Jacobo commited on
Commit
64267e0
1 Parent(s): 833e841

Update spaCy pipeline

Browse files
README.md CHANGED
@@ -13,55 +13,55 @@ model-index:
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) |
@@ -87,16 +87,16 @@ model-index:
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 |
 
13
  metrics:
14
  - name: TAG (XPOS) Accuracy
15
  type: accuracy
16
+ value: 0.9418381406
17
  - task:
18
  name: POS
19
  type: token-classification
20
  metrics:
21
  - name: POS (UPOS) Accuracy
22
  type: accuracy
23
+ value: 0.9388354339
24
  - task:
25
  name: MORPH
26
  type: token-classification
27
  metrics:
28
  - name: Morph (UFeats) Accuracy
29
  type: accuracy
30
+ value: 0.8961217898
31
  - task:
32
  name: LEMMA
33
  type: token-classification
34
  metrics:
35
  - name: Lemma Accuracy
36
  type: accuracy
37
+ value: 0.9773461321
38
  - task:
39
  name: UNLABELED_DEPENDENCIES
40
  type: token-classification
41
  metrics:
42
  - name: Unlabeled Attachment Score (UAS)
43
  type: f_score
44
+ value: 0.7462060955
45
  - task:
46
  name: LABELED_DEPENDENCIES
47
  type: token-classification
48
  metrics:
49
  - name: Labeled Attachment Score (LAS)
50
  type: f_score
51
+ value: 0.6756388244
52
  - task:
53
  name: SENTS
54
  type: token-classification
55
  metrics:
56
  - name: Sentences F-Score
57
  type: f_score
58
+ value: 0.9890302764
59
  ---
60
  | Feature | Description |
61
  | --- | --- |
62
  | **Name** | `grc_perseus_lg` |
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** | -1 keys, 200000 unique vectors (300 dimensions) |
 
87
 
88
  | Type | Score |
89
  | --- | --- |
90
+ | `POS_ACC` | 93.88 |
91
+ | `MORPH_ACC` | 89.61 |
92
+ | `TAG_ACC` | 94.18 |
93
+ | `DEP_UAS` | 74.62 |
94
+ | `DEP_LAS` | 67.56 |
95
+ | `SENTS_P` | 98.69 |
96
+ | `SENTS_R` | 99.12 |
97
+ | `SENTS_F` | 98.90 |
98
+ | `LEMMA_ACC` | 97.73 |
99
+ | `TOK2VEC_LOSS` | 6876120.10 |
100
+ | `MORPHOLOGIZER_LOSS` | 114024.69 |
101
+ | `TAGGER_LOSS` | 41222.97 |
102
+ | `PARSER_LOSS` | 1563937.90 |
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":0.9192078263,
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
  }
 
