Hugging Face's logo

Jacobo
/
grc_perseus_lg

Token Classification
spaCy
Ancient Greek (to 1453)
Eval Results
Model card Files Community
Jacobo commited on
Commit
833e841
•
1 Parent(s): a89bb66

Update spaCy pipeline

Browse files
Files changed (14) hide show
  1. README.md +24 -24
  2. accuracy.json +114 -114
  3. attribute_ruler/patterns +0 -0
  4. config.cfg +3 -23
  5. grc_perseus_lg-any-py3-none-any.whl +2 -2
  6. lemmatizer/cfg +0 -0
  7. lemmatizer/model +2 -2
  8. lemmatizer/trees +2 -2
  9. meta.json +116 -118
  10. morphologizer/model +0 -0
  11. parser/model +1 -1
  12. tagger/model +0 -0
  13. tok2vec/model +1 -1
  14. vocab/strings.json +2 -2
README.md CHANGED
@@ -13,57 +13,57 @@ model-index:
13
  metrics:
14
  - name: TAG (XPOS) Accuracy
15
  type: accuracy
16
- value: 0.941500655
17
  - task:
18
  name: POS
19
  type: token-classification
20
  metrics:
21
  - name: POS (UPOS) Accuracy
22
  type: accuracy
23
- value: 0.9381126621
24
  - task:
25
  name: MORPH
26
  type: token-classification
27
  metrics:
28
  - name: Morph (UFeats) Accuracy
29
  type: accuracy
30
- value: 0.8950126491
31
  - task:
32
  name: LEMMA
33
  type: token-classification
34
  metrics:
35
  - name: Lemma Accuracy
36
  type: accuracy
37
- value: 0.9524110672
38
  - task:
39
  name: UNLABELED_DEPENDENCIES
40
  type: token-classification
41
  metrics:
42
  - name: Unlabeled Attachment Score (UAS)
43
  type: f_score
44
- value: 0.7406005551
45
  - task:
46
  name: LABELED_DEPENDENCIES
47
  type: token-classification
48
  metrics:
49
  - name: Labeled Attachment Score (LAS)
50
  type: f_score
51
- value: 0.6705187727
52
  - task:
53
  name: SENTS
54
  type: token-classification
55
  metrics:
56
  - name: Sentences F-Score
57
  type: f_score
58
- value: 0.9903339192
59
  ---
60
  | Feature | Description |
61
  | --- | --- |
62
  | **Name** | `grc_perseus_lg` |
63
- | **Version** | `3.5.2` |
64
- | **spaCy** | `>=3.5.2,<3.6.0` |
65
- | **Default Pipeline** | `tok2vec`, `morphologizer`, `tagger`, `parser`, `senter`, `lemmatizer`, `attribute_ruler` |
66
- | **Components** | `tok2vec`, `morphologizer`, `tagger`, `parser`, `senter`, `lemmatizer`, `attribute_ruler` |
67
  | **Vectors** | -1 keys, 200000 unique vectors (300 dimensions) |
68
  | **Sources** | n/a |
69
  | **License** | n/a |
@@ -87,16 +87,16 @@ model-index:
87
 
88
  | Type | Score |
89
  | --- | --- |
90
- | `POS_ACC` | 93.81 |
91
- | `MORPH_ACC` | 89.50 |
92
- | `TAG_ACC` | 94.15 |
93
- | `DEP_UAS` | 74.06 |
94
- | `DEP_LAS` | 67.05 |
95
- | `SENTS_P` | 98.95 |
96
- | `SENTS_R` | 99.12 |
97
- | `SENTS_F` | 99.03 |
98
- | `LEMMA_ACC` | 95.24 |
99
- | `TOK2VEC_LOSS` | 8354232.82 |
100
- | `MORPHOLOGIZER_LOSS` | 928146.41 |
101
- | `TAGGER_LOSS` | 258195.37 |
102
- | `PARSER_LOSS` | 4514614.02 |
 
