adrianeboyd commited on
Commit
9179a65
1 Parent(s): 5398b80

Update spaCy pipeline

Browse files
README.md CHANGED
@@ -14,55 +14,55 @@ model-index:
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
- value: 0.8183716075
18
  - name: NER Recall
19
  type: recall
20
- value: 0.8166666667
21
  - name: NER F Score
22
  type: f_score
23
- value: 0.8175182482
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
- value: 0.9633898305
31
  - task:
32
  name: POS
33
  type: token-classification
34
  metrics:
35
  - name: POS (UPOS) Accuracy
36
  type: accuracy
37
- value: 0.9633898305
38
  - task:
39
  name: MORPH
40
  type: token-classification
41
  metrics:
42
  - name: Morph (UFeats) Accuracy
43
  type: accuracy
44
- value: 0.9568038741
45
  - task:
46
  name: LEMMA
47
  type: token-classification
48
  metrics:
49
  - name: Lemma Accuracy
50
  type: accuracy
51
- value: 0.9516707022
52
  - task:
53
  name: UNLABELED_DEPENDENCIES
54
  type: token-classification
55
  metrics:
56
  - name: Unlabeled Attachment Score (UAS)
57
  type: f_score
58
- value: 0.8195787003
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
- value: 0.7807576266
66
  - task:
67
  name: SENTS
68
  type: token-classification
@@ -78,8 +78,8 @@ Danish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, l
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `da_core_news_lg` |
81
- | **Version** | `3.3.0` |
82
- | **spaCy** | `>=3.3.0.dev0,<3.4.0` |
83
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
84
  | **Components** | `tok2vec`, `morphologizer`, `parser`, `lemmatizer`, `senter`, `attribute_ruler`, `ner` |
85
  | **Vectors** | 500000 keys, 500000 unique vectors (300 dimensions) |
@@ -91,11 +91,11 @@ Danish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, l
91
 
92
  <details>
93
 
94
- <summary>View label scheme (193 labels for 3 components)</summary>
95
 
96
  | Component | Labels |
97
  | --- | --- |
98
- | **`morphologizer`** | `AdpType=Prep\|POS=ADP`, `Definite=Ind\|Gender=Com\|Number=Sing\|POS=NOUN`, `Mood=Ind\|POS=AUX\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `POS=PROPN`, `Definite=Ind\|Number=Sing\|POS=VERB\|Tense=Past\|VerbForm=Part`, `Definite=Def\|Gender=Neut\|Number=Sing\|POS=NOUN`, `POS=SCONJ`, `Definite=Def\|Gender=Com\|Number=Sing\|POS=NOUN`, `Mood=Ind\|POS=VERB\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `POS=ADV`, `Number=Plur\|POS=DET\|PronType=Dem`, `Degree=Pos\|Number=Plur\|POS=ADJ`, `Definite=Ind\|Gender=Com\|Number=Plur\|POS=NOUN`, `POS=PUNCT`, `POS=CCONJ`, `Definite=Ind\|Degree=Cmp\|Number=Sing\|POS=ADJ`, `Degree=Cmp\|POS=ADJ`, `POS=PRON\|PartType=Inf`, `Gender=Com\|Number=Sing\|POS=DET\|PronType=Ind`, `Definite=Ind\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Case=Acc\|Gender=Neut\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Definite=Ind\|Gender=Neut\|Number=Plur\|POS=NOUN`, `Definite=Def\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Gender=Neut\|Number=Sing\|POS=DET\|PronType=Dem`, `Degree=Pos\|POS=ADV`, `Definite=Def\|Number=Sing\|POS=VERB\|Tense=Past\|VerbForm=Part`, `Definite=Ind\|Gender