EC2 Default User commited on
Commit
c636104
1 Parent(s): 53b5461

Update spaCy pipeline

Browse files
.gitattributes CHANGED
@@ -19,3 +19,5 @@
19
  *strings.json filter=lfs diff=lfs merge=lfs -text
20
  vectors filter=lfs diff=lfs merge=lfs -text
21
  model filter=lfs diff=lfs merge=lfs -text
 
 
19
  *strings.json filter=lfs diff=lfs merge=lfs -text
20
  vectors filter=lfs diff=lfs merge=lfs -text
21
  model filter=lfs diff=lfs merge=lfs -text
22
+ *key2row filter=lfs diff=lfs merge=lfs -text
23
+ *tokenizer filter=lfs diff=lfs merge=lfs -text
LICENSES_SOURCES CHANGED
@@ -105,6 +105,8 @@ END OF TERMS AND CONDITIONS```
105
  * License: CC BY 4.0
106
 
107
  ```
 
 
108
  By exercising the Licensed Rights (defined below), You accept and agree to be bound by the terms and conditions of this Creative Commons Attribution 4.0 International Public License ("Public License"). To the extent this Public License may be interpreted as a contract, You are granted the Licensed Rights in consideration of Your acceptance of these terms and conditions, and the Licensor grants You such rights in consideration of benefits the Licensor receives from making the Licensed Material available under these terms and conditions.
109
 
110
  Section 1 – Definitions.
105
  * License: CC BY 4.0
106
 
107
  ```
108
+ Creative Commons Attribution 4.0 International Public License
109
+
110
  By exercising the Licensed Rights (defined below), You accept and agree to be bound by the terms and conditions of this Creative Commons Attribution 4.0 International Public License ("Public License"). To the extent this Public License may be interpreted as a contract, You are granted the Licensed Rights in consideration of Your acceptance of these terms and conditions, and the Licensor grants You such rights in consideration of benefits the Licensor receives from making the Licensed Material available under these terms and conditions.
111
 
112
  Section 1 – Definitions.
README.md CHANGED
@@ -14,47 +14,62 @@ model-index:
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
- value: 0.8332265556
18
  - name: NER Recall
19
  type: recall
20
- value: 0.8329930747
21
  - name: NER F Score
22
  type: f_score
23
- value: 0.8331097988
 
 
 
 
 
 
 
24
  - task:
25
  name: POS
26
  type: token-classification
27
  metrics:
28
- - name: POS Accuracy
29
  type: accuracy
30
- value: 0.9448023502
31
  - task:
32
- name: SENTER
33
  type: token-classification
34
  metrics:
35
- - name: SENTER Precision
36
- type: precision
37
- value: 0.8782816229
38
- - name: SENTER Recall
39
- type: recall
40
- value: 0.8932038835
41
- - name: SENTER F Score
42
- type: f_score
43
- value: 0.8856799037
44
  - task:
45
- name: UNLABELED_DEPENDENCIES
46
  type: token-classification
47
  metrics:
48
- - name: Unlabeled Dependencies Accuracy
49
  type: accuracy
50
- value: 0.8967353554
 
 
 
 
 
 
 
51
  - task:
52
  name: LABELED_DEPENDENCIES
53
  type: token-classification
54
  metrics:
55
- - name: Labeled Dependencies Accuracy
56
- type: accuracy
57
- value: 0.8967353554
 
 
 
 
 
 
 
58
  ---
59
  ### Details: https://spacy.io/models/fr#fr_core_news_md
60
 
@@ -63,8 +78,8 @@ French pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, s
63
  | Feature | Description |
64
  | --- | --- |
65
  | **Name** | `fr_core_news_md` |
66
- | **Version** | `3.2.0` |
67
- | **spaCy** | `>=3.2.0,<3.3.0` |
68
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
69
  | **Components** | `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |
70
  | **Vectors** | 500000 keys, 20000 unique vectors (300 dimensions) |
@@ -76,13 +91,12 @@ French pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, s
76
 