13
  metrics:
14
  - name: TAG (XPOS) Accuracy
15
  type: accuracy
16
+ value: 0.9429674971
17
  - task:
18
  name: POS
19
  type: token-classification
20
  metrics:
21
  - name: POS (UPOS) Accuracy
22
  type: accuracy
23
+ value: 0.9372543705
24
  - task:
25
  name: MORPH
26
  type: token-classification
27
  metrics:
28
  - name: Morph (UFeats) Accuracy
29
  type: accuracy
30
+ value: 0.8981998058
31
  - task:
32
  name: LEMMA
33
  type: token-classification
34
  metrics:
35
  - name: Lemma Accuracy
36
  type: accuracy
37
+ value: 0.9788368154
38
  - task:
39
  name: UNLABELED_DEPENDENCIES
40
  type: token-classification
41
  metrics:
42
  - name: Unlabeled Attachment Score (UAS)
43
  type: f_score
44
+ value: 0.7427243331
45
  - task:
46
  name: LABELED_DEPENDENCIES
47
  type: token-classification
48
  metrics:
49
  - name: Labeled Attachment Score (LAS)
50
  type: f_score
51
+ value: 0.6759631173
52
  - task:
53
  name: SENTS
54
  type: token-classification
55
  metrics:
56
  - name: Sentences F-Score
57
  type: f_score
58
+ value: 0.985977213
59
  ---
60
  | Feature | Description |
61
  | --- | --- |
62
  | **Name** | `grc_perseus_lg` |
63
+ | **Version** | `3.5.3` |
64
+ | **spaCy** | `>=3.5.3,<3.6.0` |
65
+ | **Default Pipeline** | `tok2vec`, `morphologizer`, `tagger`, `parser`, `lemmatizer`, `attribute_ruler` |
66
+ | **Components** | `tok2vec`, `morphologizer`, `tagger`, `parser`, `lemmatizer`, `attribute_ruler` |
67
  | **Vectors** | -1 keys, 200000 unique vectors (300 dimensions) |
68
  | **Sources** | n/a |
69
  | **License** | n/a |
 
87
 
88
  | Type | Score |
89
  | --- | --- |
90
+ | `POS_ACC` | 93.70 |
91
+ | `MORPH_ACC` | 89.60 |
92
+ | `TAG_ACC` | 94.07 |
93
+ | `DEP_UAS` | 74.41 |
94
+ | `DEP_LAS` | 67.42 |
95
+ | `SENTS_P` | 99.47 |
96
+ | `SENTS_R` | 99.47 |
97
+ | `SENTS_F` | 99.47 |
98
+ | `LEMMA_ACC` | 97.88 |
99
+ | `TOK2VEC_LOSS` | 8318988.01 |
100
+ | `MORPHOLOGIZER_LOSS` | 702622.15 |
101
+ | `TAGGER_LOSS` | 216101.94 |
102
+ | `PARSER_LOSS` | 3888592.92 |
accuracy.json CHANGED
@@ -3,196 +3,196 @@
3
  "token_p":0.9983307102,
4
  "token_r":0.9987117706,
5
  "token_f":0.998521204,
6
- "pos_acc":0.9179928897,
7
- "morph_acc":0.8792116064,
8
- "morph_micro_p":0.9355444673,
9
- "morph_micro_r":0.9293253251,
10
- "morph_micro_f":0.9324245261,
11
  "morph_per_feat":{
12
  "Mood":{
13
- "p":0.9439342678,
14
- "r":0.9471387003,
15
- "f":0.9455337691
16
  },
17
  "Number":{
18
- "p":0.9731466605,
19
- "r":0.9674475205,
20
- "f":0.9702887219
21
  },
22
  "Person":{
23
- "p":0.9341029341,
24
- "r":0.903255814,
25
- "f":0.9184204304
26
  },
27
  "Tense":{
28
- "p":0.8954143202,
