
value: 0.9732806324
|
| 38 |
- task:
|
| 39 |
name: UNLABELED_DEPENDENCIES
|
| 40 |
type: token-classification
|
| 41 |
metrics:
|
| 42 |
- name: Unlabeled Attachment Score (UAS)
|
| 43 |
type: f_score
|
| 44 |
+
value: 0.659948986
|
| 45 |
- task:
|
| 46 |
name: LABELED_DEPENDENCIES
|
| 47 |
type: token-classification
|
| 48 |
metrics:
|
| 49 |
- name: Labeled Attachment Score (LAS)
|
| 50 |
type: f_score
|
| 51 |
+
value: 0.5802671785
|
| 52 |
- task:
|
| 53 |
name: SENTS
|
| 54 |
type: token-classification
|
| 55 |
metrics:
|
| 56 |
- name: Sentences F-Score
|
| 57 |
type: f_score
|
| 58 |
+
value: 0.9851138354
|
| 59 |
---
|
| 60 |
| Feature | Description |
|
| 61 |
| --- | --- |
|
| 62 |
| **Name** | `grc_perseus_sm` |
|
| 63 |
+
| **Version** | `3.6.0` |
|
| 64 |
+
| **spaCy** | `>=3.6.0,<3.7.0` |
|
| 65 |
| **Default Pipeline** | `tok2vec`, `morphologizer`, `tagger`, `parser`, `lemmatizer`, `attribute_ruler` |
|
| 66 |
| **Components** | `tok2vec`, `morphologizer`, `tagger`, `parser`, `lemmatizer`, `attribute_ruler` |
|
| 67 |
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
|
|
|
|
| 87 |
|
| 88 |
| Type | Score |
|
| 89 |
| --- | --- |
|
| 90 |
+
| `POS_ACC` | 89.16 |
|
| 91 |
+
| `MORPH_ACC` | 83.44 |
|
| 92 |
+
| `TAG_ACC` | 89.53 |
|
| 93 |
+
| `DEP_UAS` | 65.99 |
|
| 94 |
+
| `DEP_LAS` | 58.03 |
|
| 95 |
+
| `SENTS_P` | 98.08 |
|
| 96 |
+
| `SENTS_R` | 98.94 |
|
| 97 |
+
| `SENTS_F` | 98.51 |
|
| 98 |
+
| `LEMMA_ACC` | 97.33 |
|
| 99 |
+
| `TOK2VEC_LOSS` | 3658834.70 |
|
| 100 |
+
| `MORPHOLOGIZER_LOSS` | 154041.87 |
|
| 101 |
+
| `TAGGER_LOSS` | 65232.41 |
|
| 102 |
+
| `PARSER_LOSS` | 1540508.40 |
|
accuracy.json
CHANGED
|
@@ -3,154 +3,154 @@
|
|
| 3 |
"token_p":0.9983307102,
|
| 4 |
"token_r":0.9987117706,
|
| 5 |
"token_f":0.998521204,
|
| 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 |
"Number":{
|
| 18 |
-
"p":0.
|
| 19 |
-
"r":0.
|
| 20 |
-
"f":0.
|
| 21 |
},
|
| 22 |
"Person":{
|
| 23 |
-
"p":0.
|
| 24 |
-
"r":0.
|
| 25 |
-
"f":0.
|
| 26 |
},
|
| 27 |
"Tense":{
|
| 28 |
-
"p":0.
|
| 29 |
-
"r":0.
|
| 30 |
-
"f":0.
|
| 31 |
},
|
| 32 |
"VerbForm":{
|
| 33 |
-
"p":0.
|
| 34 |
-
"r":0.
|
| 35 |
-
"f":0.
|
| 36 |
},
|
| 37 |
"Voice":{
|
| 38 |
-
"p":0.
|
| 39 |
-
"r":0.
|
| 40 |
-
"f":0.
|
| 41 |
},
|
| 42 |
"Case":{
|
| 43 |
-
"p":0.
|
| 44 |
-
"r":0.
|
| 45 |
-
"f":0.
|
| 46 |
},
|
| 47 |
"Gender":{
|
| 48 |
-
"p":0.
|
| 49 |
-
"r":0.
|
| 50 |
-
"f":0.
|
| 51 |
},
|
| 52 |
"Aspect":{
|
| 53 |
-
"p":0.
|
| 54 |
-
"r":0.
|
| 55 |
-
"f":0.
|
| 56 |
},
|
| 57 |
"Degree":{
|
| 58 |
-
"p":0.
|
| 59 |
-
"r":0.
|
| 60 |
-
"f":0.
|
| 61 |
}
|
| 62 |
},
|
| 63 |
-
"tag_acc":0.
|
| 64 |
-
"sents_p":0.
|
| 65 |
-
"sents_r":0.
|
| 66 |
-
"sents_f":0.
|
| 67 |
-
"dep_uas":0.
|
| 68 |
-
"dep_las":0.
|
| 69 |
"dep_las_per_type":{
|
| 70 |
"root":{
|
| 71 |
-
"p":0.