77
  <details>
78
 
79
- <summary>View label scheme (238 labels for 4 components)</summary>
80
 
81
  | Component | Labels |
82
  | --- | --- |
83
  | **`morphologizer`** | `POS=PROPN`, `Gender=Fem\|Number=Sing\|POS=DET\|PronType=Dem`, `Gender=Fem\|Number=Sing\|POS=NOUN`, `Number=Plur\|POS=PRON\|Person=1`, `Mood=Ind\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin`, `POS=SCONJ`, `POS=ADP`, `Definite=Def\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Art`, `NumType=Ord\|POS=ADJ`, `Gender=Masc\|Number=Sing\|POS=NOUN`, `POS=PUNCT`, `Gender=Masc\|Number=Sing\|POS=PROPN`, `Number=Plur\|POS=ADJ`, `Gender=Masc\|Number=Plur\|POS=NOUN`, `Definite=Ind\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Art`, `Number=Sing\|POS=ADJ`, `Mood=Ind\|Number=Sing\|POS=VERB\|Person=3\|Tense=Imp\|VerbForm=Fin`, `POS=ADV`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=3\|Tense=Past\|VerbForm=Fin`, `Gender=Fem\|Number=Sing\|POS=VERB\|Tense=Past\|VerbForm=Part\|Voice=Pass`, `Definite=Def\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Art`, `Gender=Fem\|Number=Sing\|POS=PROPN`, `Definite=Def\|Number=Sing\|POS=DET\|PronType=Art`, `NumType=Card\|POS=NUM`, `Definite=Def\|Number=Plur\|POS=DET\|PronType=Art`, `Gender=Masc\|Number=Plur\|POS=ADJ`, `POS=CCONJ`, `Gender=Fem\|Number=Plur\|POS=NOUN`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin`, `Gender=Masc\|Number=Sing\|POS=VERB\|Tense=Past\|VerbForm=Part`, `Gender=Fem\|Number=Plur\|POS=ADJ`, `POS=ADJ`, `Mood=Ind\|Number=Sing\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin`, `POS=PRON\|PronType=Rel`, `Number=Sing\|POS=DET\|Poss=Yes`, `Definite=Def\|Gender=Masc\|Number=Sing\|POS=ADP\|PronType=Art`, `Definite=Def\|Number=Plur\|POS=ADP\|PronType=Art`, `Definite=Ind\|Number=Plur\|POS=DET\|PronType=Art`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=3\|Tense=Past\|VerbForm=Fin`, `Gender=Masc\|Number=Plur\|POS=VERB\|Tense=Past\|VerbForm=Part\|Voice=Pass`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin`, `POS=VERB\|VerbForm=Inf`, `Gender=Fem\|Number=Sing\|POS=ADJ`, `Gender=Masc\|Number=Sing\|POS=PRON\|Person=3`, `Number=Plur\|POS=DET`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Gender=Masc\|Number=Sing\|POS=ADJ`, `Gender=Masc\|Number=Sing\|POS=DET\|PronType=Dem`, `POS=ADV\|PronType=Int`, `POS=VERB\|Tense=Pres\|VerbForm=Part`, `Gender=Fem\|Number=Sing\|POS=VERB\|Tense=Past\|VerbForm=Part`, `Definite=Ind\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Art`, `Gender=Masc\|POS=ADJ`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=3\|Tense=Fut\|VerbForm=Fin`, `Number=Plur\|POS=DET\|Poss=Yes`, `POS=AUX\|VerbForm=Inf`, `Gender=Masc\|Number=Sing\|POS=VERB\|Tense=Past\|VerbForm=Part\|Voice=Pass`, `Gender=Masc\|POS=VERB\|Tense=Past\|VerbForm=Part`, `POS=ADV\|Polarity=Neg`, `Definite=Ind\|Number=Sing\|POS=DET\|PronType=Art`, `Gender=Fem\|Number=Sing\|POS=PRON\|Person=3`, `POS=PRON\|Person=3\|Reflex=Yes`, `Gender=Masc\|POS=NOUN`, `POS=AUX\|Tense=Past\|VerbForm=Part`, `POS=PRON\|Person=3`, `Number=Plur\|POS=NOUN`, `NumType=Ord\|Number=Sing\|POS=ADJ`, `POS=VERB\|Tense=Past\|VerbForm=Part`, `POS=AUX\|Tense=Pres\|VerbForm=Part`, `Gender=Masc\|Number=Plur\|POS=VERB\|Tense=Past\|VerbForm=Part`, `Number=Sing\|POS=PRON\|Person=3`, `Number=Sing\|POS=NOUN`, `Gender=Masc\|Number=Plur\|POS=PRON\|Person=3`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=3\|Tense=Imp\|VerbForm=Fin`, `Gender=Fem\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Number=Plur\|POS=PROPN`, `Number=Sing\|POS=PROPN`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=3\|Tense=Imp\|VerbForm=Fin`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Gender=Masc\|Number=Plur\|POS=PRON\|PronType=Dem`, `Gender=Masc\|Number=Sing\|POS=DET`, `Gender=Fem\|Number=Sing\|POS=DET\|Poss=Yes`, `Gender=Masc\|POS=PRON`, `POS=NOUN`, `Mood=Ind\|Number=Sing\|POS=VERB\|Person=3\|Tense=Fut\|VerbForm=Fin`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=3\|Tense=Fut\|VerbForm=Fin`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Number=Plur\|POS=PRON`, `Gender=Masc\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=3\|Tense=Fut\|VerbForm=Fin`, `Gender=Fem\|Number=Plur\|POS=VERB\|Tense=Past\|VerbForm=Part\|Voice=Pass`, `Number=Sing\|POS=PRON`, `Number=Sing\|POS=PRON\|PronType=Dem`, `Mood=Ind\|POS=VERB\|VerbForm=Fin`, `Number=Plur\|POS=DET\|PronType=Dem`, `Gender=Masc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Gender=Masc\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Gender=Masc\|Number=Sing\|POS=PRON`, `Gender=Masc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Gender=Masc\|Number=Sing\|POS=PRON\|PronType=Rel`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=3\|Tense=Imp\|VerbForm=Fin`, `Mood=Sub\|Number=Sing\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Gender=Masc\|NumType=Ord\|Number=Sing\|POS=ADJ`, `POS=PRON`, `POS=NUM`, `Gender=Fem\|POS=NOUN`, `Gender=Fem\|Number=Plur\|POS=PRON`, `Number=Plur\|POS=PRON\|Person=3`, `Number=Sing\|POS=VERB\|Tense=Past\|VerbForm=Part`, `Number=Sing\|POS=PRON\|Person=1`, `Mood=Ind\|Number=Sing\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Mood=Sub\|Number=Sing\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin`, `Gender=Fem\|Number=Sing\|POS=PRON`, `Gender=Fem\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Mood=Sub\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin`, `POS=INTJ`, `Number=Plur\|POS=PRON\|Person=2`, `NumType=Card\|POS=PRON`, `Definite=Ind\|Gender=Fem\|Number=Plur\|POS=DET\|PronType=Art`, `Gender=Fem\|Number=Plur\|POS=VERB\|Tense=Past\|VerbForm=Part`, `NumType=Card\|POS=NOUN`, `POS=PRON\|PronType=Int`, `Gender=Fem\|Number=Plur\|POS=PRON\|Person=3`, `Gender=Fem\|Number=Sing\|POS=DET`, `Mood=Cnd\|Number=Sing\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Gender=Fem\|Number=Plur\|POS=DET`, `Mood=Sub\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Definite=Ind\|Gender=Masc\|Number=Plur\|POS=DET\|PronType=Art`, `Mood=Cnd\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Gender=Masc\|Number=Sing\|POS=PRON\|PronType=Dem`, `Gender=Masc\|Number=Plur\|POS=PROPN`, `Mood=Cnd\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Gender=Fem\|Number=Sing\|POS=PRON\|PronType=Dem`, `Number=Sing\|POS=DET`, `Gender=Masc\|NumType=Card\|Number=Plur\|POS=NOUN`, `Gender=Fem\|Number=Plur\|POS=PRON\|PronType=Dem`, `Mood=Ind\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Gender=Fem\|POS=PRON`, `Gender=Masc\|POS=VERB\|Tense=Past\|VerbForm=Part\|Voice=Pass`, `Gender=Fem\|Number=Sing\|POS=PRON\|PronType=Rel`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=1\|Tense=Imp\|VerbForm=Fin`, `Mood=Cnd\|Number=Plur\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Gender=Masc\|Number=Sing\|POS=AUX\|Tense=Past\|VerbForm=Part`, `POS=X`, `POS=SYM`, `Mood=Imp\|Number=Plur\|POS=VERB\|Person=2\|Tense=Pres\|VerbForm=Fin`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=2\|Tense=Pres\|VerbForm=Fin`, `Gender=Masc\|Number=Sing\|POS=DET\|PronType=Int`, `Gender=Fem\|Number=Plur\|POS=DET\|PronType=Int`, `POS=DET`, `Gender=Masc\|Number=Plur\|POS=PRON`, `Mood=Sub\|Number=Plur\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Mood=Ind\|POS=VERB\|Person=3\|VerbForm=Fin`, `Number=Sing\|POS=VERB\|Tense=Past\|VerbForm=Part\|Voice=Pass`, `Mood=Cnd\|Number=Plur\|POS=VERB\|Person=2\|Tense=Pres\|VerbForm=Fin`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=2\|Tense=Pres\|VerbForm=Fin`, `Gender=Fem\|Number=Sing\|POS=DET\|PronType=Int`, `Gender=Masc\|Number=Plur\|POS=DET`, `Gender=Fem\|Number=Plur\|POS=PRON\|PronType=Rel`, `Number=Plur\|POS=VERB\|Tense=Past\|VerbForm=Part\|Voice=Pass`, `Gender=Masc\|Number=Plur\|POS=PRON\|PronType=Rel`, `POS=VERB\|Tense=Past\|VerbForm=Part\|Voice=Pass`, `Gender=Fem\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=2\|Tense=Fut\|VerbForm=Fin`, `Mood=Imp\|POS=VERB\|Tense=Pres\|VerbForm=Fin`, `Number=Plur\|POS=PRON\|Person=2\|Reflex=Yes`, `Mood=Cnd\|Number=Sing\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Number=Plur\|POS=PRON\|Person=1\|Reflex=Yes`, `Gender=Masc\|NumType=Card\|Number=Sing\|POS=NOUN`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=1\|Tense=Fut\|VerbForm=Fin`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=1\|Tense=Fut\|VerbForm=Fin`, `Number=Sing\|POS=PRON\|Person=1\|Reflex=Yes`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=1\|Tense=Imp\|VerbForm=Fin`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=1\|Tense=Imp\|VerbForm=Fin`, `Mood=Ind\|Number=Sing\|POS=VERB\|Person=1\|Tense=Imp\|VerbForm=Fin`, `Mood=Sub\|Number=Sing\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Gender=Masc\|POS=PROPN`, `Mood=Cnd\|Number=Plur\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `Mood=Sub\|Number=Sing\|POS=AUX\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Number=Plur\|POS=PRON\|Person=2\|PronType=Prs`, `Mood=Ind\|Number=Sing\|POS=VERB\|Person=1\|Tense=Fut\|VerbForm=Fin`, `Gender=Fem\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Mood=Cnd\|Number=Sing\|POS=AUX\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Mood=Sub\|Number=Plur\|POS=AUX\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Mood=Imp\|Number=Plur\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Mood=Sub\|Number=Plur\|POS=AUX\|Person=2\|Tense=Pres\|VerbForm=Fin`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=2\|Tense=Imp\|VerbForm=Fin`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=2\|Tense=Imp\|VerbForm=Fin`, `Number=Plur\|POS=VERB\|Tense=Past\|VerbForm=Part`, `Gender=Fem\|Number=Plur\|POS=PROPN`, `Gender=Masc\|NumType=Card\|POS=NUM` |
84
  | **`parser`** | `ROOT`, `acl`, `acl:relcl`, `advcl`, `advmod`, `amod`, `appos`, `aux:pass`, `aux:tense`, `case`, `cc`, `ccomp`, `conj`, `cop`, `dep`, `det`, `expl:comp`, `expl:pass`, `expl:subj`, `fixed`, `flat:foreign`, `flat:name`, `iobj`, `mark`, `nmod`, `nsubj`, `nsubj:pass`, `nummod`, `obj`, `obl:agent`, `obl:arg`, `obl:mod`, `parataxis`, `punct`, `vocative`, `xcomp` |
85
- | **`senter`** | `I`, `S` |
86
  | **`ner`** | `LOC`, `MISC`, `ORG`, `PER` |
87
 
88
  </details>
@@ -95,18 +109,18 @@ French pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, s
95
  | `TOKEN_P` | 98.44 |
96
  | `TOKEN_R` | 98.96 |
97
  | `TOKEN_F` | 98.70 |
98
- | `POS_ACC` | 97.35 |
99
- | `MORPH_ACC` | 96.46 |
100
- | `MORPH_MICRO_P` | 98.70 |
101
- | `MORPH_MICRO_R` | 97.89 |
102
- | `MORPH_MICRO_F` | 98.30 |
103
- | `SENTS_P` | 87.83 |
104
- | `SENTS_R` | 89.32 |
105
- | `SENTS_F` | 88.57 |
106
- | `DEP_UAS` | 89.67 |
107
- | `DEP_LAS` | 85.80 |
108
- | `TAG_ACC` | 94.48 |
109
- | `LEMMA_ACC` | 90.70 |
110
- | `ENTS_P` | 83.32 |
111
- | `ENTS_R` | 83.30 |
112
- | `ENTS_F` | 83.31 |
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
+ value: 0.8317787005
18
  - name: NER Recall
19
  type: recall
20
+ value: 0.8299307474
21
  - name: NER F Score
22
  type: f_score
23
+ value: 0.8308536964
24
+ - task:
25
+ name: TAG
26
+ type: token-classification
27
+ metrics:
28
+ - name: TAG (XPOS) Accuracy
29
+ type: accuracy
30
+ value: 0.9424375161
31
  - task:
32
  name: POS
33
  type: token-classification
34
  metrics:
35
+ - name: POS (UPOS) Accuracy
36
  type: accuracy
37
+ value: 0.9710899253
38
  - task:
39
+ name: MORPH
40
  type: token-classification
41
  metrics:
42
+ - name: Morph (UFeats) Accuracy
43
+ type: accuracy
44
+ value: 0.9620122674
 
 
 
 
 
 
45
  - task:
46
+ name: LEMMA
47
  type: token-classification
48
  metrics:
49
+ - name: Lemma Accuracy
50
  type: accuracy
51
+ value: 0.9063912865
52
+ - task:
53
+ name: UNLABELED_DEPENDENCIES
54
+ type: token-classification
55
+ metrics:
56
+ - name: Unlabeled Attachment Score (UAS)
57
+ type: f_score
58
+ value: 0.8977489729
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
+ - name: Labeled Attachment Score (LAS)
64
+ type: f_score
65
+ value: 0.8591264102
66
+ - task:
67
+ name: SENTS
68
+ type: token-classification
69
+ metrics:
70
+ - name: Sentences F-Score
71
+ type: f_score
72
+ value: 0.8646706587
73
  ---
74
  ### Details: https://spacy.io/models/fr#fr_core_news_md
75
 