29
- "r":0.8956545064,
30
- "f":0.8955343972
31
  },
32
  "VerbForm":{
33
- "p":0.9646017699,
34
- "r":0.9658968851,
35
- "f":0.9652488931
36
  },
37
  "Voice":{
38
- "p":0.9439528024,
39
- "r":0.9442060086,
40
- "f":0.9440793885
41
  },
42
  "Case":{
43
- "p":0.9484685995,
44
- "r":0.941792257,
45
- "f":0.9451186379
46
  },
47
  "Gender":{
48
- "p":0.8859090909,
49
- "r":0.8814218524,
50
- "f":0.8836597751
51
  },
52
  "Aspect":{
53
- "p":0.8153153153,
54
- "r":0.8032544379,
55
- "f":0.8092399404
56
  },
57
  "Degree":{
58
- "p":0.5333333333,
59
- "r":0.170212766,
60
- "f":0.2580645161
61
  }
62
  },
63
- "tag_acc":0.9199790046,
64
- "sents_p":0.9869331284,
65
- "sents_r":0.9831546708,
66
- "sents_f":0.9850402762,
67
- "dep_uas":0.7319983873,
68
- "dep_las":0.66215163,
69
  "dep_las_per_type":{
70
  "root":{
71
- "p":0.8770176787,
72
- "r":0.8736600306,
73
- "f":0.8753356348
74
  },
75
  "advmod":{
76
- "p":0.6684083601,
77
- "r":0.6460761461,
78
- "f":0.6570525484
79
  },
80
  "nsubj":{
81
- "p":0.6785150079,
82
- "r":0.6410447761,
83
- "f":0.6592478895
84
  },
85
  "det":{
86
- "p":0.8551160791,
87
- "r":0.8308270677,
88
- "f":0.8427966102
89
  },
90
  "nmod":{
91
- "p":0.5761709868,
92
- "r":0.5626110124,
93
- "f":0.5693102674
94
  },
95
  "obj":{
96
- "p":0.5941101152,
97
- "r":0.6145695364,
98
- "f":0.6041666667
99
  },
100
  "advcl":{
101
- "p":0.6148300721,
102
- "r":0.5981963928,
103
- "f":0.6063991874
104
  },
105
  "cc":{
106
- "p":0.5584082157,
107
- "r":0.6671779141,
108
- "f":0.607966457
109
  },
110
  "conj":{
111
- "p":0.5991620112,
112
- "r":0.5697211155,
113
- "f":0.5840707965
114
  },
115
  "amod":{
116
- "p":0.25,
117
- "r":0.1172413793,
118
- "f":0.1596244131
119
  },
120
  "cop":{
121
- "p":0.5862068966,
122
- "r":0.6028368794,
123
- "f":0.5944055944
124
  },
125
  "obl":{
126
- "p":0.6056851312,
127
- "r":0.5961262554,
128
- "f":0.600867679
129
  },
130
  "case":{
131
- "p":0.8842688843,
132
- "r":0.8842688843,
133
- "f":0.8842688843
134
  },
135
  "xcomp":{
136
- "p":0.3521126761,
137
- "r":0.3838771593,
138
- "f":0.3673094582
139
  },
140
  "csubj":{
141
- "p":0.3023255814,
142
- "r":0.3333333333,
143
- "f":0.3170731707
144
  },
145
  "mark":{
146
- "p":0.8717948718,
147
- "r":0.7861271676,
148
- "f":0.8267477204
149
  },
150
  "ccomp":{
151
- "p":0.4553571429,
152
- "r":0.3863636364,
153
- "f":0.4180327869
154
  },
155
  "acl":{
156
- "p":0.2909090909,
157
  "r":0.2424242424,
158
- "f":0.2644628099
159
- },
160
- "iobj":{
161
- "p":0.3707865169,
162
- "r":0.3333333333,
163
- "f":0.3510638298
164
  },
165
  "dep":{
166
  "p":0.0,
167
  "r":0.0,
168
  "f":0.0
169
  },
 