3
  "token_p":0.9983307102,
4
  "token_r":0.9987117706,
5
  "token_f":0.998521204,
6
+ "pos_acc":0.9184223712,
7
+ "morph_acc":0.8819318507,
8
+ "morph_micro_p":0.9358108769,
9
+ "morph_micro_r":0.9294808249,
10
+ "morph_micro_f":0.9326351101,
11
  "morph_per_feat":{
12
  "Mood":{
13
+ "p":0.9355620155,
14
+ "r":0.9364694471,
15
+ "f":0.9360155114
16
  },
17
  "Number":{
18
+ "p":0.9728489484,
19
+ "r":0.9674475205,
20
+ "f":0.9701407162
21
  },
22
  "Person":{
23
+ "p":0.9309178744,
24
+ "r":0.8962790698,
25
+ "f":0.9132701422
26
  },
27
  "Tense":{
28
+ "p":0.8960899839,
29
  "r":0.8975321888,
30
+ "f":0.8968105066
31
  },
32
  "VerbForm":{
33
+ "p":0.9643813605,
34
+ "r":0.9669709989,
35
+ "f":0.9656744436
36
  },
37
  "Voice":{
38
+ "p":0.9424055719,
39
+ "r":0.9436695279,
40
+ "f":0.9430371264
41
  },
42
  "Case":{
43
+ "p":0.9465080374,
44
+ "r":0.9405288331,
45
+ "f":0.9435089625
46
  },
47
  "Gender":{
48
+ "p":0.8890201781,
49
+ "r":0.8846780029,
50
+ "f":0.8868437755
51
  },
52
  "Aspect":{
53
+ "p":0.8518518519,
54
+ "r":0.8165680473,
55
+ "f":0.833836858
56
  },
57
  "Degree":{
58
+ "p":0.75,
59
+ "r":0.2234042553,
60
+ "f":0.3442622951
61
  }
62
  },
63
+ "tag_acc":0.9216893343,
64
+ "sents_p":0.9785932722,
65
+ "sents_r":0.9800918836,
66
+ "sents_f":0.9793420046,
67
+ "dep_uas":0.7354397675,
68
+ "dep_las":0.6653928956,
69
  "dep_las_per_type":{
70
  "root":{
71
+ "p":0.8898240245,
72
+ "r":0.8905053599,
73
+ "f":0.8901645618
74
  },
75
  "advmod":{
76
+ "p":0.6593186373,
77
+ "r":0.6390831391,
78
+ "f":0.6490432038
79
  },
80
  "nsubj":{
81
+ "p":0.6545589325,
82
+ "r":0.6589552239,
83
+ "f":0.6567497211
84
  },
85
  "det":{
86
+ "p":0.8490808038,
87
+ "r":0.8295739348,
88
+ "f":0.8392140292
89
  },
90
  "nmod":{
91
+ "p":0.5724106324,
92
+ "r":0.5546181172,
93
+ "f":0.5633739287
94
  },
95
  "obj":{
96
+ "p":0.6081606218,
97
+ "r":0.6218543046,
98
+ "f":0.6149312377
99
  },
100
  "advcl":{
101
+ "p":0.5722891566,
102
+ "r":0.6663326653,
103
+ "f":0.6157407407
104
  },
105
  "cc":{
106
+ "p":0.5161707633,
107
+ "r":0.6119631902,
108
+ "f":0.56
109
  },
110
  "conj":{
111
+ "p":0.5746164575,
112
+ "r":0.5471447543,
113
+ "f":0.5605442177
114
  },
115
  "amod":{
116
+ "p":0.24,
117
+ "r":0.0827586207,
118
+ "f":0.1230769231
119
  },
120
  "cop":{
121
+ "p":0.6241134752,
122
+ "r":0.6241134752,
123
+ "f":0.6241134752
124
  },
125
  "obl":{
126
+ "p":0.6376360809,
127
+ "r":0.5882352941,
128
+ "f":0.6119402985
129
  },
130
  "case":{
131
+ "p":0.8818624044,
132
+ "r":0.8794178794,
133
+ "f":0.8806384455
134
  },
135
  "xcomp":{
136
+ "p":0.3991416309,
137
+ "r":0.3570057582,
138
+ "f":0.376899696
139
  },
140
  "csubj":{
141
+ "p":0.5,
142
+ "r":0.4358974359,
143
+ "f":0.4657534247
144
  },
145
  "mark":{
146
+ "p":0.8402366864,
147
+ "r":0.8208092486,
148
+ "f":0.8304093567
149
  },
150
  "ccomp":{
151
+ "p":0.6648648649,
152
+ "r":0.4659090909,
153
+ "f":0.5478841871
 
 
 
 
 
154
  },
155
  "dep":{
156
  "p":0.0,
157
  "r":0.0,
158
  "f":0.0
159
  },
160
+ "acl":{
161
+ "p":0.36,
162
+ "r":0.2727272727,
163
+ "f":0.3103448276
164
+ },
165
  "iobj":{
166
+ "p":0.3917525773,
167
+ "r":0.3838383838,
168
+ "f":0.387755102
169
  },
170
  "discourse":{
171
+ "p":0.7419354839,
172
+ "r":0.696969697,
173
+ "f":0.71875
174
  },
175
  "vocative":{
176
+ "p":0.4615384615,
177
+ "r":0.3703703704,
178
+ "f":0.4109589041
179
  },
180
  "parataxis":{
181
+ "p":0.2,
182
  "r":0.2222222222,
183
+ "f":0.2105263158
184
  },
185
  "appos":{
186
+ "p":0.1219512195,
187
+ "r":0.1724137931,
188
+ "f":0.1428571429
189
  },
190
  "nummod":{
191
+ "p":0.1,
192
  "r":0.3333333333,
193
+ "f":0.1538461538
194
  }
195
  },
196
+ "lemma_acc":0.9159609742,
197
+ "speed":4487.7481716415
198
  }
attribute_ruler/patterns CHANGED
Binary files a/attribute_ruler/patterns and b/attribute_ruler/patterns differ
 
config.cfg CHANGED
@@ -52,6 +52,7 @@ subword_features = true
52
  [components.morphologizer]
53
  factory = "morphologizer"
54
  extend = false
 