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `fr_core_news_md` |
81
+ | **Version** | `3.3.0` |
82
+ | **spaCy** | `>=3.3.0.dev0,<3.4.0` |
83
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
84
  | **Components** | `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |
85
  | **Vectors** | 500000 keys, 20000 unique vectors (300 dimensions) |
91
 
92
  <details>
93
 
94
+ <summary>View label scheme (236 labels for 3 components)</summary>
95
 
96
  | Component | Labels |
97
  | --- | --- |
98
  | **`morphologizer`** | `POS=PROPN`, `Gender=Fem\|Number=Sing\|POS=DET\|PronType=Dem`, `Gender=Fem\|Number=Sing\|POS=NOUN`, `Number=Plur\|POS=PRON\|Person=1`, `Mood=Ind\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin`, `POS=SCONJ`, `POS=ADP`, `Definite=Def\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Art`, `NumType=Ord\|POS=ADJ`, `Gender=Masc\|Number=Sing\|POS=NOUN`, `POS=PUNCT`, `Gender=Masc\|Number=Sing\|POS=PROPN`, `Number=Plur\|POS=ADJ`, `Gender=Masc\|Number=Plur\|POS=NOUN`, `Definite=Ind\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Art`, `Number=Sing\|POS=ADJ`, `Mood=Ind\|Number=Sing\|POS=VERB\|Person=3\|Tense=Imp\|VerbForm=Fin`, `POS=ADV`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=3\|Tense=Past\|VerbForm=Fin`, `Gender=Fem\|Number=Sing\|POS=VERB\|Tense=Past\|VerbForm=Part\|Voice=Pass`, `Definite=Def\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Art`, `Gender=Fem\|Number=Sing\|POS=PROPN`, `Definite=Def\|Number=Sing\|POS=DET\|PronType=Art`, `NumType=Card\|POS=NUM`, `Definite=Def\|Number=Plur\|POS=DET\|PronType=Art`, `Gender=Masc\|Number=Plur\|POS=ADJ`, `POS=CCONJ`, `Gender=Fem\|Number=Plur\|POS=NOUN`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin`, `Gender=Masc\|Number=Sing\|POS=VERB\|Tense=Past\|VerbForm=Part`, `Gender=Fem\|Number=Plur\|POS=ADJ`, `POS=ADJ`, `Mood=Ind\|Number=Sing\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin`, `POS=PRON\|PronType=Rel`, `Number=Sing\|POS=DET\|Poss=Yes`, `Definite=Def\|Gender=Masc\|Number=Sing\|POS=ADP\|PronType=Art`, `Definite=Def\|Number=Plur\|POS=ADP\|PronType=Art`, `Definite=Ind\|Number=Plur\|POS=DET\|PronType=Art`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=3\|Tense=Past\|VerbForm=Fin`, `Gender=Masc\|Number=Plur\|POS=VERB\|Tense=Past\|VerbForm=Part\|Voice=Pass`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin`, `POS=VERB\|VerbForm=Inf`, `Gender=Fem\|Number=Sing\|POS=ADJ`, `Gender=Masc\|Number=Sing\|POS=PRON\|Person=3`, `Number=Plur\|POS=DET`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Gender=Masc\|Number=Sing\|POS=ADJ`, `Gender=Masc\|Number=Sing\|POS=DET\|PronType=Dem`, `POS=ADV\|PronType=Int`, `POS=VERB\|Tense=Pres\|VerbForm=Part`, `Gender=Fem\|Number=Sing\|POS=VERB\|Tense=Past\|VerbForm=Part`, `Definite=Ind\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Art`, `Gender=Masc\|POS=ADJ`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=3\|Tense=Fut\|VerbForm=Fin`, `Number=Plur\|POS=DET\|Poss=Yes`, `POS=AUX\|VerbForm=Inf`, `Gender=Masc\|Number=Sing\|POS=VERB\|Tense=Past\|VerbForm=Part\|Voice=Pass`, `Gender=Masc\|POS=VERB\|Tense=Past\|VerbForm=Part`, `POS=ADV\|Polarity=Neg`, `Definite=Ind\|Number=Sing\|POS=DET\|PronType=Art`, `Gender=Fem\|Number=Sing\|POS=PRON\|Person=3`, `POS=PRON\|Person=3\|Reflex=Yes`, `Gender=Masc\|POS=NOUN`, `POS=AUX\|Tense=Past\|VerbForm=Part`, `POS=PRON\|Person=3`, `Number=Plur\|POS=NOUN`, `NumType=Ord\|Number=Sing\|POS=ADJ`, `POS=VERB\|Tense=Past\|VerbForm=Part`, `POS=AUX\|Tense=Pres\|VerbForm=Part`, `Gender=Masc\|Number=Plur\|POS=VERB\|Tense=Past\|VerbForm=Part`, `Number=Sing\|POS=PRON\|Person=3`, `Number=Sing\|POS=NOUN`, `Gender=Masc\|Number=Plur\|POS=PRON\|Person=3`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=3\|Tense=Imp\|VerbForm=Fin`, `Gender=Fem\|NumType=Ord\|Number=Sing\|POS=ADJ`, `Number=Plur\|POS=PROPN`, `Number=Sing\|POS=PROPN`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=3\|Tense=Imp\|VerbForm=Fin`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Gender=Masc\|Number=Plur\|POS=PRON\|PronType=Dem`, `Gender=Masc\|Number=Sing\|POS=DET`, `Gender=Fem\|Number=Sing\|POS=DET\|Poss=Yes`, `Gender=Masc\|POS=PRON`, `POS=NOUN`, `Mood=Ind\|Number=Sing\|POS=VERB\|Person=3\|Tense=Fut\|VerbForm=Fin`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=3\|Tense=Fut\|VerbForm=Fin`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Number=Plur\|POS=PRON`, `Gender=Masc\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=3\|Tense=Fut\|VerbForm=Fin`, `Gender=Fem\|Number=Plur\|POS=VERB\|Tense=Past\|VerbForm=Part\|Voice=Pass`, `Number=Sing\|POS=PRON`, `Number=Sing\|POS=PRON\|PronType=Dem`, `Mood=Ind\|POS=VERB\|VerbForm=Fin`, `Number=Plur\|POS=DET\|PronType=Dem`, `Gender=Masc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Gender=Masc\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Gender=Masc\|Number=Sing\|POS=PRON`, `Gender=Masc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Dem`, `Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Gender=Masc\|Number=Sing\|POS=PRON\|PronType=Rel`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=3\|Tense=Imp\|VerbForm=Fin`, `Mood=Sub\|Number=Sing\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Gender=Masc\|NumType=Ord\|Number=Sing\|POS=ADJ`, `POS=PRON`, `POS=NUM`, `Gender=Fem\|POS=NOUN`, `Gender=Fem\|Number=Plur\|POS=PRON`, `Number=Plur\|POS=PRON\|Person=3`, `Number=Sing\|POS=VERB\|Tense=Past\|VerbForm=Part`, `Number=Sing\|POS=PRON\|Person=1`, `Mood=Ind\|Number=Sing\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Mood=Sub\|Number=Sing\|POS=VERB\|Person=3\|Tense=Past\|VerbForm=Fin`, `Gender=Fem\|Number=Sing\|POS=PRON`, `Gender=Fem\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Mood=Sub\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin`, `POS=INTJ`, `Number=Plur\|POS=PRON\|Person=2`, `NumType=Card\|POS=PRON`, `Definite=Ind\|Gender=Fem\|Number=Plur\|POS=DET\|PronType=Art`, `Gender=Fem\|Number=Plur\|POS=VERB\|Tense=Past\|VerbForm=Part`, `NumType=Card\|POS=NOUN`, `POS=PRON\|PronType=Int`, `Gender=Fem\|Number=Plur\|POS=PRON\|Person=3`, `Gender=Fem\|Number=Sing\|POS=DET`, `Mood=Cnd\|Number=Sing\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Gender=Fem\|Number=Plur\|POS=DET`, `Mood=Sub\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Definite=Ind\|Gender=Masc\|Number=Plur\|POS=DET\|PronType=Art`, `Mood=Cnd\|Number=Sing\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Gender=Masc\|Number=Sing\|POS=PRON\|PronType=Dem`, `Gender=Masc\|Number=Plur\|POS=PROPN`, `Mood=Cnd\|Number=Plur\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Gender=Fem\|Number=Sing\|POS=PRON\|PronType=Dem`, `Number=Sing\|POS=DET`, `Gender=Masc\|NumType=Card\|Number=Plur\|POS=NOUN`, `Gender=Fem\|Number=Plur\|POS=PRON\|PronType=Dem`, `Mood=Ind\|POS=VERB\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Gender=Fem\|POS=PRON`, `Gender=Masc\|POS=VERB\|Tense=Past\|VerbForm=Part\|Voice=Pass`, `Gender=Fem\|Number=Sing\|POS=PRON\|PronType=Rel`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=1\|Tense=Imp\|VerbForm=Fin`, `Mood=Cnd\|Number=Plur\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Gender=Masc\|Number=Sing\|POS=AUX\|Tense=Past\|VerbForm=Part`, `POS=X`, `POS=SYM`, `Mood=Imp\|Number=Plur\|POS=VERB\|Person=2\|Tense=Pres\|VerbForm=Fin`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=2\|Tense=Pres\|VerbForm=Fin`, `Gender=Masc\|Number=Sing\|POS=DET\|PronType=Int`, `Gender=Fem\|Number=Plur\|POS=DET\|PronType=Int`, `POS=DET`, `Gender=Masc\|Number=Plur\|POS=PRON`, `Mood=Sub\|Number=Plur\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Mood=Ind\|POS=VERB\|Person=3\|VerbForm=Fin`, `Number=Sing\|POS=VERB\|Tense=Past\|VerbForm=Part\|Voice=Pass`, `Mood=Cnd\|Number=Plur\|POS=VERB\|Person=2\|Tense=Pres\|VerbForm=Fin`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=2\|Tense=Pres\|VerbForm=Fin`, `Gender=Fem\|Number=Sing\|POS=DET\|PronType=Int`, `Gender=Masc\|Number=Plur\|POS=DET`, `Gender=Fem\|Number=Plur\|POS=PRON\|PronType=Rel`, `Number=Plur\|POS=VERB\|Tense=Past\|VerbForm=Part\|Voice=Pass`, `Gender=Masc\|Number=Plur\|POS=PRON\|PronType=Rel`, `POS=VERB\|Tense=Past\|VerbForm=Part\|Voice=Pass`, `Gender=Fem\|NumType=Ord\|Number=Plur\|POS=ADJ`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=2\|Tense=Fut\|VerbForm=Fin`, `Mood=Imp\|POS=VERB\|Tense=Pres\|VerbForm=Fin`, `Number=Plur\|POS=PRON\|Person=2\|Reflex=Yes`, `Mood=Cnd\|Number=Sing\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Number=Plur\|POS=PRON\|Person=1\|Reflex=Yes`, `Gender=Masc\|NumType=Card\|Number=Sing\|POS=NOUN`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=1\|Tense=Fut\|VerbForm=Fin`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=1\|Tense=Fut\|VerbForm=Fin`, `Number=Sing\|POS=PRON\|Person=1\|Reflex=Yes`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=1\|Tense=Imp\|VerbForm=Fin`, `Mood=Ind\|Number=Plur\|POS=AUX\|Person=1\|Tense=Imp\|VerbForm=Fin`, `Mood=Ind\|Number=Sing\|POS=VERB\|Person=1\|Tense=Imp\|VerbForm=Fin`, `Mood=Sub\|Number=Sing\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Gender=Masc\|POS=PROPN`, `Mood=Cnd\|Number=Plur\|POS=AUX\|Person=3\|Tense=Pres\|VerbForm=Fin`, `Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `Mood=Sub\|Number=Sing\|POS=AUX\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Number=Plur\|POS=PRON\|Person=2\|PronType=Prs`, `Mood=Ind\|Number=Sing\|POS=VERB\|Person=1\|Tense=Fut\|VerbForm=Fin`, `Gender=Fem\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Mood=Cnd\|Number=Sing\|POS=AUX\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Mood=Sub\|Number=Plur\|POS=AUX\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Mood=Imp\|Number=Plur\|POS=VERB\|Person=1\|Tense=Pres\|VerbForm=Fin`, `Mood=Sub\|Number=Plur\|POS=AUX\|Person=2\|Tense=Pres\|VerbForm=Fin`, `Mood=Ind\|Number=Plur\|POS=VERB\|Person=2\|Tense=Imp\|VerbForm=Fin`, `Mood=Ind\|Number=Sing\|POS=AUX\|Person=2\|Tense=Imp\|VerbForm=Fin`, `Number=Plur\|POS=VERB\|Tense=Past\|VerbForm=Part`, `Gender=Fem\|Number=Plur\|POS=PROPN`, `Gender=Masc\|NumType=Card\|POS=NUM` |
99
  | **`parser`** | `ROOT`, `acl`, `acl:relcl`, `advcl`, `advmod`, `amod`, `appos`, `aux:pass`, `aux:tense`, `case`, `cc`, `ccomp`, `conj`, `cop`, `dep`, `det`, `expl:comp`, `expl:pass`, `expl:subj`, `fixed`, `flat:foreign`, `flat:name`, `iobj`, `mark`, `nmod`, `nsubj`, `nsubj:pass`, `nummod`, `obj`, `obl:agent`, `obl:arg`, `obl:mod`, `parataxis`, `punct`, `vocative`, `xcomp` |
 