 
 
 
 
170
  "discourse":{
171
- "p":0.75,
172
- "r":0.7272727273,
173
- "f":0.7384615385
174
  },
175
  "vocative":{
176
- "p":0.5135135135,
177
  "r":0.4691358025,
178
- "f":0.4903225806
179
  },
180
  "parataxis":{
181
- "p":0.025,
182
- "r":0.1111111111,
183
- "f":0.0408163265
184
  },
185
  "appos":{
186
- "p":0.0161290323,
187
- "r":0.0344827586,
188
- "f":0.021978022
189
  },
190
  "nummod":{
191
- "p":0.05,
192
  "r":0.3333333333,
193
- "f":0.0869565217
194
  }
195
  },
196
- "lemma_acc":0.8944443119,
197
- "speed":5660.0229860201
198
  }
 
3
  "token_p":0.9983307102,
4
  "token_r":0.9987117706,
5
  "token_f":0.998521204,
6
+ "pos_acc":0.9192078263,
7
+ "morph_acc":0.881719917,
8
+ "morph_micro_p":0.9351866374,
9
+ "morph_micro_r":0.9272066398,
10
+ "morph_micro_f":0.9311795422,
11
  "morph_per_feat":{
12
  "Mood":{
13
+ "p":0.9355307804,
14
+ "r":0.9359844811,
15
+ "f":0.9357575758
16
  },
17
  "Number":{
18
+ "p":0.9705093834,
19
+ "r":0.9636446608,
20
+ "f":0.9670648399
21
  },
22
  "Person":{
23
+ "p":0.9333333333,
24
+ "r":0.8986046512,
25
+ "f":0.9156398104
26
  },
27
  "Tense":{
28
+ "p":0.8984962406,
29
+ "r":0.8975321888,
30
+ "f":0.898013956
31
  },
32
  "VerbForm":{
33
+ "p":0.9645542427,
34
+ "r":0.9645542427,
35
+ "f":0.9645542427
36
  },
37
  "Voice":{
38
+ "p":0.9406552095,
39
+ "r":0.9396459227,
40
+ "f":0.9401502952
41
  },
42
  "Case":{
43
+ "p":0.9442321689,
44
+ "r":0.9366483169,
45
+ "f":0.9404249536
46
  },
47
  "Gender":{
48
+ "p":0.8916211293,
49
+ "r":0.8854920405,
50
+ "f":0.8885460156
51
  },
52
  "Aspect":{
53
+ "p":0.8390625,
54
+ "r":0.7943786982,
55
+ "f":0.8161094225
56
  },
57
  "Degree":{
58
+ "p":0.6388888889,
59
+ "r":0.2446808511,
60
+ "f":0.3538461538
61
  }
62
  },
63
+ "tag_acc":0.9239835847,
64
+ "sents_p":0.9748283753,
65
+ "sents_r":0.97856049,
66
+ "sents_f":0.9766908674,
67
+ "dep_uas":0.7356321839,
68
+ "dep_las":0.6667922802,
69
  "dep_las_per_type":{
70
  "root":{
71
+ "p":0.8839694656,
72
+ "r":0.886676876,
73
+ "f":0.8853211009
74
  },
75
  "advmod":{
76
+ "p":0.6761744966,
77
+ "r":0.6262626263,
78
+ "f":0.6502622025
79
  },
80
  "nsubj":{
81
+ "p":0.6622222222,
82
+ "r":0.6671641791,
83
+ "f":0.6646840149
84
  },
85
  "det":{
86
+ "p":0.8597246127,
87
+ "r":0.8345864662,
88
+ "f":0.8469690547
89
  },
90
  "nmod":{
91
+ "p":0.5877792978,
92
+ "r":0.5723801066,
93
+ "f":0.5799775028
94
  },
95
  "obj":{
96
+ "p":0.5925700365,
97
+ "r":0.6443708609,
98
+ "f":0.6173857868
99
  },
100
  "advcl":{
101
+ "p":0.6216216216,
102
+ "r":0.622244489,
103
+ "f":0.6219328993
104
  },
105
  "cc":{
106
+ "p":0.5249695493,
107
+ "r":0.6610429448,
108
+ "f":0.5852002716
109
  },
110
  "conj":{
111
+ "p":0.6241032999,
112
+ "r":0.577689243,
113
+ "f":0.6
114
  },
115
  "amod":{
116
+ "p":0.2452830189,
117
+ "r":0.0896551724,
118
+ "f":0.1313131313
119
  },
120
  "cop":{
121
+ "p":0.6206896552,
122
+ "r":0.6382978723,
123
+ "f":0.6293706294
124
  },
125
  "obl":{
126
+ "p":0.6191950464,
127
+ "r":0.5738880918,
128
+ "f":0.5956813105
129
  },
130
  "case":{
131
+ "p":0.8853727145,
132
+ "r":0.8724878725,
133
+ "f":0.8788830716
134
  },
135
  "xcomp":{
136
+ "p":0.3618290258,
137
+ "r":0.349328215,
138
+ "f":0.35546875
139
  },
140
  "csubj":{
141
+ "p":0.2127659574,
142
+ "r":0.2564102564,
143
+ "f":0.2325581395
144
  },
145
  "mark":{
146
+ "p":0.8179190751,
147
+ "r":0.8179190751,
148
+ "f":0.8179190751
149
  },
150
  "ccomp":{
151
+ "p":0.5377777778,
152
+ "r":0.4583333333,
153
+ "f":0.4948875256
154
  },
155
  "acl":{
156
+ "p":0.3047619048,
157
  "r":0.2424242424,
158
+ "f":0.2700421941
 
 
 
 
 
159
  },
160
  "dep":{
161
  "p":0.0,
162
  "r":0.0,
163
  "f":0.0
164
  },
165
+ "iobj":{
166
+ "p":0.3424657534,
167
+ "r":0.2525252525,
168
+ "f":0.2906976744
169
+ },
170
  "discourse":{
171
+ "p":0.7142857143,
172
+ "r":0.7575757576,
173
+ "f":0.7352941176
174
  },
175
  "vocative":{
176
+ "p":0.5428571429,
177
  "r":0.4691358025,
178
+ "f":0.5033112583
179
  },
180
  "parataxis":{
181
+ "p":0.1818181818,
182
+ "r":0.2222222222,
183
+ "f":0.2
184
  },
185
  "appos":{
186
+ "p":0.085106383,
187
+ "r":0.1379310345,
188
+ "f":0.1052631579
189
  },
190
  "nummod":{
191
+ "p":0.0416666667,
192
  "r":0.3333333333,
193
+ "f":0.0740740741
194
  }
195
  },
196
+ "lemma_acc":0.9155315951,
197
+ "speed":4213.5364349904
198
  }
attribute_ruler/patterns CHANGED
Binary files a/attribute_ruler/patterns and b/attribute_ruler/patterns differ
 
config.cfg CHANGED
@@ -11,7 +11,7 @@ seed = 0
11
 
12
  [nlp]
13
  lang = "grc"
14
- pipeline = ["tok2vec","morphologizer","tagger","parser","senter","lemmatizer","attribute_ruler"]
15
  batch_size = 128
16
  disabled = []
17
  before_creation = null
@@ -86,26 +86,6 @@ nO = null
86
  width = ${components.tok2vec.model.encode.width}
87
  upstream = "tok2vec"
88
 