|
| 72 |
-
"r":0.
|
| 73 |
-
"f":0.
|
| 74 |
},
|
| 75 |
"advmod":{
|
| 76 |
-
"p":0.
|
| 77 |
-
"r":0.
|
| 78 |
-
"f":0.
|
| 79 |
},
|
| 80 |
"nsubj":{
|
| 81 |
-
"p":0.
|
| 82 |
"r":0.523880597,
|
| 83 |
-
"f":0.
|
| 84 |
},
|
| 85 |
"det":{
|
| 86 |
-
"p":0.
|
| 87 |
-
"r":0.
|
| 88 |
-
"f":0.
|
| 89 |
},
|
| 90 |
"nmod":{
|
| 91 |
-
"p":0.
|
| 92 |
-
"r":0.
|
| 93 |
-
"f":0.
|
| 94 |
},
|
| 95 |
"obj":{
|
| 96 |
-
"p":0.
|
| 97 |
-
"r":0.
|
| 98 |
-
"f":0.
|
| 99 |
},
|
| 100 |
"advcl":{
|
| 101 |
-
"p":0.
|
| 102 |
-
"r":0.
|
| 103 |
-
"f":0.
|
| 104 |
},
|
| 105 |
"cc":{
|
| 106 |
-
"p":0.
|
| 107 |
-
"r":0.
|
| 108 |
-
"f":0.
|
| 109 |
},
|
| 110 |
"conj":{
|
| 111 |
-
"p":0.
|
| 112 |
"r":0.4302788845,
|
| 113 |
-
"f":0.
|
| 114 |
},
|
| 115 |
"amod":{
|
| 116 |
-
"p":0.
|
| 117 |
-
"r":0.
|
| 118 |
-
"f":0.
|
| 119 |
},
|
| 120 |
"cop":{
|
| 121 |
-
"p":0.
|
| 122 |
-
"r":0.
|
| 123 |
-
"f":0.
|
| 124 |
},
|
| 125 |
"obl":{
|
| 126 |
-
"p":0.
|
| 127 |
-
"r":0.
|
| 128 |
-
"f":0.
|
| 129 |
},
|
| 130 |
"case":{
|
| 131 |
-
"p":0.
|
| 132 |
-
"r":0.
|
| 133 |
-
"f":0.
|
| 134 |
},
|
| 135 |
"xcomp":{
|
| 136 |
-
"p":0.
|
| 137 |
-
"r":0.
|
| 138 |
-
"f":0.
|
| 139 |
},
|
| 140 |
"csubj":{
|
| 141 |
-
"p":0.
|
| 142 |
-
"r":0.
|
| 143 |
-
"f":0.
|
| 144 |
},
|
| 145 |
"mark":{
|
| 146 |
-
"p":0.
|
| 147 |
-
"r":0.
|
| 148 |
-
"f":0.
|
| 149 |
},
|
| 150 |
"ccomp":{
|
| 151 |
-
"p":0.
|
| 152 |
-
"r":0.
|
| 153 |
-
"f":0.
|
| 154 |
},
|
| 155 |
"dep":{
|
| 156 |
"p":0.0,
|
|
@@ -158,41 +158,41 @@
|
|
| 158 |
"f":0.0
|
| 159 |
},
|
| 160 |
"acl":{
|
| 161 |
-
"p":0.
|
| 162 |
-
"r":0.
|
| 163 |
-
"f":0.
|
| 164 |
},
|
| 165 |
"iobj":{
|
| 166 |
-
"p":0.
|
| 167 |
-
"r":0.
|
| 168 |
-
"f":0.
|
| 169 |
-
},
|
| 170 |
-
"appos":{
|
| 171 |
-
"p":0.1,
|
| 172 |
-
"r":0.1034482759,
|
| 173 |
-
"f":0.1016949153
|
| 174 |
},
|
| 175 |
"discourse":{
|
| 176 |
-
"p":0.
|
| 177 |
-
"r":0.
|
| 178 |
-
"f":0.
|
| 179 |
},
|
| 180 |
"vocative":{
|
| 181 |
-
"p":0.
|
| 182 |
-
"r":0.
|
| 183 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 184 |
},
|
| 185 |
"parataxis":{
|
| 186 |
-
"p":0.
|
| 187 |
"r":0.2222222222,
|
| 188 |
-
"f":0.
|
| 189 |
},
|
| 190 |
"nummod":{
|
| 191 |
-
"p":0.
|
| 192 |
-
"r":0.
|
| 193 |
-
"f":0.
|
| 194 |
}
|
| 195 |
},
|
| 196 |
-
"lemma_acc":0.