100
  | **`ner`** | `LOC`, `MISC`, `ORG`, `PER` |
101
 
102
  </details>
109
  | `TOKEN_P` | 98.44 |
110
  | `TOKEN_R` | 98.96 |
111
  | `TOKEN_F` | 98.70 |
112
+ | `POS_ACC` | 97.11 |
113
+ | `MORPH_ACC` | 96.20 |
114
+ | `MORPH_MICRO_P` | 98.40 |
115
+ | `MORPH_MICRO_R` | 97.68 |
116
+ | `MORPH_MICRO_F` | 98.04 |
117
+ | `SENTS_P` | 85.34 |
118
+ | `SENTS_R` | 89.20 |
119
+ | `SENTS_F` | 86.47 |
120
+ | `DEP_UAS` | 89.77 |
121
+ | `DEP_LAS` | 85.91 |
122
+ | `TAG_ACC` | 94.24 |
123
+ | `LEMMA_ACC` | 90.64 |
124
+ | `ENTS_P` | 83.18 |
125
+ | `ENTS_R` | 82.99 |
126
+ | `ENTS_F` | 83.09 |
accuracy.json CHANGED
@@ -3,133 +3,133 @@
3
  "token_p": 0.9844389844,
4
  "token_r": 0.9896058454,
5
  "token_f": 0.9870156531,
6
- "pos_acc": 0.9734577127,
7
- "morph_acc": 0.9646282355,
8
- "morph_micro_p": 0.9870385159,
9
- "morph_micro_r": 0.9789204338,
10
- "morph_micro_f": 0.9829627137,
11
  "morph_per_feat": {
12
  "Definite": {
13
- "p": 0.9890270666,
14
  "r": 0.9868613139,
15
- "f": 0.9879430033
16
  },
17
  "Number": {
18
- "p": 0.9940597735,
19
- "r": 0.9858247423,
20
- "f": 0.9899251317
21
  },
22
  "PronType": {
23
- "p": 0.9954896907,
24
- "r": 0.9884836852,
25
- "f": 0.9919743178
26
  },
27
  "Gender": {
28
- "p": 0.9824380165,
29
- "r": 0.9721441349,
30
- "f": 0.9772639692
31
  },
32
  "Mood": {
33
- "p": 0.972972973,
34
- "r": 0.9591474245,
35
- "f": 0.9660107335
36
  },
37
  "Person": {
38
- "p": 0.9897828863,
39
- "r": 0.9748427673,
40
- "f": 0.9822560203
41
  },
42
  "Tense": {
43
- "p": 0.9672131148,
44
- "r": 0.9642492339,
45
- "f": 0.9657289003
46
  },
47
  "VerbForm": {
48
- "p": 0.9816971714,
49
- "r": 0.9768211921,
50
- "f": 0.979253112
51
  },
52
  "NumType": {
53
- "p": 0.9929577465,
54
- "r": 0.9624573379,
55
- "f": 0.9774696707
56
  },
57
  "Reflex": {
58
- "p": 0.9777777778,
59
  "r": 1.0,
60
- "f": 0.9887640449
61
  },
62
  "Voice": {
63
- "p": 0.9224137931,
64
  "r": 0.9553571429,
65
- "f": 0.9385964912
66
  },
67
  "Poss": {
68
- "p": 1.0,
69
  "r": 1.0,
70
- "f": 1.0
71
  },
72
  "Polarity": {
73
  "p": 1.0,
74
- "r": 0.9764705882,
75
- "f": 0.9880952381
76
  }
77
  },
78
- "sents_p": 0.8782816229,
79
- "sents_r": 0.8932038835,
80
- "sents_f": 0.8856799037,
81
- "dep_uas": 0.8967353554,
82
- "dep_las": 0.8580193321,
83
  "dep_las_per_type": {
84
  "det": {
85
- "p": 0.9805668016,
86
- "r": 0.9774011299,
87
- "f": 0.9789814066
88
  },
89
  "nsubj": {
90
- "p": 0.8762376238,
91
- "r": 0.8530120482,
92
- "f": 0.8644688645
93
  },
94
  "aux:tense": {
95
- "p": 0.9285714286,
96
- "r": 0.936,
97
- "f": 0.9322709163
98
  },
99
  "root": {
100
- "p": 0.8865248227,
101
- "r": 0.9101941748,
102
- "f": 0.8982035928
103
  },
104
  "obj": {
105
- "p": 0.849112426,
106
- "r": 0.8516320475,
107
- "f": 0.8503703704
108
  },
109
  "cc": {
110
- "p": 0.8909090909,
111
- "r": 0.9032258065,
112
- "f": 0.8970251716
113
  },
114
  "case": {
115
- "p": 0.9695740365,
116
- "r": 0.9768392371,
117
- "f": 0.9731930777
118
  },
119
  "obl:mod": {
120
- "p": 0.6749226006,
121
- "r": 0.6507462687,
122
- "f": 0.6626139818
123
  },
124
  "nmod": {
125
- "p": 0.8055028463,
126
- "r": 0.8481518482,
127
- "f": 0.8262773723
128
  },
129
  "conj": {
130
- "p": 0.5241935484,
131
- "r": 0.5118110236,
132
- "f": 0.5179282869
133
  },
134
  "nummod": {
135
  "p": 0.9141104294,
@@ -137,114 +137,114 @@
137
  "f": 0.8975903614
138
  },
139
  "amod": {
140
- "p": 0.9235074627,
141
- "r": 0.9016393443,
142
- "f": 0.9124423963
143
  },
144
  "acl": {
145
- "p": 0.6994219653,
146
- "r": 0.6994219653,
147
- "f": 0.6994219653
148
  },
149
  "mark": {
150
- "p": 0.8689956332,
151
- "r": 0.8766519824,
152
- "f": 0.8728070175
153
  },
154
  "xcomp": {
155
- "p": 0.8531468531,
156
- "r": 0.8079470199,
157
- "f": 0.8299319728
158
  },
159
  "flat:name": {
160
- "p": 0.9504950495,
161
- "r": 0.9142857143,
162
- "f": 0.932038835
163
  },
164
  "cop": {
165
- "p": 0.8602150538,
166
- "r": 0.8888888889,
167
- "f": 0.8743169399
168
  },
169
  "advmod": {
170
- "p": 0.8566978193,
171
- "r": 0.8620689655,
172
- "f": 0.859375
173
  },
174
  "obl:arg": {
175
- "p": 0.7562189055,
176
- "r": 0.6909090909,
177
- "f": 0.7220902613
178
  },
179
  "appos": {
180
- "p": 0.4938271605,
181
  "r": 0.4819277108,
182
- "f": 0.487804878
183
  },
184
  "nsubj:pass": {
185
- "p": 0.875,
186
- "r": 0.8235294118,
187
- "f": 0.8484848485
188
  },
189
  "aux:pass": {
190
- "p": 0.9469026549,
191
  "r": 0.9553571429,
192
- "f": 0.9511111111
193
  },
194
  "acl:relcl": {
195
- "p": 0.5764705882,
196
- "r": 0.5697674419,
197
- "f": 0.5730994152
198
  },
199
  "advcl": {
200
- "p": 0.4698795181,
201
- "r": 0.5,
202
- "f": 0.4844720497
203
  },
204
  "fixed": {
205
- "p": 0.8705882353,
206
- "r": 0.74,
207
- "f": 0.8
208
  },
209
  "dep": {
210
- "p": 0.3392857143,
211
- "r": 0.6551724138,
212
- "f": 0.4470588235
213
  },
214
  "expl:subj": {
215
- "p": 0.7647058824,
216
  "r": 0.8125,
217
- "f": 0.7878787879
218
  },
219
  "expl:comp": {
220
- "p": 0.6585365854,
221
- "r": 0.9,
222
- "f": 0.7605633803
223
  },
224
  "expl:pass": {
225
- "p": 0.3333333333,
226
  "r": 0.1428571429,
227
- "f": 0.2
228
  },
229
  "ccomp": {
230
- "p": 0.7058823529,
231
- "r": 0.7058823529,
232
- "f": 0.7058823529
233
  },
234
  "parataxis": {
235
- "p": 0.5,
236
- "r": 0.3571428571,
237
- "f": 0.4166666667
238
  },
239
  "iobj": {
240
- "p": 0.7222222222,
241
- "r": 0.52,
242
- "f": 0.6046511628
243
  },
244
  "obl:agent": {
245
- "p": 0.8684210526,
246
  "r": 0.7857142857,
247
- "f": 0.825
248
  },
249
  "nsubj:caus": {
250
  "p": 0.0,
@@ -277,9 +277,9 @@
277
  "f": 0.0
278
  },
279
  "flat:foreign": {
280
- "p": 1.0,
281
- "r": 0.4285714286,
282
- "f": 0.6
283
  },
284
  "orphan": {
285
  "p": 0.0,
@@ -297,32 +297,32 @@
297
  "f": 0.0
298
  }
299
  },
300
- "tag_acc": 0.9448023502,
301
- "lemma_acc": 0.9070078093,
302
- "ents_p": 0.8332265556,
303
- "ents_r": 0.8329930747,
304
- "ents_f": 0.8331097988,
305
  "ents_per_type": {
306
  "PER": {
307
- "p": 0.8976195492,
308
- "r": 0.9158845024,
309
- "f": 0.9066600468
310
  },
311
  "LOC": {
312
- "p": 0.8411137734,
313
- "r": 0.8516690371,
314
- "f": 0.8463584968
315
  },