=Neut\|Number=Sing\|POS=NOUN`, `POS=PRON\|PronType=Dem`, `NumType=Card\|POS=NUM`, `Definite=Ind\|Degree=Pos\|Gender=Neut\|Number=Sing\|POS=ADJ`, `Case=Acc\|Gender=Com\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Degree=Pos\|Gender=Com\|Number=Sing\|POS=ADJ`, `Case=Nom\|Gender=Com\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `NumType=Ord\|POS=ADJ`, `Gender=Com\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs\|Reflex=Yes`, `Mood=Ind\|POS=AUX\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `POS=VERB\|VerbForm=Inf\|Voice=Act`, `Mood=Ind\|POS=VERB\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `POS=NOUN`, `Mood=Ind\|POS=VERB\|Tense=Pres\|VerbForm=Fin\|Voice=Pass`, `POS=ADP\|PartType=Inf`, `Degree=Pos\|POS=ADJ`, `Definite=Def\|Gender=Com\|Number=Plur\|POS=NOUN`, `Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Definite=Def\|Gender=Com\|Number=Sing\|POS=NOUN`, `POS=AUX\|VerbForm=Inf\|Voice=Act`, `Definite=Ind\|Degree=Pos\|Gender=Com\|Number=Sing\|POS=ADJ`, `Gender=Com\|Number=Sing\|POS=DET\|PronType=Dem`, `Number=Plur\|POS=DET\|PronType=Ind`, `Gender=Com\|Number=Sing\|POS=PRON\|PronType=Ind`, `Case=Acc\|POS=PRON\|Person=3\|PronType=Prs\|Reflex=Yes`, `POS=PART\|PartType=Inf`, `Gender=Neut\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Acc\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Gen\|Definite=Def\|Gender=Neut\|Number=Sing\|POS=NOUN`, `Case=Nom\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Nom\|Gender=Com\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Nom\|Gender=Com\|POS=PRON\|PronType=Ind`, `Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Ind`, `Mood=Imp\|POS=VERB`, `Gender=Com\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Definite=Ind\|Number=Sing\|POS=AUX\|Tense=Past\|VerbForm=Part`, `POS=X`, `Case=Nom\|Gender=Com\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Gen\|Definite=Def\|Gender=Com\|Number=Plur\|POS=NOUN`, `POS=VERB\|Tense=Pres\|VerbForm=Part`, `Number=Plur\|POS=PRON\|PronType=Int,Rel`, `POS=VERB\|VerbForm=Inf\|Voice=Pass`, `Case=Gen\|Definite=Ind\|Gender=Com\|Number=Sing\|POS=NOUN`, `Degree=Cmp\|POS=ADV`, `POS=ADV\|PartType=Inf`, `Degree=Sup\|POS=ADV`, `Number=Plur\|POS=PRON\|PronType=Dem`, `Number=Plur\|POS=PRON\|PronType=Ind`, `Definite=Def\|Gender=Neut\|Number=Plur\|POS=NOUN`, `Case=Acc\|Gender=Com\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Gen\|POS=PROPN`, `POS=ADP`, `Degree=Cmp\|Number=Plur\|POS=ADJ`, `Definite=Def\|Degree=Sup\|POS=ADJ`, `Gender=Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Degree=Pos\|Number=Sing\|POS=ADJ`, `Number=Plur\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs\|Reflex=Yes`, `Gender=Com\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs\|Style=Form`, `Number=Plur\|POS=PRON\|PronType=Rcp`, `Case=Gen\|Degree=Cmp\|POS=ADJ`, `Case=Gen\|Definite=Def\|Gender=Neut\|Number=Plur\|POS=NOUN`, `Number[psor]=Plur\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `POS=INTJ`, `Number=Plur\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Degree=Pos\|Gender=Neut\|Number=Sing\|POS=ADJ`, `Gender=Neut\