|
| 197 |
-
"speed":
|
| 198 |
}
|
|
|
|
| 3 |
"token_p":0.9983307102,
|
| 4 |
"token_r":0.9987117706,
|
| 5 |
"token_f":0.998521204,
|
| 6 |
+
"pos_acc":0.8699324727,
|
| 7 |
+
"morph_acc":0.8186026534,
|
| 8 |
+
"morph_micro_p":0.8806058222,
|
| 9 |
+
"morph_micro_r":0.8702159504,
|
| 10 |
+
"morph_micro_f":0.8753800581,
|
| 11 |
"morph_per_feat":{
|
| 12 |
"Mood":{
|
| 13 |
+
"p":0.8717201166,
|
| 14 |
+
"r":0.870029098,
|
| 15 |
+
"f":0.8708737864
|
| 16 |
},
|
| 17 |
"Number":{
|
| 18 |
+
"p":0.9419844985,
|
| 19 |
+
"r":0.9336020688,
|
| 20 |
+
"f":0.9377745521
|
| 21 |
},
|
| 22 |
"Person":{
|
| 23 |
+
"p":0.8788172564,
|
| 24 |
+
"r":0.843255814,
|
| 25 |
+
"f":0.8606693568
|
| 26 |
},
|
| 27 |
"Tense":{
|
| 28 |
+
"p":0.7730227519,
|
| 29 |
+
"r":0.7655579399,
|
| 30 |
+
"f":0.7692722372
|
| 31 |
},
|
| 32 |
"VerbForm":{
|
| 33 |
+
"p":0.8905742145,
|
| 34 |
+
"r":0.8829215897,
|
| 35 |
+
"f":0.8867313916
|
| 36 |
},
|
| 37 |
"Voice":{
|
| 38 |
+
"p":0.8717809705,
|
| 39 |
+
"r":0.8626609442,
|
| 40 |
+
"f":0.8671969799
|
| 41 |
},
|
| 42 |
"Case":{
|
| 43 |
+
"p":0.9000182282,
|
| 44 |
+
"r":0.8911650573,
|
| 45 |
+
"f":0.8955697638
|
| 46 |
},
|
| 47 |
"Gender":{
|
| 48 |
+
"p":0.8379093314,
|
| 49 |
+
"r":0.8308610709,
|
| 50 |
+
"f":0.8343703165
|
| 51 |
},
|
| 52 |
"Aspect":{
|
| 53 |
+
"p":0.7140625,
|
| 54 |
+
"r":0.676035503,
|
| 55 |
+
"f":0.6945288754
|
| 56 |
},
|
| 57 |
"Degree":{
|
| 58 |
+
"p":0.3,
|
| 59 |
+
"r":0.1276595745,
|
| 60 |
+
"f":0.1791044776
|
| 61 |
}
|
| 62 |
},
|
| 63 |
+
"tag_acc":0.8736548235,
|
| 64 |
+
"sents_p":0.9710365854,
|
| 65 |
+
"sents_r":0.9754977029,
|
| 66 |
+
"sents_f":0.9732620321,
|
| 67 |
+
"dep_uas":0.6399031347,
|
| 68 |
+
"dep_las":0.5625807146,
|
| 69 |
"dep_las_per_type":{
|
| 70 |
"root":{
|
| 71 |
+
"p":0.8041158537,
|
| 72 |
+
"r":0.8078101072,
|
| 73 |
+
"f":0.8059587471
|
| 74 |
},
|
| 75 |
"advmod":{
|
| 76 |
+
"p":0.593495935,
|
| 77 |
+
"r":0.5672105672,
|
| 78 |
+
"f":0.5800556218
|
| 79 |
},
|
| 80 |
"nsubj":{
|
| 81 |
+
"p":0.5616,
|
| 82 |
"r":0.523880597,
|
| 83 |
+
"f":0.5420849421
|
| 84 |
},
|
| 85 |
"det":{
|
| 86 |
+
"p":0.7864829961,
|
| 87 |
+
"r":0.7631578947,
|
| 88 |
+
"f":0.7746449014
|
| 89 |
},
|
| 90 |
"nmod":{
|
| 91 |
+
"p":0.4310954064,
|
| 92 |
+
"r":0.43339254,
|
| 93 |
+
"f":0.4322409212
|
| 94 |
},
|
| 95 |
"obj":{
|
| 96 |
+
"p":0.4340557276,
|
| 97 |
+
"r":0.4642384106,
|
| 98 |
+
"f":0.44864
|
| 99 |
},
|
| 100 |
"advcl":{
|
| 101 |
+
"p":0.5180995475,
|
| 102 |
+
"r":0.4589178357,
|
| 103 |
+
"f":0.4867162593
|
| 104 |
},
|
| 105 |
"cc":{
|
| 106 |
+
"p":0.4395061728,
|
| 107 |
+
"r":0.5460122699,
|
| 108 |
+
"f":0.487004104
|
| 109 |
},
|
| 110 |
"conj":{
|
| 111 |
+
"p":0.392251816,
|
| 112 |
"r":0.4302788845,
|
| 113 |
+
"f":0.4103863205
|
| 114 |
},
|
| 115 |
"amod":{
|
| 116 |
+
"p":0.0689655172,
|
| 117 |
+
"r":0.0275862069,
|
| 118 |
+
"f":0.039408867
|
| 119 |
},
|
| 120 |
"cop":{
|
| 121 |
+
"p":0.5354609929,
|
| 122 |
+
"r":0.5354609929,
|
| 123 |
+
"f":0.5354609929
|
| 124 |
},
|
| 125 |
"obl":{
|
| 126 |
+
"p":0.4874010079,
|
| 127 |
+
"r":0.4856527977,
|
| 128 |
+
"f":0.4865253324
|
| 129 |
},
|
| 130 |
"case":{
|
| 131 |
+
"p":0.8220986796,