89
- [components.senter]
90
- factory = "senter"
91
- overwrite = false
92
- scorer = {"@scorers":"spacy.senter_scorer.v1"}
93
-
94
- [components.senter.model]
95
- @architectures = "spacy.Tagger.v2"
96
- nO = null
97
- normalize = false
98
-
99
- [components.senter.model.tok2vec]
100
- @architectures = "spacy.HashEmbedCNN.v2"
101
- pretrained_vectors = true
102
- width = 12
103
- depth = 1
104
- embed_size = 2000
105
- window_size = 1
106
- maxout_pieces = 2
107
- subword_features = true
108
-
109
  [components.tagger]
110
  factory = "tagger"
111
  neg_prefix = "!"
@@ -177,7 +157,7 @@ patience = 5000
177
  max_epochs = 0
178
  max_steps = 20000
179
  eval_frequency = 200
180
- frozen_components = ["lemmatizer","senter"]
181
  annotating_components = []
182
  before_to_disk = null
183
  before_update = null
@@ -197,7 +177,7 @@ t = 0.0
197
 
198
  [training.logger]
199
  @loggers = "spacy.WandbLogger.v3"
200
- project_name = "proiel"
201
  remove_config_values = ["paths.train","paths.dev","corpora.train.path","corpora.dev.path"]
202
  log_dataset_dir = "./corpus"
203
  model_log_interval = 1000
 
11
 
12
  [nlp]
13
  lang = "grc"
14
+ pipeline = ["tok2vec","morphologizer","tagger","parser","lemmatizer","attribute_ruler"]
15
  batch_size = 128
16
  disabled = []
17
  before_creation = null
 
86
  width = ${components.tok2vec.model.encode.width}
87
  upstream = "tok2vec"
88
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
89
  [components.tagger]
90
  factory = "tagger"
91
  neg_prefix = "!"
 
157
  max_epochs = 0
158
  max_steps = 20000
159
  eval_frequency = 200
160
+ frozen_components = ["lemmatizer"]
161
  annotating_components = []
162
  before_to_disk = null
163
  before_update = null
 
177
 
178
  [training.logger]
179
  @loggers = "spacy.WandbLogger.v3"
180
+ project_name = "greCy"
181
  remove_config_values = ["paths.train","paths.dev","corpora.train.path","corpora.dev.path"]
182
  log_dataset_dir = "./corpus"
183
  model_log_interval = 1000
grc_perseus_lg-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b50f460d8d3b3b8323241052a4dc54df938dfed826a230fcdba127a851938b68
3
- size 275642921
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdd4a1c65fd7edc3157b60e82c8800277d4607972bac691bf14de9c975585721
3
+ size 279295660
lemmatizer/cfg CHANGED
The diff for this file is too large to render. See raw diff
 
lemmatizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf615bba8c5f7d45fe4067080123c26a556e77975a56a34327b6b884147e0efb
3
- size 20965398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39e4bd7cc76a93e28df338b870437f588562b373304ed017c70e86372846d794
3
+ size 24489602
lemmatizer/trees CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1955a3f6c2d5cf3de0861432f755a153c2781b03abe897c1db6c972ddd3f260
3
- size 4089585
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0b4cacd6282ecfa887b731fe8aed793709e236050f81662e72cd06fe73a6458
3
+ size 5318689
meta.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "lang":"grc",
3
  "name":"perseus_lg",
4
- "version":"3.5.2",
5
  "description":"",
6
  "author":"",
7
  "email":"",
8
  "url":"",
9
  "license":"",
10
- "spacy_version":">=3.5.2,<3.6.0",
11
- "spacy_git_version":"Unknown",
12
  "vectors":{
13
  "width":300,
14
  "vectors":200000,
@@ -946,7 +946,6 @@
946
  "morphologizer",
947
  "tagger",
948
  "parser",
949
- "senter",
950
  "lemmatizer",
951
  "attribute_ruler"
952
  ],
@@ -955,7 +954,6 @@
955
  "morphologizer",
956
  "tagger",
957
  "parser",
958
- "senter",
959
  "lemmatizer",
960
  "attribute_ruler"
961
  ],
@@ -963,173 +961,178 @@
963
 