316
  "ORG": {
317
- "p": 0.763618677,
318
- "r": 0.7490458015,
319
- "f": 0.7562620424
320
  },
321
  "MISC": {
322
- "p": 0.7152963371,
323
- "r": 0.6633620061,
324
- "f": 0.6883509834
325
  }
326
  },
327
- "speed": 4392.7454027339
328
  }
3
  "token_p": 0.9844389844,
4
  "token_r": 0.9896058454,
5
  "token_f": 0.9870156531,
6
+ "pos_acc": 0.9710899253,
7
+ "morph_acc": 0.9620122674,
8
+ "morph_micro_p": 0.9839828168,
9
+ "morph_micro_r": 0.9768490313,
10
+ "morph_micro_f": 0.9804029472,
11
  "morph_per_feat": {
12
  "Definite": {
13
+ "p": 0.9868613139,
14
  "r": 0.9868613139,
15
+ "f": 0.9868613139
16
  },
17
  "Number": {
18
+ "p": 0.992584353,
19
+ "r": 0.985640648,
20
+ "f": 0.9891003141
21
  },
22
  "PronType": {
23
+ "p": 0.9942159383,
24
+ "r": 0.9897632758,
25
+ "f": 0.9919846105
26
  },
27
  "Gender": {
28
+ "p": 0.9798813516,
29
+ "r": 0.970866343,
30
+ "f": 0.9753530167
31
  },
32
  "Mood": {
33
+ "p": 0.9675090253,
34
+ "r": 0.9520426288,
35
+ "f": 0.9597135184
36
  },
37
  "Person": {
38
+ "p": 0.9821428571,
39
+ "r": 0.9685534591,
40
+ "f": 0.9753008233
41
  },
42
  "Tense": {
43
+ "p": 0.9578622816,
44
+ "r": 0.9519918284,
45
+ "f": 0.9549180328
46
  },
47
  "VerbForm": {
48
+ "p": 0.9742310889,
49
+ "r": 0.9701986755,
50
+ "f": 0.972210701
51
  },
52
  "NumType": {
53
+ "p": 0.9893992933,
54
+ "r": 0.9556313993,
55
+ "f": 0.9722222222
56
  },
57
  "Reflex": {
58
+ "p": 1.0,
59
  "r": 1.0,
60
+ "f": 1.0
61
  },
62
  "Voice": {
63
+ "p": 0.9304347826,
64
  "r": 0.9553571429,
65
+ "f": 0.9427312775
66
  },
67
  "Poss": {
68
+ "p": 0.9827586207,
69
  "r": 1.0,
70
+ "f": 0.9913043478
71
  },
72
  "Polarity": {
73
  "p": 1.0,
74
+ "r": 0.9882352941,
75
+ "f": 0.9940828402
76
  }
77
  },
78
+ "sents_p": 0.853427896,
79
+ "sents_r": 0.8919553503,
80
+ "sents_f": 0.8646706587,
81
+ "dep_uas": 0.8977489729,
82
+ "dep_las": 0.8591264102,
83
  "dep_las_per_type": {
84
  "det": {
85
+ "p": 0.9854014599,
86
+ "r": 0.98062954,
87
+ "f": 0.9830097087
88
  },
89
  "nsubj": {
90
+ "p": 0.8819277108,
91
+ "r": 0.8819277108,
92
+ "f": 0.8819277108
93
  },
94
  "aux:tense": {
95
+ "p": 0.952,
96
+ "r": 0.952,
97
+ "f": 0.952
98
  },
99
  "root": {
100
+ "p": 0.8717339667,
101
+ "r": 0.890776699,
102
+ "f": 0.881152461
103
  },
104
  "obj": {
105
+ "p": 0.8700906344,
106
+ "r": 0.8545994065,
107
+ "f": 0.8622754491
108
  },
109
  "cc": {
110
+ "p": 0.8986175115,
111
+ "r": 0.8986175115,
112
+ "f": 0.8986175115
113
  },
114
  "case": {
115
+ "p": 0.9695328368,
116
+ "r": 0.9754768392,
117
+ "f": 0.9724957555
118
  },
119
  "obl:mod": {
120
+ "p": 0.6677316294,
121
+ "r": 0.623880597,
122
+ "f": 0.6450617284
123
  },
124
  "nmod": {
125
+ "p": 0.8051330798,
126
+ "r": 0.8461538462,
127
+ "f": 0.8251339503
128
  },
129
  "conj": {
130
+ "p": 0.5863453815,
131
+ "r": 0.5748031496,
132
+ "f": 0.5805168986
133
  },
134
  "nummod": {
135
  "p": 0.9141104294,
137
  "f": 0.8975903614
138
  },
139
  "amod": {
140
+ "p": 0.9037037037,
141
+ "r": 0.8888888889,
142
+ "f": 0.8962350781
143
  },
144
  "acl": {
145
+ "p": 0.6892655367,
146
+ "r": 0.7052023121,
147
+ "f": 0.6971428571
148
  },
149
  "mark": {
150
+ "p": 0.88,
151
+ "r": 0.872246696,
152
+ "f": 0.8761061947
153
  },
154
  "xcomp": {
155
+ "p": 0.8476821192,
156
+ "r": 0.8476821192,
157
+ "f": 0.8476821192
158
  },
159
  "flat:name": {
160
+ "p": 0.9223300971,
161
+ "r": 0.9047619048,
162
+ "f": 0.9134615385
163
  },
164
  "cop": {
165
+ "p": 0.8709677419,
166
+ "r": 0.9,
167
+ "f": 0.8852459016
168
  },
169
  "advmod": {
170
+ "p": 0.8698412698,
171
+ "r": 0.8589341693,
172
+ "f": 0.8643533123
173
  },
174
  "obl:arg": {
175
+ "p": 0.6872037915,
176
+ "r": 0.6590909091,
177
+ "f": 0.6728538283
178
  },
179
  "appos": {
180
+ "p": 0.5263157895,
181
  "r": 0.4819277108,
182
+ "f": 0.5031446541
183
  },
184
  "nsubj:pass": {
185
+ "p": 0.9156626506,
186
+ "r": 0.8941176471,
187
+ "f": 0.9047619048
188
  },
189
  "aux:pass": {
190
+ "p": 0.963963964,
191
  "r": 0.9553571429,
192
+ "f": 0.9596412556
193
  },
194
  "acl:relcl": {
195
+ "p": 0.6511627907,
196
+ "r": 0.6511627907,
197
+ "f": 0.6511627907
198
  },
199
  "advcl": {
200
+ "p": 0.5128205128,
201
+ "r": 0.5128205128,
202
+ "f": 0.5128205128
203
  },
204
  "fixed": {
205
+ "p": 0.8539325843,
206
+ "r": 0.76,
207
+ "f": 0.8042328042
208
  },
209
  "dep": {
210
+ "p": 0.2571428571,
211
+ "r": 0.6206896552,
212
+ "f": 0.3636363636
213
  },
214
  "expl:subj": {
215
+ "p": 0.8666666667,
216
  "r": 0.8125,
217
+ "f": 0.8387096774
218
  },
219
  "expl:comp": {
220
+ "p": 0.625,
221
+ "r": 0.8333333333,
222
+ "f": 0.7142857143
223
  },
224
  "expl:pass": {
225
+ "p": 0.25,
226
  "r": 0.1428571429,
227
+ "f": 0.1818181818
228
  },
229
  "ccomp": {
230
+ "p": 0.6666666667,
231
+ "r": 0.6666666667,
232
+ "f": 0.6666666667
233
  },
234
  "parataxis": {
235
+ "p": 0.5714285714,
236
+ "r": 0.4285714286,
237
+ "f": 0.4897959184
238
  },
239
  "iobj": {
240
+ "p": 0.75,
241
+ "r": 0.48,
242
+ "f": 0.5853658537
243
  },
244
  "obl:agent": {
245
+ "p": 0.8918918919,
246
  "r": 0.7857142857,
247
+ "f": 0.835443038
248
  },
249
  "nsubj:caus": {
250
  "p": 0.0,
277
  "f": 0.0
278
  },
279
  "flat:foreign": {
280
+ "p": 0.0,
281
+ "r": 0.0,
282
+ "f": 0.0
283
  },
284
  "orphan": {
285
  "p": 0.0,
297
  "f": 0.0
298
  }
299
  },
300
+ "tag_acc": 0.9424375161,
301
+ "lemma_acc": 0.9063912865,
302
+ "ents_p": 0.8317787005,
303
+ "ents_r": 0.8299307474,
304
+ "ents_f": 0.8308536964,
305
  "ents_per_type": {
306
  "PER": {
307
+ "p": 0.8974413195,
308
+ "r": 0.912230422,
309
+ "f": 0.9047754406
310
  },
311
  "LOC": {
312
+ "p": 0.8422664625,
313
+ "r": 0.851250732,
314
+ "f": 0.8467347661
315
  },
316
  "ORG": {
317
+ "p": 0.7548623147,
318
+ "r": 0.7480916031,
319
+ "f": 0.751461708
320
  },
321
  "MISC": {
322
+ "p": 0.7072900158,
323
+ "r": 0.6506779414,
324
+ "f": 0.6778039335
325
  }
326
  },
327
+ "speed": 4445.2953793177
328
  }
attribute_ruler/patterns CHANGED
Binary files a/attribute_ruler/patterns and b/attribute_ruler/patterns differ
config.cfg CHANGED
@@ -39,8 +39,9 @@ overwrite = true
39
  scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
40
 