|
| 132 |
+
"r":0.8198198198,
|
| 133 |
+
"f":0.8209576683
|
| 134 |
},
|
| 135 |
"xcomp":{
|
| 136 |
+
"p":0.2757936508,
|
| 137 |
+
"r":0.2667946257,
|
| 138 |
+
"f":0.2712195122
|
| 139 |
},
|
| 140 |
"csubj":{
|
| 141 |
+
"p":0.2564102564,
|
| 142 |
+
"r":0.2564102564,
|
| 143 |
+
"f":0.2564102564
|
| 144 |
},
|
| 145 |
"mark":{
|
| 146 |
+
"p":0.763803681,
|
| 147 |
+
"r":0.7196531792,
|
| 148 |
+
"f":0.7410714286
|
| 149 |
},
|
| 150 |
"ccomp":{
|
| 151 |
+
"p":0.4467005076,
|
| 152 |
+
"r":0.3333333333,
|
| 153 |
+
"f":0.3817787419
|
| 154 |
},
|
| 155 |
"dep":{
|
| 156 |
"p":0.0,
|
|
|
|
| 158 |
"f":0.0
|
| 159 |
},
|
| 160 |
"acl":{
|
| 161 |
+
"p":0.1764705882,
|
| 162 |
+
"r":0.1363636364,
|
| 163 |
+
"f":0.1538461538
|
| 164 |
},
|
| 165 |
"iobj":{
|
| 166 |
+
"p":0.2804878049,
|
| 167 |
+
"r":0.2323232323,
|
| 168 |
+
"f":0.2541436464
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 169 |
},
|
| 170 |
"discourse":{
|
| 171 |
+
"p":0.7741935484,
|
| 172 |
+
"r":0.7272727273,
|
| 173 |
+
"f":0.75
|
| 174 |
},
|
| 175 |
"vocative":{
|
| 176 |
+
"p":0.4310344828,
|
| 177 |
+
"r":0.3086419753,
|
| 178 |
+
"f":0.3597122302
|
| 179 |
+
},
|
| 180 |
+
"appos":{
|
| 181 |
+
"p":0.0434782609,
|
| 182 |
+
"r":0.0689655172,
|
| 183 |
+
"f":0.0533333333
|
| 184 |
},
|
| 185 |
"parataxis":{
|
| 186 |
+
"p":0.0833333333,
|
| 187 |
"r":0.2222222222,
|
| 188 |
+
"f":0.1212121212
|
| 189 |
},
|
| 190 |
"nummod":{
|
| 191 |
+
"p":0.0625,
|
| 192 |
+
"r":0.3333333333,
|
| 193 |
+
"f":0.1052631579
|
| 194 |
}
|
| 195 |
},
|
| 196 |
+
"lemma_acc":0.8996445695,
|
| 197 |
+
"speed":5487.9074486941
|
| 198 |
}
|
attribute_ruler/patterns
CHANGED
|
Binary files a/attribute_ruler/patterns and b/attribute_ruler/patterns differ
|
|
|
config.cfg
CHANGED
|
@@ -51,6 +51,7 @@ subword_features = true
|
|
| 51 |
[components.morphologizer]
|
| 52 |
factory = "morphologizer"
|
| 53 |
extend = false
|
|
|
|
| 54 |
overwrite = true
|
| 55 |
scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
|
| 56 |
|
|
@@ -88,6 +89,7 @@ upstream = "tok2vec"
|
|
| 88 |
|
| 89 |
[components.tagger]
|
| 90 |
factory = "tagger"
|
|
|
|
| 91 |
neg_prefix = "!"
|
| 92 |
overwrite = false
|
| 93 |
scorer = {"@scorers":"spacy.tagger_scorer.v1"}
|
|
|
|
| 51 |
[components.morphologizer]
|
| 52 |
factory = "morphologizer"
|
| 53 |
extend = false
|
| 54 |
+
label_smoothing = 0.0
|
| 55 |
overwrite = true
|
| 56 |
scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
|
| 57 |
|
|
|
|
| 89 |
|
| 90 |
[components.tagger]
|
| 91 |
factory = "tagger"
|
| 92 |
+
label_smoothing = 0.0
|
| 93 |
neg_prefix = "!"
|
| 94 |
overwrite = false
|
| 95 |
scorer = {"@scorers":"spacy.tagger_scorer.v1"}
|
grc_perseus_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:b81c27337928769c7466da3549b50cb4ae8ffdd632599bbe40b33f3b23fba94d
|
| 3 |
+
size 59914313
|
lemmatizer/model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 24263260
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47c2c081c979e7cb5953f63ec0f8c30fb603c65e6cb7315730d37776e684fa40
|
| 3 |
size 24263260
|
meta.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"lang":"grc",
|
| 3 |
"name":"perseus_sm",
|
| 4 |
-
"version":"3.