964
  ],
965
  "performance":{
966
- "pos_acc":0.9381126621,
967
- "morph_acc":0.8950126491,
968
  "morph_per_feat":{
969
  "Case":{
970
- "p":0.9593611358,
971
- "r":0.9535232384,
972
- "f":0.9564332788
973
  },
974
  "Gender":{
975
- "p":0.9113182423,
976
- "r":0.9068904594,
977
- "f":0.9090989595
978
  },
979
  "Number":{
980
- "p":0.9789568616,
981
- "r":0.9752920036,
982
- "f":0.9771209962
983
  },
984
  "Degree":{
985
- "p":0.675,
986
- "r":0.3176470588,
987
- "f":0.432
988
  },
989
  "Tense":{
990
- "p":0.896151053,
991
- "r":0.8970196268,
992
- "f":0.8965851296
993
  },
994
  "VerbForm":{
995
- "p":0.9750665698,
996
- "r":0.9760116307,
997
- "f":0.9755388714
998
  },
999
  "Voice":{
1000
- "p":0.9496246064,
1001
- "r":0.9507759457,
1002
- "f":0.9501999273
1003
  },
1004
  "Aspect":{
1005
- "p":0.8443877551,
1006
- "r":0.8063337393,
1007
- "f":0.8249221184
1008
  },
1009
  "Mood":{
1010
- "p":0.9327442317,
1011
- "r":0.941993059,
1012
- "f":0.9373458313
1013
  },
1014
  "Person":{
1015
- "p":0.9452054795,
1016
- "r":0.9217557252,
1017
- "f":0.9333333333
1018
  }
1019
  },
1020
- "tag_acc":0.941500655,
1021
- "dep_uas":0.7406005551,
1022
- "dep_las":0.6705187727,
1023
  "dep_las_per_type":{
1024
  "det":{
1025
- "p":0.8930889653,
1026
- "r":0.8691936083,
1027
- "f":0.8809792844
1028
  },
1029
  "advmod":{
1030
- "p":0.6954800396,
1031
- "r":0.6795615732,
1032
- "f":0.6874286646
1033
  },
1034
  "case":{
1035
- "p":0.901026393,
1036
- "r":0.9130757801,
1037
- "f":0.9070110701
1038
  },
1039
  "nmod":{
1040
- "p":0.5503282276,
1041
- "r":0.5420258621,
1042
- "f":0.546145494
1043
  },
1044
  "cc":{
1045
- "p":0.6397459165,
1046
- "r":0.6844660194,
1047
- "f":0.6613508443
1048
  },
1049
  "conj":{
1050
- "p":0.626705653,
1051
- "r":0.5792792793,
1052
- "f":0.6020599251
1053
  },
1054
  "csubj":{
1055
- "p":0.4050632911,
1056
- "r":0.3106796117,
1057
- "f":0.3516483516
1058
  },
1059
  "obl":{
1060
- "p":0.5914051842,
1061
- "r":0.6122881356,
1062
- "f":0.6016655101
1063
  },
1064
  "root":{
1065
- "p":0.8814749781,
1066
- "r":0.8830255057,
1067
- "f":0.8822495606
1068
  },
1069
  "cop":{
1070
- "p":0.6765799257,
1071
- "r":0.6431095406,
1072
- "f":0.6594202899
1073
  },
1074
  "obj":{
1075
- "p":0.5807807808,
1076
- "r":0.6214652956,
1077
- "f":0.6004346476
1078
  },
1079
  "acl":{
1080
- "p":0.3130434783,
1081
- "r":0.2222222222,
1082
- "f":0.2599277978
1083
  },
1084
  "xcomp":{
1085
- "p":0.3653846154,
1086
- "r":0.417888563,
1087
- "f":0.389876881
1088
  },
1089
  "nsubj":{
1090
- "p":0.6964448496,
1091
- "r":0.6006289308,
1092
- "f":0.6449978894
1093
  },
1094
  "amod":{
1095
- "p":0.253164557,
1096
  "r":0.1470588235,
1097
- "f":0.1860465116
1098
  },
1099
  "advcl":{
1100
- "p":0.5992714026,
1101
- "r":0.5731707317,
1102
- "f":0.5859305432
1103
  },
1104
  "mark":{
1105
- "p":0.8,
1106
- "r":0.7688022284,
1107
- "f":0.7840909091
1108
  },
1109
  "iobj":{
1110
- "p":0.4166666667,
1111
- "r":0.4411764706,
1112
- "f":0.4285714286
1113
  },
1114
  "ccomp":{
1115
- "p":0.3097345133,
1116
- "r":0.3365384615,
1117
- "f":0.3225806452
1118
  },
1119
  "dep":{
1120
  "p":0.0,
1121
  "r":0.0,
1122
  "f":0.0
1123
  },
1124
- "appos":{
1125
- "p":0.125,
1126
- "r":0.12,
1127
- "f":0.1224489796
1128
- },
1129
  "nummod":{
1130
- "p":0.2592592593,
1131
  "r":0.4375,
1132
- "f":0.3255813953
 