41
  [components.morphologizer.model]
42
- @architectures = "spacy.Tagger.v1"
43
  nO = null
 
44
 
45
  [components.morphologizer.model.tok2vec]
46
  @architectures = "spacy.Tok2VecListener.v1"
@@ -70,7 +71,7 @@ nO = null
70
  @architectures = "spacy.MultiHashEmbed.v2"
71
  width = 96
72
  attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
73
- rows = [5000,2500,2500,2500,100]
74
  include_static_vectors = true
75
 
76
  [components.ner.model.tok2vec.encode]
@@ -108,8 +109,9 @@ overwrite = false
108
  scorer = {"@scorers":"spacy.senter_scorer.v1"}
109
 
110
  [components.senter.model]
111
- @architectures = "spacy.Tagger.v1"
112
  nO = null
 
113
 
114
  [components.senter.model.tok2vec]
115
  @architectures = "spacy.Tok2Vec.v2"
@@ -138,7 +140,7 @@ factory = "tok2vec"
138
  @architectures = "spacy.MultiHashEmbed.v2"
139
  width = ${components.tok2vec.model.encode:width}
140
  attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
141
- rows = [5000,2500,2500,2500,100]
142
  include_static_vectors = true
143
 
144
  [components.tok2vec.model.encode]
@@ -175,7 +177,7 @@ dropout = 0.1
175
  accumulate_gradient = 1
176
  patience = 5000
177
  max_epochs = 0
178
- max_steps = 0
179
  eval_frequency = 1000
180
  frozen_components = []
181
  before_to_disk = null
39
  scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
40
 
41
  [components.morphologizer.model]
42
+ @architectures = "spacy.Tagger.v2"
43
  nO = null
44
+ normalize = false
45
 
46
  [components.morphologizer.model.tok2vec]
47
  @architectures = "spacy.Tok2VecListener.v1"
71
  @architectures = "spacy.MultiHashEmbed.v2"
72
  width = 96
73
  attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
74
+ rows = [5000,1000,2500,2500,50]
75
  include_static_vectors = true
76
 
77
  [components.ner.model.tok2vec.encode]
109
  scorer = {"@scorers":"spacy.senter_scorer.v1"}
110
 
111
  [components.senter.model]
112
+ @architectures = "spacy.Tagger.v2"
113
  nO = null
114
+ normalize = false
115
 
116
  [components.senter.model.tok2vec]
117
  @architectures = "spacy.Tok2Vec.v2"
140
  @architectures = "spacy.MultiHashEmbed.v2"
141
  width = ${components.tok2vec.model.encode:width}
142
  attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
143
+ rows = [5000,1000,2500,2500,50]
144
  include_static_vectors = true
145
 
146
  [components.tok2vec.model.encode]
177
  accumulate_gradient = 1
178
  patience = 5000
179
  max_epochs = 0
180
+ max_steps = 100000
181
  eval_frequency = 1000
182
  frozen_components = []
183
  before_to_disk = null
fr_core_news_md-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc89844588a50d13c21f203e80e6fa6df3857d1a29b19c92a8e7338ec487f522
3
- size 46938345
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cb3ededc431167417a358e61a4bd1f96356b2525b7ba7da9edb39097b0ae81e
3
+ size 45836699
meta.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "lang":"fr",
3
  "name":"core_news_md",
4
- "version":"3.2.0",
5
  "description":"French pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"LGPL-LR",
10
- "spacy_version":">=3.2.0,<3.3.0",
11
- "spacy_git_version":"bb26550e2",
12
  "vectors":{
13
  "width":300,
14
  "vectors":20000,
@@ -255,10 +255,6 @@
255
  "vocative",
256
  "xcomp"
257
  ],
258
- "senter":[
259
- "I",
260
- "S"
261
- ],
262
  "attribute_ruler":[
263
 