|
| 5 |
"description":"",
|
| 6 |
"author":"",
|
| 7 |
"email":"",
|
| 8 |
"url":"",
|
| 9 |
"license":"",
|
| 10 |
-
"spacy_version":">=3.
|
| 11 |
-
"spacy_git_version":"
|
| 12 |
"vectors":{
|
| 13 |
"width":0,
|
| 14 |
"vectors":0,
|
|
@@ -961,198 +961,198 @@
|
|
| 961 |
|
| 962 |
],
|
| 963 |
"performance":{
|
| 964 |
-
"pos_acc":0.
|
| 965 |
-
"morph_acc":0.
|
| 966 |
"morph_per_feat":{
|
| 967 |
"Case":{
|
| 968 |
-
"p":0.
|
| 969 |
-
"r":0.
|
| 970 |
-
"f":0.
|
| 971 |
},
|
| 972 |
"Gender":{
|
| 973 |
-
"p":0.
|
| 974 |
-
"r":0.
|
| 975 |
-
"f":0.
|
| 976 |
},
|
| 977 |
"Number":{
|
| 978 |
-
"p":0.
|
| 979 |
-
"r":0.
|
| 980 |
-
"f":0.
|
| 981 |
},
|
| 982 |
"Degree":{
|
| 983 |
-
"p":0.
|
| 984 |
-
"r":0.
|
| 985 |
-
"f":0.
|
| 986 |
},
|
| 987 |
"Tense":{
|
| 988 |
-
"p":0.
|
| 989 |
-
"r":0.
|
| 990 |
-
"f":0.
|
| 991 |
},
|
| 992 |
"VerbForm":{
|
| 993 |
-
"p":0.
|
| 994 |
-
"r":0.
|
| 995 |
-
"f":0.
|
| 996 |
},
|
| 997 |
"Voice":{
|
| 998 |
-
"p":0.
|
| 999 |
-
"r":0.
|
| 1000 |
-
"f":0.
|
| 1001 |
},
|
| 1002 |
"Aspect":{
|
| 1003 |
-
"p":0.
|
| 1004 |
-
"r":0.
|
| 1005 |
-
"f":0.
|
| 1006 |
},
|
| 1007 |
"Mood":{
|
| 1008 |
-
"p":0.
|
| 1009 |
-
"r":0.
|
| 1010 |
-
"f":0.
|
| 1011 |
},
|
| 1012 |
"Person":{
|
| 1013 |
-
"p":0.
|
| 1014 |
-
"r":0.
|
| 1015 |
-
"f":0.
|
| 1016 |
}
|
| 1017 |
},
|
| 1018 |
-
"tag_acc":0.
|
| 1019 |
-
"dep_uas":0.
|
| 1020 |
-
"dep_las":0.
|
| 1021 |
"dep_las_per_type":{
|
| 1022 |
"det":{
|
| 1023 |
-
"p":0.
|
| 1024 |
-
"r":0.
|
| 1025 |
-
"f":0.
|
| 1026 |
},
|
| 1027 |
"advmod":{
|
| 1028 |
-
"p":0.
|
| 1029 |
-
"r":0.
|
| 1030 |
-
"f":0.
|
| 1031 |
},
|
| 1032 |
"case":{
|
| 1033 |
-
"p":0.
|
| 1034 |
-
"r":0.
|
| 1035 |
-
"f":0.
|
| 1036 |
},
|
| 1037 |
"nmod":{
|
| 1038 |
-
"p":0.
|
| 1039 |
-
"r":0.
|
| 1040 |
-
"f":0.
|
| 1041 |
},
|
| 1042 |
"cc":{
|
| 1043 |
-
"p":0.
|
| 1044 |
-
"r":0.
|
| 1045 |
-
"f":0.
|
| 1046 |
},
|
| 1047 |
"conj":{
|
| 1048 |
-
"p":0.
|
| 1049 |
-
"r":0.
|
| 1050 |
-
"f":0.
|
| 1051 |
},
|
| 1052 |
"csubj":{
|
| 1053 |
-
"p":0.
|
| 1054 |
"r":0.1941747573,
|
| 1055 |
-
"f":0.
|
| 1056 |
},
|
| 1057 |
"obl":{
|
| 1058 |
-
"p":0.
|
| 1059 |
-
"r":0.
|
| 1060 |
-
"f":0.
|
| 1061 |
},
|
| 1062 |
"root":{
|
| 1063 |
-
"p":0.
|
| 1064 |
-
"r":0.
|
| 1065 |
-
"f":0.
|
| 1066 |
},
|
| 1067 |
"cop":{
|
| 1068 |
-
"p":0.
|
| 1069 |
-
"r":0.
|
| 1070 |
-
"f":0.
|
| 1071 |
},
|
| 1072 |
"obj":{
|
| 1073 |
-
"p":0.