 
 
 
 
 
 
 
 
 
1133
  },
1134
  "parataxis":{
1135
  "p":0.0,
@@ -1137,24 +1140,19 @@
1137
  "f":0.0
1138
  },
1139
  "discourse":{
1140
- "p":0.9375,
1141
  "r":0.8823529412,
1142
- "f":0.9090909091
1143
- },
1144
- "vocative":{
1145
- "p":0.5789473684,
1146
- "r":0.4782608696,
1147
- "f":0.5238095238
1148
  }
1149
  },
1150
- "sents_p":0.9894644425,
1151
- "sents_r":0.9912049252,
1152
- "sents_f":0.9903339192,
1153
- "lemma_acc":0.9524110672,
1154
- "tok2vec_loss":83542.3282417511,
1155
- "morphologizer_loss":9281.4641113281,
1156
- "tagger_loss":2581.9537159204,
1157
- "parser_loss":45146.1402039352
1158
  },
1159
  "requirements":[
1160
 
 
1
  {
2
  "lang":"grc",
3
  "name":"perseus_lg",
4
+ "version":"3.5.3",
5
  "description":"",
6
  "author":"",
7
  "email":"",
8
  "url":"",
9
  "license":"",
10
+ "spacy_version":">=3.5.3,<3.6.0",
11
+ "spacy_git_version":"512241e12",
12
  "vectors":{
13
  "width":300,
14
  "vectors":200000,
 