55
  overwrite = true
56
  scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
57
 
@@ -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"}
 
52
  [components.morphologizer]
53
  factory = "morphologizer"
54
  extend = false
55
+ label_smoothing = 0.0
56
  overwrite = true
57
  scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
58
 
 
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_lg-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bdd4a1c65fd7edc3157b60e82c8800277d4607972bac691bf14de9c975585721
3
- size 279295660
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6bc99b25f0cf64399050e83aadb3c1709ae36e25a8f9d7d022c7a48a5ff3296
3
+ size 279293334
lemmatizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39e4bd7cc76a93e28df338b870437f588562b373304ed017c70e86372846d794
3
  size 24489602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27789bec48a44e7f4651d87d904d92a159e4769a5cdb3d249ba949e92ebf22cd
3
  size 24489602
meta.json CHANGED
@@ -1,14 +1,14 @@
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,
@@ -961,198 +961,198 @@
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,
1139
  "r":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
 
 
1
  {
2
  "lang":"grc",
3
  "name":"perseus_lg",
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":300,
14
  "vectors":200000,
 
961
 
962
  ],
963
  "performance":{
964
+ "pos_acc":0.9388354339,
965
+ "morph_acc":0.8961217898,
966
  "morph_per_feat":{
967
  "Case":{
968
+ "p":0.9551815766,
969
+ "r":0.9510538848,
970
+ "f":0.9531132617
971
  },
972
  "Gender":{
973
+ "p":0.9176710386,
974
+ "r":0.9147526502,
975
+ "f":0.9162095204
976
  },
977
  "Number":{
978
+ "p":0.9778628246,
979
+ "r":0.9756663672,
980
+ "f":0.9767633611
981
  },
982
  "Degree":{
983
+ "p":0.5384615385,
984
+ "r":0.2470588235,
985
+ "f":0.3387096774
986
  },
987
  "Tense":{
988
+ "p":0.897865114,
989
+ "r":0.8967773201,
990
+ "f":0.8973208874
991
  },
992
  "VerbForm":{
993
+ "p":0.9745269287,
994
+ "r":0.9733462564,
995
+ "f":0.9739362347
996
  },
997
  "Voice":{
998
+ "p":0.945375091,
999
+ "r":0.944228904,
1000
+ "f":0.9448016499
1001
  },
1002
  "Aspect":{
1003
+ "p":0.8730569948,
1004
+ "r":0.8209500609,
1005
+ "f":0.8462021343
1006
  },
1007
  "Mood":{
1008
+ "p":0.9277996071,
1009
+ "r":0.936539415,
1010
+ "f":0.9321490254
1011
  },
1012
  "Person":{
1013
+ "p":0.9438476562,
1014
+ "r":0.9222328244,
1015
+ "f":0.9329150579
1016
  }
1017
  },
1018
+ "tag_acc":0.9418381406,
1019
+ "dep_uas":0.7462060955,
1020
+ "dep_las":0.6756388244,
1021
  "dep_las_per_type":{
1022
  "det":{
1023
+ "p":0.8861573374,
1024
+ "r":0.8706800446,
1025
+ "f":0.8783505155
1026
  },
1027
  "advmod":{
1028
+ "p":0.6887007489,
1029
+ "r":0.6818181818,
1030
+ "f":0.6852421837
1031
  },
1032
  "case":{
1033
+ "p":0.9024211299,
1034
+ "r":0.9138187221,
1035
+ "f":0.9080841639
1036
  },
1037
  "nmod":{
1038
+ "p":0.5729822553,
1039
+ "r":0.5393318966,
1040
+ "f":0.5556480711
1041
  },
1042
  "cc":{
1043
+ "p":0.6155988858,
1044
+ "r":0.6436893204,
1045
+ "f":0.6293308021
1046
  },
1047
  "conj":{
1048
+ "p":0.6214689266,
1049
+ "r":0.5945945946,
1050
+ "f":0.6077348066
1051
  },
1052
  "csubj":{
1053
+ "p":0.4637681159,
1054
+ "r":0.3106796117,
1055
+ "f":0.3720930233
1056
  },
1057
  "obl":{
1058
+ "p":0.6196105702,
1059
+ "r":0.6292372881,
1060
+ "f":0.6243868255
1061
  },
1062
  "root":{
1063
+ "p":0.8870402802,
1064
+ "r":0.890941073,
1065
+ "f":0.8889863975
1066
  },
1067
  "cop":{
1068
+ "p":0.65,
1069
+ "r":0.6431095406,
1070
+ "f":0.6465364121
1071
  },
1072
  "obj":{
1073
+ "p":0.6085343228,
1074
+ "r":0.6323907455,
1075
+ "f":0.6202332178
1076
  },
1077
  "acl":{
1078
+ "p":0.362745098,
1079
  "r":0.2283950617,
1080
+ "f":0.2803030303
1081
  },
1082
  "xcomp":{
1083
+ "p":0.4114021572,
1084
+ "r":0.3914956012,
1085
+ "f":0.4012021037
1086
  },
1087
  "nsubj":{
1088
+ "p":0.6713692946,
1089
+ "r":0.6360062893,
1090
+ "f":0.6532095277
1091
  },
1092
  "amod":{
1093
+ "p":0.2469135802,
1094
  "r":0.1470588235,
1095
+ "f":0.1843317972
1096
  },
1097
  "advcl":{
1098
+ "p":0.5465742879,
1099
+ "r":0.618466899,
1100
+ "f":0.5803024111
1101
  },
1102
  "mark":{
1103
+ "p":0.8150289017,
1104
+ "r":0.7855153203,
1105
+ "f":0.8
1106
  },
1107
  "iobj":{
1108
+ "p":0.3888888889,
1109
+ "r":0.3602941176,
1110
+ "f":0.3740458015
 