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs\|Style=Form`, `Case=Acc\|Gender=Com\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Gender=Com\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Definite=Ind\|Gender=Neut\|Number=Plur\|POS=NOUN`, `Number=Sing\|POS=PRON\|PronType=Int,Rel`, `Number=Plur\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs\|Style=Form`, `Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Int,Rel`, `Definite=Def\|Degree=Sup\|Number=Plur\|POS=ADJ`, `Case=Nom\|Gender=Com\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Gender=Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs\|Reflex=Yes`, `Definite=Ind\|Number=Sing\|POS=NOUN`, `Number=Plur\|POS=VERB\|Tense=Past\|VerbForm=Part`, `Number=Plur\|Number[psor]=Sing\|POS=PRON\|Person=3\|Poss=Yes\|PronType=Prs\|Reflex=Yes`, `POS=SYM`, `Case=Nom\|Gender=Com\|POS=PRON\|Person=2\|Polite=Form\|PronType=Prs`, `Degree=Sup\|POS=ADJ`, `Number=Plur\|POS=DET\|PronType=Ind\|Style=Arch`, `Case=Gen\|Gender=Com\|Number=Sing\|POS=DET\|PronType=Dem`, `Foreign=Yes\|POS=X`, `POS=DET\|Person=2\|Polite=Form\|Poss=Yes\|PronType=Prs`, `Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Dem`, `Case=Acc\|Gender=Com\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Gen\|Definite=Ind\|Gender=Neut\|Number=Sing\|POS=NOUN`, `Case=Gen\|POS=PRON\|PronType=Int,Rel`, `Gender=Com\|Number=Sing\|POS=PRON\|PronType=Dem`, `Abbr=Yes\|POS=X`, `Case=Gen\|Definite=Ind\|Gender=Com\|Number=Plur\|POS=NOUN`, `Definite=Def\|Degree=Abs\|POS=ADJ`, `Definite=Ind\|Degree=Sup\|Number=Sing\|POS=ADJ`, `Definite=Ind\|POS=NOUN`, `Gender=Com\|Number=Plur\|POS=NOUN`, `Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Gender=Com\|POS=PRON\|PronType=Int,Rel`, `Case=Nom\|Gender=Com\|Number=Plur\|POS=PRON\|Person=2\|PronType=Prs`, `Degree=Abs\|POS=ADV`, `POS=VERB\|VerbForm=Ger`, `POS=VERB\|Tense=Past\|VerbForm=Part`, `Definite=Def\|Degree=Sup\|Number=Sing\|POS=ADJ`, `Number=Plur\|Number[psor]=Plur\|POS=PRON\|Person=1\|Poss=Yes\|PronType=Prs\|Style=Form`, `Case=Gen\|Definite=Def\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Case=Gen\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Case=Acc\|Gender=Com\|POS=PRON\|Person=2\|Polite=Form\|PronType=Prs`, `Gender=Com\|Number=Sing\|POS=PRON\|PronType=Int,Rel`, `POS=VERB\|Tense=Pres`, `Case=Gen\|Number=Plur\|POS=DET\|PronType=Ind`, `Number[psor]=Plur\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `POS=PRON\|Person=2\|Polite=Form\|Poss=Yes\|PronType=Prs`, `Gender=Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `POS=AUX\|Tense=Pres\|VerbForm=Part`, `Mood=Ind\|POS=VERB\|Tense=Past\|VerbForm=Fin\|Voice=Pass`, `Gender=Com\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Poss=Yes\|PronType=Prs\|Reflex=Yes`, `Degree=Sup\|Number=Plur\|POS=ADJ`, `Case=Acc\|Gender=Com\|Number=Plur\|POS=PRON\|Person=2\|PronType=Prs`, `Gender=Neut\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Poss=Yes\|PronType=Prs\|Reflex=Yes`, `Definite=Ind\|Number=Plur\|POS=NOUN`, `Case=Gen\|Number=Plur\|POS=VERB\|Tense=Past\|VerbForm=Part`, `Mood=Imp\|POS=AUX`, `Gender