264
  ],
@@ -297,133 +293,133 @@
297
  "token_p":0.9844389844,
298
  "token_r":0.9896058454,
299
  "token_f":0.9870156531,
300
- "pos_acc":0.9734577127,
301
- "morph_acc":0.9646282355,
302
- "morph_micro_p":0.9870385159,
303
- "morph_micro_r":0.9789204338,
304
- "morph_micro_f":0.9829627137,
305
  "morph_per_feat":{
306
  "Definite":{
307
- "p":0.9890270666,
308
  "r":0.9868613139,
309
- "f":0.9879430033
310
  },
311
  "Number":{
312
- "p":0.9940597735,
313
- "r":0.9858247423,
314
- "f":0.9899251317
315
  },
316
  "PronType":{
317
- "p":0.9954896907,
318
- "r":0.9884836852,
319
- "f":0.9919743178
320
  },
321
  "Gender":{
322
- "p":0.9824380165,
323
- "r":0.9721441349,
324
- "f":0.9772639692
325
  },
326
  "Mood":{
327
- "p":0.972972973,
328
- "r":0.9591474245,
329
- "f":0.9660107335
330
  },
331
  "Person":{
332
- "p":0.9897828863,
333
- "r":0.9748427673,
334
- "f":0.9822560203
335
  },
336
  "Tense":{
337
- "p":0.9672131148,
338
- "r":0.9642492339,
339
- "f":0.9657289003
340
  },
341
  "VerbForm":{
342
- "p":0.9816971714,
343
- "r":0.9768211921,
344
- "f":0.979253112
345
  },
346
  "NumType":{
347
- "p":0.9929577465,
348
- "r":0.9624573379,
349
- "f":0.9774696707
350
  },
351
  "Reflex":{
352
- "p":0.9777777778,
353
  "r":1.0,
354
- "f":0.9887640449
355
  },
356
  "Voice":{
357
- "p":0.9224137931,
358
  "r":0.9553571429,
359
- "f":0.9385964912
360
  },
361
  "Poss":{
362
- "p":1.0,
363
  "r":1.0,
364
- "f":1.0
365
  },
366
  "Polarity":{
367
  "p":1.0,
368
- "r":0.9764705882,
369
- "f":0.9880952381
370
  }
371
  },
372
- "sents_p":0.8782816229,
373
- "sents_r":0.8932038835,
374
- "sents_f":0.8856799037,
375
- "dep_uas":0.8967353554,
376
- "dep_las":0.8580193321,
377
  "dep_las_per_type":{
378
  "det":{
379
- "p":0.9805668016,
380
- "r":0.9774011299,
381
- "f":0.9789814066
382
  },
383
  "nsubj":{
384
- "p":0.8762376238,
385
- "r":0.8530120482,
386
- "f":0.8644688645
387
  },
388
  "aux:tense":{
389
- "p":0.9285714286,
390
- "r":0.936,
391
- "f":0.9322709163
392
  },
393
  "root":{
394
- "p":0.8865248227,
395
- "r":0.9101941748,
396
- "f":0.8982035928
397
  },
398
  "obj":{
399
- "p":0.849112426,
400
- "r":0.8516320475,
401
- "f":0.8503703704
402
  },
403
  "cc":{
404
- "p":0.8909090909,
405
- "r":0.9032258065,
406
- "f":0.8970251716
407
  },
408
  "case":{
409
- "p":0.9695740365,
410
- "r":0.9768392371,
411
- "f":0.9731930777
412
  },
413
  "obl:mod":{
414
- "p":0.6749226006,
415
- "r":0.6507462687,
416
- "f":0.6626139818
417
  },
418
  "nmod":{
419
- "p":0.8055028463,
420
- "r":0.8481518482,
421
- "f":0.8262773723
422
  },
423
  "conj":{
424
- "p":0.5241935484,
425
- "r":0.5118110236,
426
- "f":0.5179282869
427
  },
428
  "nummod":{
429
  "p":0.9141104294,
@@ -431,114 +427,114 @@
431
  "f":0.8975903614
432
  },
433
  "amod":{
434
- "p":0.9235074627,
435
- "r":0.9016393443,
436
- "f":0.9124423963
437
  },
438
  "acl":{
439
- "p":0.6994219653,
440
- "r":0.6994219653,
441
- "f":0.6994219653
442
  },
443
  "mark":{
444
- "p":0.8689956332,
445
- "r":0.8766519824,
446
- "f":0.8728070175
447
  },
448
  "xcomp":{
449
- "p":0.8531468531,
450
- "r":0.8079470199,
451
- "f":0.8299319728
452
  },
453
  "flat:name":{
454
- "p":0.9504950495,
455
- "r":0.9142857143,
456
- "f":0.932038835
457
  },
458
  "cop":{
459
- "p":0.8602150538,
460
- "r":0.8888888889,
461
- "f":0.8743169399
462
  },
463
  "advmod":{
464
- "p":0.8566978193,
465
- "r":0.8620689655,
466
- "f":0.859375
467
  },
468
  "obl:arg":{
469
- "p":0.7562189055,
470
- "r":0.6909090909,
471
- "f":0.7220902613
472
  },
473
  "appos":{
474
- "p":0.4938271605,
475
  "r":0.4819277108,
476
- "f":0.487804878
477
  },
478
  "nsubj:pass":{
479
- "p":0.875,
480
- "r":0.8235294118,
481
- "f":0.8484848485
482
  },
483
  "aux:pass":{
484
- "p":0.9469026549,
485
  "r":0.9553571429,
486
- "f":0.9511111111
487
  },
488
  "acl:relcl":{
489
- "p":0.5764705882,
490
- "r":0.5697674419,
491
- "f":0.5730994152
492
  },
493
  "advcl":{
494
- "p":0.4698795181,
495
- "r":0.5,
496
- "f":0.4844720497
497
  },
498
  "fixed":{
499
- "p":0.8705882353,
500
- "r":0.74,
501
- "f":0.8
502
  },
503
  "dep":{
504
- "p":0.3392857143,
505
- "r":0.6551724138,
506
- "f":0.4470588235
507
  },
508
  "expl:subj":{
509
- "p":0.7647058824,
510
  "r":0.8125,
511
- "f":0.7878787879
512
  },
513
  "expl:comp":{
514
- "p":0.6585365854,
515
- "r":0.9,
516
- "f":0.7605633803
517
  },
518
  "expl:pass":{
519
- "p":0.3333333333,
520
  "r":0.1428571429,
521
- "f":0.2
522
  },
523
  "ccomp":{
524
- "p":0.7058823529,
525
- "r":0.7058823529,
526
- "f":0.7058823529
527
  },
528
  "parataxis":{
529
- "p":0.5,
530
- "r":0.3571428571,
531
- "f":0.4166666667
532
  },
533
  "iobj":{
534
- "p":0.7222222222,
535
- "r":0.52,
536
- "f":0.6046511628
537
  },
538
  "obl:agent":{
539
- "p":0.8684210526,
540
  "r":0.7857142857,
541
- "f":0.825
542
  },
543
  "nsubj:caus":{
544
  "p":0.0,
@@ -571,9 +567,9 @@
571
  "f":0.0
572
  },
573
  "flat:foreign":{
574
- "p":1.0,
575
- "r":0.4285714286,
576
- "f":0.6
577
  },
578
  "orphan":{
579
  "p":0.0,
@@ -591,34 +587,34 @@
591
  "f":0.0
592
  }
593
  },
594
- "tag_acc":0.9448023502,
595
- "lemma_acc":0.9070078093,
596
- "ents_p":0.8332265556,
597
- "ents_r":0.8329930747,
598
- "ents_f":0.8331097988,
599
  "ents_per_type":{
600
  "PER":{
601
- "p":0.8976195492,
602
- "r":0.9158845024,
603
- "f":0.9066600468
604
  },
605
  "LOC":{
606
- "p":0.8411137734,
607
- "r":0.8516690371,
608
- "f":0.8463584968
609
  },
610
  "ORG":{
611
- "p":0.763618677,
612
- "r":0.7490458015,
613
- "f":0.7562620424
614
  },
615
  "MISC":{
616
- "p":0.7152963371,
617
- "r":0.6633620061,
618
- "f":0.6883509834
619
  }
620
  },
621
- "speed":4392.7454027339
622
  },
623
  "sources":[
624
  {
1
  {
2
  "lang":"fr",
3
  "name":"core_news_md",
4
+ "version":"3.3.0",
5
  "description":"French pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler, lemmatizer.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"LGPL-LR",
10
+ "spacy_version":">=3.3.0.dev0,<3.4.0",
11
+ "spacy_git_version":"849bef2de",
12
  "vectors":{
13
  "width":300,
14
  "vectors":20000,
255
  "vocative",
256
  "xcomp"
257
  ],
 
 
 