946
  "morphologizer",
947
  "tagger",
948
  "parser",
 
949
  "lemmatizer",
950
  "attribute_ruler"
951
  ],
 
954
  "morphologizer",
955
  "tagger",
956
  "parser",
 
957
  "lemmatizer",
958
  "attribute_ruler"
959
  ],
 
961
 
962
  ],
963
  "performance":{
964
+ "pos_acc":0.9372543705,
965
+ "morph_acc":0.8981998058,
966
  "morph_per_feat":{
967
  "Case":{
968
+ "p":0.9575865129,
969
+ "r":0.9517594144,
970
+ "f":0.9546640718
971
  },
972
  "Gender":{
973
+ "p":0.9187006302,
974
+ "r":0.9143992933,
975
+ "f":0.9165449152
976
  },
977
  "Number":{
978
+ "p":0.9770900623,
979
+ "r":0.9739442947,
980
+ "f":0.9755146425
981
  },
982
  "Degree":{
983
+ "p":0.6233766234,
984
+ "r":0.2823529412,
985
+ "f":0.3886639676
986
  },
987
  "Tense":{
988
+ "p":0.9025392987,
989
+ "r":0.9042888297,
990
+ "f":0.9034132171
991
  },
992
  "VerbForm":{
993
+ "p":0.9736396614,
994
+ "r":0.9755270172,
995
+ "f":0.9745824256
996
  },
997
  "Voice":{
998
+ "p":0.946782777,
999
+ "r":0.9490785645,
1000
+ "f":0.9479292807
1001
  },
1002
  "Aspect":{
1003
+ "p":0.8759894459,
1004
+ "r":0.8087697929,
1005
+ "f":0.841038632
1006
  },
1007
  "Mood":{
1008
+ "p":0.9270680372,
1009
+ "r":0.9390183441,
1010
+ "f":0.9330049261
1011
  },
1012
  "Person":{
1013
+ "p":0.943957115,
1014
+ "r":0.9241412214,
1015
+ "f":0.9339440694
1016
  }
1017
  },
1018
+ "tag_acc":0.9429674971,
1019
+ "dep_uas":0.7427243331,
1020
+ "dep_las":0.6759631173,
1021
  "dep_las_per_type":{
1022
  "det":{
1023
+ "p":0.8862685432,
1024
+ "r":0.8658491267,
1025
+ "f":0.8759398496
1026
  },
1027
  "advmod":{
1028
+ "p":0.7145287513,
1029
+ "r":0.6769825919,
1030
+ "f":0.6952491309
1031
  },
1032
  "case":{
1033
+ "p":0.9119822485,
1034
+ "r":0.9160475483,
1035
+ "f":0.9140103781
1036
  },
1037
  "nmod":{
1038
+ "p":0.5823863636,
1039
+ "r":0.552262931,
1040
+ "f":0.5669247788
1041
  },
1042
  "cc":{
1043
+ "p":0.6079295154,
1044
+ "r":0.6699029126,
1045
+ "f":0.6374133949
1046
  },
1047
  "conj":{
1048
+ "p":0.6175637394,
1049
+ "r":0.5891891892,
1050
+ "f":0.6030428769
1051
  },
1052
  "csubj":{
1053
+ "p":0.4054054054,
1054
+ "r":0.2912621359,
1055
+ "f":0.3389830508
1056
  },
1057
  "obl":{
1058
+ "p":0.6044034091,
1059
+ "r":0.6009887006,
1060
+ "f":0.6026912181
1061
  },
1062
  "root":{
1063
+ "p":0.8855895197,
1064
+ "r":0.8918205805,
1065
+ "f":0.888694128
1066
  },
1067
  "cop":{
1068
+ "p":0.6818181818,
1069
+ "r":0.6890459364,
1070
+ "f":0.6854130053
1071
  },
1072
  "obj":{
1073
+ "p":0.5670800451,
1074
+ "r":0.646529563,
1075
+ "f":0.6042042042
1076
  },
1077
  "acl":{
1078
+ "p":0.3032786885,
1079
+ "r":0.2283950617,
1080
+ "f":0.2605633803
1081
  },
1082
  "xcomp":{
1083
+ "p":0.4141732283,
1084
+ "r":0.3856304985,
1085
+ "f":0.3993925588
1086
  },
1087
  "nsubj":{
1088
+ "p":0.6595918367,
1089
+ "r":0.6352201258,
1090
+ "f":0.6471766119
1091
  },
1092
  "amod":{
1093
+ "p":0.3333333333,
1094
  "r":0.1470588235,
1095
+ "f":0.2040816327
1096
  },
1097
  "advcl":{
1098
+ "p":0.5998225377,
1099
+ "r":0.5888501742,
1100
+ "f":0.5942857143
1101
  },
1102
  "mark":{
1103
+ "p":0.7624020888,
1104
+ "r":0.8133704735,
1105
+ "f":0.7870619946
1106
  },
1107
  "iobj":{
1108
+ "p":0.4318181818,
1109
+ "r":0.2794117647,
1110
+ "f":0.3392857143
1111
  },
1112
  "ccomp":{
1113
+ "p":0.3820754717,
1114
+ "r":0.3894230769,
1115
+ "f":0.3857142857
1116
  },
1117
  "dep":{
1118
  "p":0.0,
1119
  "r":0.0,
1120
  "f":0.0
1121
  },
 
 
 
 
 
1122
  "nummod":{
1123
+ "p":0.2413793103,
1124
  "r":0.4375,
1125
+ "f":0.3111111111
1126
+ },
1127
+ "vocative":{
1128
+ "p":0.5,
1129
+ "r":0.5217391304,
1130
+ "f":0.5106382979
1131
+ },
1132
+ "appos":{
1133
+ "p":0.1,
1134
+ "r":0.08,
1135
+ "f":0.0888888889
1136
  },
1137
  "parataxis":{
1138
  "p":0.0,
 
1140
  "f":0.0
1141
  },
1142
  "discourse":{
1143
+ "p":0.8823529412,
1144
  "r":0.8823529412,
1145
+ "f":0.8823529412
 
 
 
 
 
1146
  }
1147
  },
1148
+ "sents_p":0.9825327511,
1149
+ "sents_r":0.9894459103,
1150
+ "sents_f":0.985977213,
1151
+ "lemma_acc":0.9788368154,
1152
+ "tok2vec_loss":69239.8042737423,
1153
+ "morphologizer_loss":1246.8738424778,
1154
+ "tagger_loss":522.4041499092,
1155
+ "parser_loss":15742.1677297733
1156
  },
1157
  "requirements":[
1158
 
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:f48ecbdcbd1ca93c9a150399eda4f8494d2281e95e2b10953365ccaece7106a2
3
  size 1787174
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13cfb18ca4f2d53515c86c213e5f20868f70dfaca1c976f25147b359cfd1cd72
3
  size 1787174
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 sha256:6047985b2a7fcbe192a94f3d1f4091da317ba478419b29b507d81f88020117c5
3
  size 35970008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e64db7205aa7ea10eadf2c996adf29378ab3044307579d1435438eaf82e52570
3
  size 35970008
vocab/strings.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:504bca4cbc93122e97f6a171f4a7a621aed5c1ff274b1441abd84f9de9064e5b
3
- size 11874654
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0de656cd87b26fbc27769a617a87b62315b6acd3fb41ef03f4d4bf8300ef0fb9
3
+ size 17713662