=Com\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=1\|Poss=Yes\|PronType=Prs`, `Number[psor]=Sing\|POS=PRON\|Person=3\|Poss=Yes\|PronType=Prs`, `Definite=Def\|Gender=Com\|Number=Sing\|POS=VERB\|Tense=Past\|VerbForm=Part`, `Number=Plur\|Number[psor]=Sing\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Gender=Com\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Gen\|POS=NOUN`, `Number[psor]=Plur\|POS=PRON\|Person=3\|Poss=Yes\|PronType=Prs`, `POS=DET\|PronType=Dem`, `Definite=Def\|Number=Plur\|POS=NOUN` |
99
  | **`parser`** | `ROOT`, `acl:relcl`, `advcl`, `advmod`, `advmod:lmod`, `amod`, `appos`, `aux`, `case`, `cc`, `ccomp`, `compound:prt`, `conj`, `cop`, `dep`, `det`, `expl`, `fixed`, `flat`, `iobj`, `list`, `mark`, `nmod`, `nmod:poss`, `nsubj`, `nummod`, `obj`, `obl`, `obl:lmod`, `obl:tmod`, `punct`, `xcomp` |
100
  | **`ner`** | `LOC`, `MISC`, `ORG`, `PER` |
101
 
@@ -109,18 +109,18 @@ Danish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, l
109
  | `TOKEN_P` | 99.78 |
110
  | `TOKEN_R` | 99.75 |
111
  | `TOKEN_F` | 99.76 |
112
- | `POS_ACC` | 96.34 |
113
- | `MORPH_ACC` | 95.68 |
114
- | `MORPH_MICRO_P` | 97.27 |
115
- | `MORPH_MICRO_R` | 96.56 |
116
- | `MORPH_MICRO_F` | 96.91 |
117
  | `SENTS_P` | 91.04 |
118
  | `SENTS_R` | 90.07 |
119
  | `SENTS_F` | 90.55 |
120
- | `DEP_UAS` | 81.96 |
121
- | `DEP_LAS` | 78.08 |
122
- | `LEMMA_ACC` | 95.17 |
123
- | `TAG_ACC` | 96.34 |
124
- | `ENTS_P` | 81.84 |
125
- | `ENTS_R` | 81.67 |
126
- | `ENTS_F` | 81.75 |
 
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
+ value: 0.8161157025
18
  - name: NER Recall
19
  type: recall
20
+ value: 0.8229166667
21
  - name: NER F Score
22
  type: f_score
23
+ value: 0.8195020747
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
+ value: 0.9641646489
31
  - task:
32
  name: POS
33
  type: token-classification
34
  metrics:
35
  - name: POS (UPOS) Accuracy
36
  type: accuracy
37
+ value: 0.9641646489
38
  - task:
39
  name: MORPH
40
  type: token-classification
41
  metrics:
42
  - name: Morph (UFeats) Accuracy
43
  type: accuracy
44
+ value: 0.9538014528
45
  - task:
46
  name: LEMMA
47
  type: token-classification
48
  metrics:
49
  - name: Lemma Accuracy
50
  type: accuracy
51
+ value: 0.9518644068
52
  - task:
53
  name: UNLABELED_DEPENDENCIES
54
  type: token-classification
55
  metrics:
56
  - name: Unlabeled Attachment Score (UAS)
57
  type: f_score
58
+ value: 0.8220111732
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
+ value: 0.7817440366
66
  - task:
67
  name: SENTS
68
  type: token-classification
 
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `da_core_news_lg` |
81
+ | **Version** | `3.4.0` |
82
+ | **spaCy** | `>=3.4.0,<3.5.0` |
83
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
84
  | **Components** | `tok2vec`, `morphologizer`, `parser`, `lemmatizer`, `senter`, `attribute_ruler`, `ner` |
85
  | **Vectors** | 500000 keys, 500000 unique vectors (300 dimensions) |
 
91
 
92
  <details>
93
 
94
+ <summary>View label scheme (194 labels for 3 components)</summary>
95
 
96
  | Component | Labels |