 
258
  "attribute_ruler":[
259
 
260
  ],
293
  "token_p":0.9844389844,
294
  "token_r":0.9896058454,
295
  "token_f":0.9870156531,
296
+ "pos_acc":0.9710899253,
297
+ "morph_acc":0.9620122674,
298
+ "morph_micro_p":0.9839828168,
299
+ "morph_micro_r":0.9768490313,
300
+ "morph_micro_f":0.9804029472,
301
  "morph_per_feat":{
302
  "Definite":{
303
+ "p":0.9868613139,
304
  "r":0.9868613139,
305
+ "f":0.9868613139
306
  },
307
  "Number":{
308
+ "p":0.992584353,
309
+ "r":0.985640648,
310
+ "f":0.9891003141
311
  },
312
  "PronType":{
313
+ "p":0.9942159383,
314
+ "r":0.9897632758,
315
+ "f":0.9919846105
316
  },
317
  "Gender":{
318
+ "p":0.9798813516,
319
+ "r":0.970866343,
320
+ "f":0.9753530167
321
  },
322
  "Mood":{
323
+ "p":0.9675090253,
324
+ "r":0.9520426288,
325
+ "f":0.9597135184
326
  },
327
  "Person":{
328
+ "p":0.9821428571,
329
+ "r":0.9685534591,
330
+ "f":0.9753008233
331
  },
332
  "Tense":{
333
+ "p":0.9578622816,
334
+ "r":0.9519918284,
335
+ "f":0.9549180328
336
  },
337
  "VerbForm":{
338
+ "p":0.9742310889,
339
+ "r":0.9701986755,
340
+ "f":0.972210701
341
  },
342
  "NumType":{
343
+ "p":0.9893992933,
344
+ "r":0.9556313993,
345
+ "f":0.9722222222
346
  },
347
  "Reflex":{
348
+ "p":1.0,
349
  "r":1.0,
350
+ "f":1.0
351
  },
352
  "Voice":{
353
+ "p":0.9304347826,
354
  "r":0.9553571429,
355
+ "f":0.9427312775
356
  },
357
  "Poss":{
358
+ "p":0.9827586207,
359
  "r":1.0,
360
+ "f":0.9913043478
361
  },
362
  "Polarity":{
363
  "p":1.0,
364
+ "r":0.9882352941,
365
+ "f":0.9940828402
366
  }
367
  },
368
+ "sents_p":0.853427896,
369
+ "sents_r":0.8919553503,
370
+ "sents_f":0.8646706587,
371
+ "dep_uas":0.8977489729,
372
+ "dep_las":0.8591264102,
373
  "dep_las_per_type":{
374
  "det":{
375
+ "p":0.9854014599,
376
+ "r":0.98062954,
377
+ "f":0.9830097087
378
  },
379
  "nsubj":{
380
+ "p":0.8819277108,
381
+ "r":0.8819277108,
382
+ "f":0.8819277108
383
  },
384
  "aux:tense":{
385
+ "p":0.952,
386
+ "r":0.952,
387
+ "f":0.952
388
  },
389
  "root":{
390
+ "p":0.8717339667,
391
+ "r":0.890776699,
392
+ "f":0.881152461
393
  },
394
  "obj":{
395
+ "p":0.8700906344,
396
+ "r":0.8545994065,
397
+ "f":0.8622754491
398
  },
399
  "cc":{
400
+ "p":0.8986175115,
401
+ "r":0.8986175115,
402
+ "f":0.8986175115
403
  },
404
  "case":{
405
+ "p":0.9695328368,
406
+ "r":0.9754768392,
407
+ "f":0.9724957555
408
  },
409
  "obl:mod":{
410
+ "p":0.6677316294,
411
+ "r":0.623880597,
412
+ "f":0.6450617284
413
  },
414
  "nmod":{
415
+ "p":0.8051330798,
416
+ "r":0.8461538462,
417
+ "f":0.8251339503
418
  },
419
  "conj":{
420
+ "p":0.5863453815,
421
+ "r":0.5748031496,
422
+ "f":0.5805168986
423
  },
424
  "nummod":{
425
  "p":0.9141104294,
427
  "f":0.8975903614
428
  },
429
  "amod":{
430
+ "p":0.9037037037,
431
+ "r":0.8888888889,
432
+ "f":0.8962350781
433
  },
434
  "acl":{
435
+ "p":0.6892655367,
436
+ "r":0.7052023121,
437
+ "f":0.6971428571
438
  },
439
  "mark":{
440
+ "p":0.88,
441
+ "r":0.872246696,
442
+ "f":0.8761061947
443
  },
444
  "xcomp":{
445
+ "p":0.8476821192,
446
+ "r":0.8476821192,
447
+ "f":0.8476821192
448
  },
449
  "flat:name":{
450
+ "p":0.9223300971,
451
+ "r":0.9047619048,
452
+ "f":0.9134615385
453
  },
454
  "cop":{
455
+ "p":0.8709677419,
456
+ "r":0.9,
457
+ "f":0.8852459016
458
  },
459
  "advmod":{
460
+ "p":0.8698412698,
461
+ "r":0.8589341693,
462
+ "f":0.8643533123
463
  },
464
  "obl:arg":{
465
+ "p":0.6872037915,
466
+ "r":0.6590909091,
467
+ "f":0.6728538283
468
  },
469
  "appos":{
470
+ "p":0.5263157895,
471
  "r":0.4819277108,
472
+ "f":0.5031446541
473
  },
474
  "nsubj:pass":{
475
+ "p":0.9156626506,
476
+ "r":0.8941176471,
477
+ "f":0.9047619048
478
  },
479
  "aux:pass":{
480
+ "p":0.963963964,
481
  "r":0.9553571429,
482
+ "f":0.9596412556
483
  },
484
  "acl:relcl":{
485
+ "p":0.6511627907,
486
+ "r":0.6511627907,
487
+ "f":0.6511627907
488
  },
489
  "advcl":{
490
+ "p":0.5128205128,
491
+ "r":0.5128205128,
492
+ "f":0.5128205128
493
  },
494
  "fixed":{
495
+ "p":0.8539325843,
496
+ "r":0.76,
497
+ "f":0.8042328042
498
  },
499
  "dep":{
500
+ "p":0.2571428571,
501
+ "r":0.6206896552,
502
+ "f":0.3636363636
503
  },
504
  "expl:subj":{
505
+ "p":0.8666666667,
506
  "r":0.8125,
507
+ "f":0.8387096774
508
  },
509
  "expl:comp":{
510
+ "p":0.625,
511
+ "r":0.8333333333,
512
+ "f":0.7142857143
513
  },
514
  "expl:pass":{
515
+ "p":0.25,
516
  "r":0.1428571429,
517
+ "f":0.1818181818
518
  },
519
  "ccomp":{
520
+ "p":0.6666666667,
521
+ "r":0.6666666667,
522
+ "f":0.6666666667
523
  },
524
  "parataxis":{
525
+ "p":0.5714285714,
526
+ "r":0.4285714286,
527
+ "f":0.4897959184
528
  },
529
  "iobj":{
530
+ "p":0.75,
531
+ "r":0.48,
532
+ "f":0.5853658537
533
  },
534
  "obl:agent":{
535
+ "p":0.8918918919,
536
  "r":0.7857142857,
537
+ "f":0.835443038
538
  },
539
  "nsubj:caus":{
540
  "p":0.0,
567
  "f":0.0
568
  },
569
  "flat:foreign":{
570
+ "p":0.0,
571
+ "r":0.0,
572
+ "f":0.0
573
  },
574
  "orphan":{
575
  "p":0.0,
587
  "f":0.0
588
  }
589
  },
590
+ "tag_acc":0.9424375161,
591
+ "lemma_acc":0.9063912865,
592
+ "ents_p":0.8317787005,
593
+ "ents_r":0.8299307474,
594
+ "ents_f":0.8308536964,
595
  "ents_per_type":{
596
  "PER":{
597
+ "p":0.8974413195,
598
+ "r":0.912230422,
599
+ "f":0.9047754406
600
  },
601
  "LOC":{
602
+ "p":0.8422664625,
603
+ "r":0.851250732,
604
+ "f":0.8467347661
605
  },
606
  "ORG":{
607
+ "p":0.7548623147,
608
+ "r":0.7480916031,
609
+ "f":0.751461708
610
  },
611
  "MISC":{
612
+ "p":0.7072900158,
613
+ "r":0.6506779414,
614
+ "f":0.6778039335
615
  }
616
  },
617
+ "speed":4445.2953793177
618
  },
619
  "sources":[
620
  {
morphologizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8f6e299aaab5cf2bcd757266929412d0e77f6f0eabb5c54d8d66b9858f5bbad
3
- size 76433
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f234c10dce74481a8744633cdac0e2e001e56a5d308278baf8952cff0c3eaef
3
+ size 76485
ner/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2eb85f2160479c0c66deb7fb71f6a64d43a53d93feeac102f95b62ae15ce8f1
3
- size 7091792
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05d7cd87ca49796c5636fd36d8c416c7166392369cf2d84c724462c9c8d4ff22
3
+ size 6496592
parser/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f6076c8cfc279056f9a92518c31679ab7b91e5c907f76ff4d159ab97396cbba
3
  size 304828
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c9329fa019d416ef3706ad75d4f89ecf07b1487169b271c5d9203e9d6a5e444
3
  size 304828
parser/moves CHANGED
@@ -1 +1 @@
1
- ��moves��{"0":{"":25255},"1":{"":21680},"2":{"case":7258,"det":6062,"nsubj":1982,"punct":1645,"advmod":1210,"cc":1205,"mark":1051,"aux:tense":673,"amod":662,"nummod":595,"aux:pass":544,"obl:mod":483,"nsubj:pass":425,"cop":365,"expl:comp":204,"obj":170,"expl:subj":164,"iobj":139,"advcl":123,"nmod":92,"expl:pass":40,"vocative":35,"dep":0},"3":{"nmod":5132,"punct":3954,"amod":2083,"conj":1517,"obj":1410,"obl:mod":1184,"obl:arg":1078,"acl":782,"xcomp":739,"flat:name":657,"advmod":562,"fixed":409,"appos":408,"acl:relcl":365,"advcl":306,"ccomp":238,"obl:agent":206,"dep":138,"nummod":117,"parataxis":92,"nsubj":75,"flat:foreign":63},"4":{"ROOT":2219}}�cfg��neg_key�
1
+ ��moves��{"0":{"":25345},"1":{"":21571},"2":{"case":7318,"det":6066,"nsubj":1969,"punct":1660,"cc":1214,"advmod":1209,"mark":1055,"aux:tense":673,"amod":664,"nummod":609,"aux:pass":546,"obl:mod":480,"nsubj:pass":420,"cop":366,"expl:comp":204,"obj":170,"expl:subj":165,"iobj":139,"advcl":123,"nmod":92,"expl:pass":40,"vocative":35,"dep":0},"3":{"nmod":4995,"punct":4040,"amod":2051,"conj":1514,"obj":1405,"obl:mod":1188,"obl:arg":1070,"acl":785,"xcomp":739,"flat:name":622,"advmod":564,"fixed":413,"appos":412,"acl:relcl":368,"advcl":306,"ccomp":238,"obl:agent":203,"dep":142,"nummod":124,"parataxis":95,"nsubj":76,"flat:foreign":59},"4":{"ROOT":2231}}�cfg��neg_key�
senter/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8f8d83b4bbb2ddd0ccc1600164d4800009725cfd3c90dc9b19a81c5e32864bd
3
- size 219901
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:236641e083cd8e6d0be18b66dda62d29b8ef0379abcbb81fd5bef54cd0e7a2df
3
+ size 219953
tok2vec/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ec17debc2efb7061b8328501691a3584231826b53ae2265cb104e696aab5ebd
3
- size 6960804
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7712b3912119628cdc4b5bf11b909e1e06a4e40f4672c5b9bce197726e152500
3
+ size 6365604
tokenizer CHANGED
The diff for this file is too large to render. See raw diff
vocab/key2row CHANGED
Binary files a/vocab/key2row and b/vocab/key2row differ