|
| 1074 |
-
"r":0.
|
| 1075 |
-
"f":0.
|
| 1076 |
},
|
| 1077 |
"acl":{
|
| 1078 |
-
"p":0.
|
| 1079 |
-
"r":0.
|
| 1080 |
-
"f":0.
|
| 1081 |
},
|
| 1082 |
"xcomp":{
|
| 1083 |
-
"p":0.
|
| 1084 |
-
"r":0.
|
| 1085 |
-
"f":0.
|
| 1086 |
},
|
| 1087 |
"nsubj":{
|
| 1088 |
-
"p":0.
|
| 1089 |
-
"r":0.
|
| 1090 |
-
"f":0.
|
| 1091 |
},
|
| 1092 |
"amod":{
|
| 1093 |
-
"p":0.
|
| 1094 |
-
"r":0.
|
| 1095 |
-
"f":0.
|
| 1096 |
},
|
| 1097 |
"advcl":{
|
| 1098 |
-
"p":0.
|
| 1099 |
-
"r":0.
|
| 1100 |
-
"f":0.
|
| 1101 |
},
|
| 1102 |
"mark":{
|
| 1103 |
-
"p":0.
|
| 1104 |
-
"r":0.
|
| 1105 |
-
"f":0.
|
| 1106 |
},
|
| 1107 |
"iobj":{
|
| 1108 |
-
"p":0.
|
| 1109 |
-
"r":0.
|
| 1110 |
-
"f":0.
|
| 1111 |
},
|
| 1112 |
"dep":{
|
| 1113 |
"p":0.0,
|
| 1114 |
"r":0.0,
|
| 1115 |
"f":0.0
|
| 1116 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1117 |
"appos":{
|
| 1118 |
-
"p":0.
|
| 1119 |
-
"r":0.
|
| 1120 |
-
"f":0.
|
| 1121 |
},
|
| 1122 |
-
"
|
| 1123 |
-
"p":0.
|
| 1124 |
-
"r":0.
|
| 1125 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1126 |
},
|
| 1127 |
"parataxis":{
|
| 1128 |
"p":0.0,
|
| 1129 |
"r":0.0,
|
| 1130 |
"f":0.0
|
| 1131 |
-
},
|
| 1132 |
-
"vocative":{
|
| 1133 |
-
"p":0.3333333333,
|
| 1134 |
-
"r":0.3913043478,
|
| 1135 |
-
"f":0.36
|
| 1136 |
-
},
|
| 1137 |
-
"nummod":{
|
| 1138 |
-
"p":0.1578947368,
|
| 1139 |
-
"r":0.1875,
|
| 1140 |
-
"f":0.1714285714
|
| 1141 |
-
},
|
| 1142 |
-
"discourse":{
|
| 1143 |
-
"p":0.9375,
|
| 1144 |
-
"r":0.8823529412,
|
| 1145 |
-
"f":0.9090909091
|
| 1146 |
}
|
| 1147 |
},
|
| 1148 |
-
"sents_p":0.
|
| 1149 |
"sents_r":0.9894459103,
|
| 1150 |
-
"sents_f":0.
|
| 1151 |
-
"lemma_acc":0.
|
| 1152 |
-
"tok2vec_loss":
|
| 1153 |
-
"morphologizer_loss":
|
| 1154 |
-
"tagger_loss":
|
| 1155 |
-
"parser_loss":
|
| 1156 |
},
|
| 1157 |
"requirements":[
|
| 1158 |
|
|
|
|
| 1 |
{
|
| 2 |
"lang":"grc",
|
| 3 |
"name":"perseus_sm",
|
| 4 |
+
"version":"3.6.0",
|
| 5 |
"description":"",
|
| 6 |
"author":"",
|
| 7 |
"email":"",
|
| 8 |
"url":"",
|
| 9 |
"license":"",
|
| 10 |
+
"spacy_version":">=3.6.0,<3.7.0",
|
| 11 |
+
"spacy_git_version":"6fc153a26",
|
| 12 |
"vectors":{
|
| 13 |
"width":0,
|
| 14 |
"vectors":0,
|
|
|
|
| 961 |
|
| 962 |
],
|
| 963 |
"performance":{
|
| 964 |
+
"pos_acc":0.8915542906,
|
| 965 |
+
"morph_acc":0.8344251186,
|
| 966 |
"morph_per_feat":{
|
| 967 |
"Case":{
|
| 968 |
+
"p":0.9173730704,
|
| 969 |
+
"r":0.906693712,
|
| 970 |
+
"f":0.912002129
|
| 971 |
},
|
| 972 |
"Gender":{
|
| 973 |
+
"p":0.8755916763,
|
| 974 |
+
"r":0.8660777385,
|
| 975 |
+
"f":0.8708087223
|
| 976 |
},
|
| 977 |
"Number":{
|
| 978 |
+
"p":0.9480304286,
|
| 979 |
+
"r":0.9424228811,
|
| 980 |
+
"f":0.9452183382
|
| 981 |
},
|
| 982 |
"Degree":{
|
| 983 |
+
"p":0.5396825397,
|
| 984 |
+
"r":0.2,
|
| 985 |
+
"f":0.2918454936
|
| 986 |
},
|
| 987 |
"Tense":{
|
| 988 |
+
"p":0.7483075435,
|
| 989 |
+
"r":0.7499394233,
|
| 990 |
+
"f":0.7491225947