97
  | --- | --- |
98
+ | **`morphologizer`** | `AdpType=Prep\|POS=ADP`, `Definite=Ind\|Gender=Com\|Number=Sing\|POS=NOUN`, `Mood=Ind\|POS=AUX\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `POS=PROPN`, `Definite=Ind\|Number=Sing\|POS=VERB\|Tense=Past\|VerbForm=Part`, `Definite=Def\|Gender=Neut\|Number=Sing\|POS=NOUN`, `POS=SCONJ`, `Definite=Def\|Gender=Com\|Number=Sing\|POS=NOUN`, `Mood=Ind\|POS=VERB\|Tense=Pres\|VerbForm=Fin\|Voice=Act`, `POS=ADV`, `Number=Plur\|POS=DET\|PronType=Dem`, `Degree=Pos\|Number=Plur\|POS=ADJ`, `Definite=Ind\|Gender=Com\|Number=Plur\|POS=NOUN`, `POS=PUNCT`, `POS=CCONJ`, `Definite=Ind\|Degree=Cmp\|Number=Sing\|POS=ADJ`, `Degree=Cmp\|POS=ADJ`, `POS=PRON\|PartType=Inf`, `Gender=Com\|Number=Sing\|POS=DET\|PronType=Ind`, `Definite=Ind\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Case=Acc\|Gender=Neut\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Definite=Ind\|Gender=Neut\|Number=Plur\|POS=NOUN`, `Definite=Def\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Gender=Neut\|Number=Sing\|POS=DET\|PronType=Dem`, `Degree=Pos\|POS=ADV`, `Definite=Def\|Number=Sing\|POS=VERB\|Tense=Past\|VerbForm=Part`, `Definite=Ind\|Gender=Neut\|Number=Sing\|POS=NOUN`, `POS=PRON\|PronType=Dem`, `NumType=Card\|POS=NUM`, `Definite=Ind\|Degree=Pos\|Gender=Neut\|Number=Sing\|POS=ADJ`, `Case=Acc\|Gender=Com\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Degree=Pos\|Gender=Com\|Number=Sing\|POS=ADJ`, `Case=Nom\|Gender=Com\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `NumType=Ord\|POS=ADJ`, `Gender=Com\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs\|Reflex=Yes`, `Mood=Ind\|POS=AUX\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `POS=VERB\|VerbForm=Inf\|Voice=Act`, `Mood=Ind\|POS=VERB\|Tense=Past\|VerbForm=Fin\|Voice=Act`, `POS=NOUN`, `Mood=Ind\|POS=VERB\|Tense=Pres\|VerbForm=Fin\|Voice=Pass`, `POS=ADP\|PartType=Inf`, `Degree=Pos\|POS=ADJ`, `Definite=Def\|Gender=Com\|Number=Plur\|POS=NOUN`, `Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Definite=Def\|Gender=Com\|Number=Sing\|POS=NOUN`, `POS=AUX\|VerbForm=Inf\|Voice=Act`, `Definite=Ind\|Degree=Pos\|Gender=Com\|Number=Sing\|POS=ADJ`, `Gender=Com\|Number=Sing\|POS=DET\|PronType=Dem`, `Number=Plur\|POS=DET\|PronType=Ind`, `Gender=Com\|Number=Sing\|POS=PRON\|PronType=Ind`, `Case=Acc\|POS=PRON\|Person=3\|PronType=Prs\|Reflex=Yes`, `POS=PART\|PartType=Inf`, `Gender=Neut\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Acc\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Gen\|Definite=Def\|Gender=Neut\|Number=Sing\|POS=NOUN`, `Case=Nom\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Nom\|Gender=Com\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Nom\|Gender=Com\|POS=PRON\|PronType=Ind`, `Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Ind`, `Mood=Imp\|POS=VERB`, `Gender=Com\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Definite=Ind\|Number=Sing\|POS=AUX\|Tense=Past\|VerbForm=Part`, `POS=X`, `Case=Nom\|Gender=Com\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Gen\|Definite=Def\|Gender=Com\|Number=Plur\|POS=NOUN`, `POS=VERB\|Tense=Pres\|VerbForm=Part`, `Number=Plur\|POS=PRON\|PronType=Int,Rel`, `POS=VERB\|VerbForm=Inf\|Voice=Pass`, `Case=Gen\|Definite=Ind\|Gender=Com\|Number=Sing\|POS=NOUN`, `Degree=Cmp\|POS=ADV`, `POS=ADV\|PartType=Inf`, `Degree=Sup\|POS=ADV`, `Number=Plur\|POS=PRON\|PronType=Dem`, `Number=Plur\|POS=PRON\|PronType=Ind`, `Definite=Def\|Gender=Neut\|Number=Plur\|POS=NOUN`, `Case=Acc\|Gender=Com\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Gen\|POS=PROPN`, `POS=ADP`, `Degree=Cmp\|Number=Plur\|POS=ADJ`, `Definite=Def\|Degree=Sup\|POS=ADJ`, `Gender=Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Degree=Pos\|Number=Sing\|POS=ADJ`, `Number=Plur\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs\|Reflex=Yes`, `Gender=Com\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs\|Style=Form`, `Number=Plur\|POS=PRON\|PronType=Rcp`, `Case=Gen\|Degree=Cmp\|POS=ADJ`, `POS=SPACE`, `Case=Gen\|Definite=Def\|Gender=Neut\|Number=Plur\|POS=NOUN`, `Number[psor]=Plur\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs`, `POS=INTJ`, `Number=Plur\|Number[psor]=Sing\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Degree=Pos\|Gender=Neut\|Number=Sing\|POS=ADJ`, `Gender=Neut\|Number=Sing\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs\|Style=Form`, `Case=Acc\|Gender=Com\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Gender=Com\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Definite=Ind\|Gender=Neut\|Number=Plur\|POS=NOUN`, `Number=Sing\|POS=PRON\|PronType=Int,Rel`, `Number=Plur\|Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs\|Style=Form`, `Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Int,Rel`, `Definite=Def\|Degree=Sup\|Number=Plur\|POS=ADJ`, `Case=Nom\|Gender=Com\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Gender=Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=3\|Poss=Yes\|PronType=Prs\|Reflex=Yes`, `Definite=Ind\|Number=Sing\|POS=NOUN`, `Number=Plur\|POS=VERB\|Tense=Past\|VerbForm=Part`, `Number=Plur\|Number[psor]=Sing\|POS=PRON\|Person=3\|Poss=Yes\|PronType=Prs\|Reflex=Yes`, `POS=SYM`, `Case=Nom\|Gender=Com\|POS=PRON\|Person=2\|Polite=Form\|PronType=Prs`, `Degree=Sup\|POS=ADJ`, `Number=Plur\|POS=DET\|PronType=Ind\|Style=Arch`, `Case=Gen\|Gender=Com\|Number=Sing\|POS=DET\|PronType=Dem`, `Foreign=Yes\|POS=X`, `POS=DET\|Person=2\|Polite=Form\|Poss=Yes\|PronType=Prs`, `Gender=Neut\|Number=Sing\|POS=PRON\|PronType=Dem`, `Case=Acc\|Gender=Com\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Gen\|Definite=Ind\|Gender=Neut\|Number=Sing\|POS=NOUN`, `Case=Gen\|POS=PRON\|PronType=Int,Rel`, `Gender=Com\|Number=Sing\|POS=PRON\|PronType=Dem`, `Abbr=Yes\|POS=X`, `Case=Gen\|Definite=Ind\|Gender=Com\|Number=Plur\|POS=NOUN`, `Definite=Def\|Degree=Abs\|POS=ADJ`, `Definite=Ind\|Degree=Sup\|Number=Sing\|POS=ADJ`, `Definite=Ind\|POS=NOUN`, `Gender=Com\|Number=Plur\|POS=NOUN`, `Number[psor]=Plur\|POS=DET\|Person=1\|Poss=Yes\|PronType=Prs`, `Gender=Com\|POS=PRON\|PronType=Int,Rel`, `Case=Nom\|Gender=Com\|Number=Plur\|POS=PRON\|Person=2\|PronType=Prs`, `Degree=Abs\|POS=ADV`, `POS=VERB\|VerbForm=Ger`, `POS=VERB\|Tense=Past\|VerbForm=Part`, `Definite=Def\|Degree=Sup\|Number=Sing\|POS=ADJ`, `Number=Plur\|Number[psor]=Plur\|POS=PRON\|Person=1\|Poss=Yes\|PronType=Prs\|Style=Form`, `Case=Gen\|Definite=Def\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Case=Gen\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Case=Acc\|Gender=Com\|POS=PRON\|Person=2\|Polite=Form\|PronType=Prs`, `Gender=Com\|Number=Sing\|POS=PRON\|PronType=Int,Rel`, `POS=VERB\|Tense=Pres`, `Case=Gen\|Number=Plur\|POS=DET\|PronType=Ind`, `Number[psor]=Plur\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `POS=PRON\|Person=2\|Polite=Form\|Poss=Yes\|PronType=Prs`, `Gender=Neut\|Number=Sing\|Number[psor]=Sing\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `POS=AUX\|Tense=Pres\|VerbForm=Part`, `Mood=Ind\|POS=VERB\|Tense=Past\|VerbForm=Fin\|Voice=Pass`, `Gender=Com\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Poss=Yes\|PronType=Prs\|Reflex=Yes`, `Degree=Sup\|Number=Plur\|POS=ADJ`, `Case=Acc\|Gender=Com\|Number=Plur\|POS=PRON\|Person=2\|PronType=Prs`, `Gender=Neut\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=3\|Poss=Yes\|PronType=Prs\|Reflex=Yes`, `Definite=Ind\|Number=Plur\|POS=NOUN`, `Case=Gen\|Number=Plur\|POS=VERB\|Tense=Past\|VerbForm=Part`, `Mood=Imp\|POS=AUX`, `Gender=Com\|Number=Sing\|Number[psor]=Sing\|POS=PRON\|Person=1\|Poss=Yes\|PronType=Prs`, `Number[psor]=Sing\|POS=PRON\|Person=3\|Poss=Yes\|PronType=Prs`, `Definite=Def\|Gender=Com\|Number=Sing\|POS=VERB\|Tense=Past\|VerbForm=Part`, `Number=Plur\|Number[psor]=Sing\|POS=DET\|Person=2\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Gender=Com\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Gen\|POS=NOUN`, `Number[psor]=Plur\|POS=PRON\|Person=3\|Poss=Yes\|PronType=Prs`, `POS=DET\|PronType=Dem`, `Definite=Def\|Number=Plur\|POS=NOUN` |
99
  | **`parser`** | `ROOT`, `acl:relcl`, `advcl`, `advmod`, `advmod:lmod`, `amod`, `appos`, `aux`, `case`, `cc`, `ccomp`, `compound:prt`, `conj`, `cop`, `dep`, `det`, `expl`, `fixed`, `flat`, `iobj`, `list`, `mark`, `nmod`, `nmod:poss`, `nsubj`, `nummod`, `obj`, `obl`, `obl:lmod`, `obl:tmod`, `punct`, `xcomp` |
100
  | **`ner`** | `LOC`, `MISC`, `ORG`, `PER` |
101
 
 
109
  | `TOKEN_P` | 99.78 |
110
  | `TOKEN_R` | 99.75 |
111
  | `TOKEN_F` | 99.76 |
112
+ | `POS_ACC` | 96.42 |
113
+ | `MORPH_ACC` | 95.38 |
114
+ | `MORPH_MICRO_P` | 97.06 |
115
+ | `MORPH_MICRO_R` | 96.42 |
116
+ | `MORPH_MICRO_F` | 96.74 |
117
  | `SENTS_P` | 91.04 |
118
  | `SENTS_R` | 90.07 |
119
  | `SENTS_F` | 90.55 |
120
+ | `DEP_UAS` | 82.20 |
121
+ | `DEP_LAS` | 78.17 |
122
+ | `LEMMA_ACC` | 95.19 |
123
+ | `TAG_ACC` | 96.42 |
124
+ | `ENTS_P` | 81.61 |
125
+ | `ENTS_R` | 82.29 |
126
+ | `ENTS_F` | 81.95 |
accuracy.json CHANGED
@@ -3,81 +3,81 @@
3
  "token_p": 0.9977732598,
4
  "token_r": 0.9974835463,
5
  "token_f": 0.997628382,
6
- "pos_acc": 0.9633898305,
7
- "morph_acc": 0.9568038741,
8
- "morph_micro_p": 0.9727434528,
9
- "morph_micro_r": 0.9655746807,
10
- "morph_micro_f": 0.9691458101,
11
  "morph_per_feat": {
12
  "Mood": {
13
- "p": 0.9799043062,
14
- "r": 0.9761677788,