 
 
 
 
1111
  },
1112
  "dep":{
1113
  "p":0.0,
1114
  "r":0.0,
1115
  "f":0.0
1116
  },
1117
+ "ccomp":{
1118
+ "p":0.4013157895,
1119
+ "r":0.2932692308,
1120
+ "f":0.3388888889
 
 
 
 
 
1121
  },
1122
  "appos":{
1123
+ "p":0.0,
1124
+ "r":0.0,
1125
+ "f":0.0
1126
  },
1127
  "parataxis":{
1128
  "p":0.0,
1129
  "r":0.0,
1130
  "f":0.0
1131
  },
1132
+ "nummod":{
1133
+ "p":0.2,
1134
+ "r":0.1875,
1135
+ "f":0.1935483871
1136
+ },
1137
  "discourse":{
1138
+ "p":0.9411764706,
1139
+ "r":0.9411764706,
1140
+ "f":0.9411764706
1141
+ },
1142
+ "vocative":{
1143
+ "p":0.4782608696,
1144
+ "r":0.4782608696,
1145
+ "f":0.4782608696
1146
  }
1147
  },
1148
+ "sents_p":0.9868651489,
1149
+ "sents_r":0.9912049252,
1150
+ "sents_f":0.9890302764,
1151
+ "lemma_acc":0.9773461321,
1152
+ "tok2vec_loss":68761.2009886586,
1153
+ "morphologizer_loss":1140.2468731403,
1154
+ "tagger_loss":412.2296842122,
1155
+ "parser_loss":15639.3790108471
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 sha256:13cfb18ca4f2d53515c86c213e5f20868f70dfaca1c976f25147b359cfd1cd72
3
  size 1787174
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8fc558cea706a70aaf3608af29298542fe2ccbe9ba2bb8a40019843ad2ed093
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:e64db7205aa7ea10eadf2c996adf29378ab3044307579d1435438eaf82e52570
3
  size 35970008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d9f4fd7bd11ebb355078272033cdd1c546dc9de55ac6a411a2d3e724355a262
3
  size 35970008
vocab/strings.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0de656cd87b26fbc27769a617a87b62315b6acd3fb41ef03f4d4bf8300ef0fb9
3
- size 17713662
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42212c2535f6d094c557a958a13fb8a4ccb5d9fe67d2c959aa480acf4ab23196
3
+ size 17704511
vocab/vectors.cfg CHANGED
@@ -5,5 +5,6 @@
5
  "hash_count":2,
6
  "hash_seed":2166136261,
7
  "bow":"<",
8
- "eow":">"
 
9
  }
 
5
  "hash_count":2,
6
  "hash_seed":2166136261,
7
  "bow":"<",
8
+ "eow":">",
9
+ "attr":65
10
  }