|
| 991 |
},
|
| 992 |
"VerbForm":{
|
| 993 |
+
"p":0.8986943907,
|
| 994 |
+
"r":0.9006542283,
|
| 995 |
+
"f":0.8996732422
|
| 996 |
},
|
| 997 |
"Voice":{
|
| 998 |
+
"p":0.8732769045,
|
| 999 |
+
"r":0.8756062076,
|
| 1000 |
+
"f":0.8744400048
|
| 1001 |
},
|
| 1002 |
"Aspect":{
|
| 1003 |
+
"p":0.7441217151,
|
| 1004 |
+
"r":0.6552984166,
|
| 1005 |
+
"f":0.6968911917
|
| 1006 |
},
|
| 1007 |
"Mood":{
|
| 1008 |
+
"p":0.8381642512,
|
| 1009 |
+
"r":0.8601883986,
|
| 1010 |
+
"f":0.8490335209
|
| 1011 |
},
|
| 1012 |
"Person":{
|
| 1013 |
+
"p":0.8780722892,
|
| 1014 |
+
"r":0.8692748092,
|
| 1015 |
+
"f":0.8736514025
|
| 1016 |
}
|
| 1017 |
},
|
| 1018 |
+
"tag_acc":0.895328876,
|
| 1019 |
+
"dep_uas":0.659948986,
|
| 1020 |
+
"dep_las":0.5802671785,
|
| 1021 |
"dep_las_per_type":{
|
| 1022 |
"det":{
|
| 1023 |
+
"p":0.8417649296,
|
| 1024 |
+
"r":0.8223708658,
|
| 1025 |
+
"f":0.8319548872
|
| 1026 |
},
|
| 1027 |
"advmod":{
|
| 1028 |
+
"p":0.6199667221,
|
| 1029 |
+
"r":0.6005802708,
|
| 1030 |
+
"f":0.610119535
|
| 1031 |
},
|
| 1032 |
"case":{
|
| 1033 |
+
"p":0.8566176471,
|
| 1034 |
+
"r":0.8655274889,
|
| 1035 |
+
"f":0.8610495196
|
| 1036 |
},
|
| 1037 |
"nmod":{
|
| 1038 |
+
"p":0.4407787994,
|
| 1039 |
+
"r":0.4391163793,
|
| 1040 |
+
"f":0.4399460189
|
| 1041 |
},
|
| 1042 |
"cc":{
|
| 1043 |
+
"p":0.4926787252,
|
| 1044 |
+
"r":0.5553398058,
|
| 1045 |
+
"f":0.522136011
|
| 1046 |
},
|
| 1047 |
"conj":{
|
| 1048 |
+
"p":0.4486626402,
|
| 1049 |
+
"r":0.4684684685,
|
| 1050 |
+
"f":0.4583516968
|
| 1051 |
},
|
| 1052 |
"csubj":{
|
| 1053 |
+
"p":0.3225806452,
|
| 1054 |
"r":0.1941747573,
|
| 1055 |
+
"f":0.2424242424
|
| 1056 |
},
|
| 1057 |
"obl":{
|
| 1058 |
+
"p":0.4875755541,
|
| 1059 |
+
"r":0.5127118644,
|
| 1060 |
+
"f":0.499827883
|
| 1061 |
},
|
| 1062 |
"root":{
|
| 1063 |
+
"p":0.8090671316,
|
| 1064 |
+
"r":0.8161829376,
|
| 1065 |
+
"f":0.8126094571
|
| 1066 |
},
|
| 1067 |
"cop":{
|
| 1068 |
+
"p":0.5895522388,
|
| 1069 |
+
"r":0.5583038869,
|
| 1070 |
+
"f":0.5735027223
|
| 1071 |
},
|
| 1072 |
"obj":{
|
| 1073 |
+
"p":0.4628339141,
|
| 1074 |
+
"r":0.5122107969,
|
| 1075 |
+
"f":0.4862721171
|
| 1076 |
},
|
| 1077 |
"acl":{
|
| 1078 |
+
"p":0.214953271,
|
| 1079 |
+
"r":0.1419753086,
|
| 1080 |
+
"f":0.1710037175
|
| 1081 |
},
|
| 1082 |
"xcomp":{
|
| 1083 |
+
"p":0.2867132867,
|
| 1084 |
+
"r":0.3005865103,
|
| 1085 |
+
"f":0.2934860415
|
| 1086 |
},
|
| 1087 |
"nsubj":{
|
| 1088 |
+
"p":0.5661971831,
|
| 1089 |
+
"r":0.4740566038,
|
| 1090 |
+
"f":0.5160462131
|
| 1091 |
},
|
| 1092 |
"amod":{
|
| 1093 |
+
"p":0.0980392157,
|
| 1094 |
+
"r":0.0367647059,
|
| 1095 |
+
"f":0.0534759358
|
| 1096 |
},
|
| 1097 |
"advcl":{
|
| 1098 |
+
"p":0.490530303,
|
| 1099 |
+
"r":0.4512195122,
|
| 1100 |
+
"f":0.4700544465
|
| 1101 |
},
|
| 1102 |
"mark":{
|
| 1103 |
+
"p":0.6933701657,
|
| 1104 |
+
"r":0.6991643454,
|
| 1105 |
+
"f":0.6962552011
|
| 1106 |
},
|
| 1107 |
"iobj":{
|
| 1108 |
+
"p":0.2924528302,
|
| 1109 |
+
"r":0.2279411765,
|
| 1110 |
+
"f":0.2561983471
|
| 1111 |
},
|
| 1112 |
"dep":{
|
| 1113 |
"p":0.0,
|
| 1114 |
"r":0.0,
|
| 1115 |
"f":0.0
|
| 1116 |
},
|
| 1117 |
+
"ccomp":{
|
| 1118 |
+
"p":0.3265306122,
|
| 1119 |
+
"r":0.2307692308,
|
| 1120 |
+
"f":0.2704225352
|
| 1121 |
+
},
|
| 1122 |
+
"nummod":{
|
| 1123 |
+
"p":0.1764705882,
|
| 1124 |
+
"r":0.1875,
|
| 1125 |
+
"f":0.1818181818
|
| 1126 |
+
},
|
| 1127 |
"appos":{
|
| 1128 |
+
"p":0.0434782609,
|
| 1129 |
+
"r":0.04,
|
| 1130 |
+
"f":0.0416666667
|
| 1131 |
},
|
| 1132 |
+
"vocative":{
|
| 1133 |
+
"p":0.4210526316,
|
| 1134 |
+
"r":0.347826087,
|
| 1135 |
+
"f":0.380952381
|
| 1136 |
+
},
|
| 1137 |
+
"discourse":{
|
| 1138 |
+
"p":1.0,
|
| 1139 |
+
"r":0.9411764706,
|
| 1140 |
+
"f":0.9696969697
|
| 1141 |
},
|
| 1142 |
"parataxis":{
|
| 1143 |
"p":0.0,
|
| 1144 |
"r":0.0,
|
| 1145 |
"f":0.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1146 |
}
|
| 1147 |
},
|
| 1148 |
+
"sents_p":0.9808195292,
|
| 1149 |
"sents_r":0.9894459103,
|
| 1150 |
+
"sents_f":0.9851138354,
|
| 1151 |
+
"lemma_acc":0.9732806324,
|
| 1152 |
+
"tok2vec_loss":36588.3470359681,
|
| 1153 |
+
"morphologizer_loss":1540.4186540842,
|
| 1154 |
+
"tagger_loss":652.3240905628,
|
| 1155 |
+
"parser_loss":15405.0840186316
|
| 1156 |
},
|
| 1157 |
"requirements":[
|
| 1158 |
|
morphologizer/cfg
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"extend":false,
|
|
|
|
| 3 |
"labels_morph":{
|
| 4 |
"Mood=Ind|Number=Sing|POS=VERB|Person=3|Tense=Pres|VerbForm=Fin|Voice=Act":"Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin|Voice=Act",
|
| 5 |
"POS=ADV":"",
|
|
|
|
| 1 |
{
|
| 2 |
"extend":false,
|
| 3 |
+
"label_smoothing":0.0,
|
| 4 |
"labels_morph":{
|
| 5 |
"Mood=Ind|Number=Sing|POS=VERB|Person=3|Tense=Pres|VerbForm=Fin|Voice=Act":"Mood=Ind|Number=Sing|Person=3|Tense=Pres|VerbForm=Fin|Voice=Act",
|
| 6 |
"POS=ADV":"",
|
morphologizer/model
CHANGED
|
Binary files a/morphologizer/model and b/morphologizer/model differ
|
|
|
parser/model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1787174
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc21fb0fef768e115393328f7d44a603e06f604119a8fe2e10f46993d4d3a92e
|
| 3 |
size 1787174
|
tagger/cfg
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"labels":[
|
| 3 |
"---------",
|
| 4 |
"--p---fa-",
|
|
|
|
| 1 |
{
|
| 2 |
+
"label_smoothing":0.0,
|
| 3 |
"labels":[
|
| 4 |
"---------",
|
| 5 |
"--p---fa-",
|
tagger/model
CHANGED
|
Binary files a/tagger/model and b/tagger/model differ
|
|
|
tok2vec/model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 34875837
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0e5d61f49c49355cfebabef521ce4fa6daac809b439029b80f35837a8cde009
|
| 3 |
size 34875837
|
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 sha256:98c9232e0838d5982674523dd78788027c3317c49964b74076872779fdc6aa7c
|
| 3 |
+
size 17958766
|