15
- "f": 0.9780324737
16
  },
17
  "Tense": {
18
- "p": 0.9772727273,
19
- "r": 0.9713855422,
20
- "f": 0.9743202417
21
  },
22
  "VerbForm": {
23
- "p": 0.9686153846,
24
- "r": 0.9632802938,
25
- "f": 0.9659404725
26
  },
27
  "Voice": {
28
- "p": 0.9798206278,
29
- "r": 0.9798206278,
30
- "f": 0.9798206278
31
  },
32
  "Definite": {
33
- "p": 0.968812475,
34
- "r": 0.9573291189,
35
- "f": 0.963036566
36
  },
37
  "Gender": {
38
- "p": 0.9597720416,
39
- "r": 0.9514788966,
40
- "f": 0.9556074766
41
  },
42
  "Number": {
43
- "p": 0.9683961022,
44
- "r": 0.9590505999,
45
- "f": 0.9637006945
46
  },
47
  "AdpType": {
48
- "p": 0.9982206406,
49
  "r": 0.9920424403,
50
- "f": 0.9951219512
51
  },
52
  "PartType": {
53
- "p": 0.996763754,
54
  "r": 1.0,
55
- "f": 0.9983792545
56
  },
57
  "Case": {
58
- "p": 0.9806451613,
59
- "r": 0.9605055292,
60
- "f": 0.9704708699
61
  },
62
  "Person": {
63
- "p": 0.9804270463,
64
- "r": 0.9786856128,
65
- "f": 0.9795555556
66
  },
67
  "PronType": {
68
- "p": 0.9835390947,
69
- "r": 0.9827302632,
70
- "f": 0.9831345125
71
  },
72
  "NumType": {
73
- "p": 0.9931506849,
74
- "r": 0.9602649007,
75
- "f": 0.9764309764
76
  },
77
  "Degree": {
78
- "p": 0.9578313253,
79
- "r": 0.9578313253,
80
- "f": 0.9578313253
81
  },
82
  "Reflex": {
83
  "p": 1.0,
@@ -85,19 +85,19 @@
85
  "f": 1.0
86
  },
87
  "Number[psor]": {
88
- "p": 0.9772727273,
89
- "r": 1.0,
90
- "f": 0.9885057471
91
  },
92
  "Poss": {
93
- "p": 0.9887640449,
94
- "r": 1.0,
95
- "f": 0.9943502825
96
  },
97
  "Foreign": {
98
- "p": 0.6,
99
- "r": 0.3,
100
- "f": 0.4
101
  },
102
  "Abbr": {
103
  "p": 0.0,
@@ -118,143 +118,138 @@
118
  "sents_p": 0.9103942652,
119
  "sents_r": 0.9007092199,
120
  "sents_f": 0.9055258467,
121
- "dep_uas": 0.8195787003,
122
- "dep_las": 0.7807576266,
123
  "dep_las_per_type": {
124
  "advmod": {
125
- "p": 0.6955345061,
126
- "r": 0.7259887006,
127
- "f": 0.7104353836
128
  },
129
  "root": {
130
- "p": 0.824686941,
131
- "r": 0.8173758865,
132
- "f": 0.821015138
133
  },
134
  "nsubj": {
135
- "p": 0.8361884368,
136
- "r": 0.8238396624,
137
- "f": 0.829968119
138
  },
139
  "case": {
140
- "p": 0.9003984064,
141
- "r": 0.8915187377,
142
- "f": 0.8959365709
143
  },
144
  "obl": {
145
- "p": 0.7221297837,
146
- "r": 0.6739130435,
147
- "f": 0.697188755
148
  },
149
  "cc": {
150
- "p": 0.7630057803,
151
- "r": 0.7674418605,
152
- "f": 0.7652173913
153
  },
154
  "conj": {
155
- "p": 0.6106442577,
156
- "r": 0.5813333333,
157
- "f": 0.5956284153
158
  },
159
  "obj": {
160
- "p": 0.7893772894,
161
- "r": 0.8368932039,
162
- "f": 0.8124410933
163
  },
164
  "aux": {
165
- "p": 0.8764705882,
166
- "r": 0.8688046647,
167
- "f": 0.8726207906
168
  },
169
  "acl:relcl": {
170
- "p": 0.6300578035,
171
- "r": 0.5891891892,
172
- "f": 0.6089385475
173
  },
174
  "advmod:lmod": {
175
- "p": 0.7272727273,
176
- "r": 0.7164179104,
177
- "f": 0.7218045113
178
  },
179
  "det": {
180
- "p": 0.9140495868,
181
- "r": 0.9110378913,
182
- "f": 0.9125412541
183
  },
184
  "amod": {
185
- "p": 0.8080645161,
186
- "r": 0.8549488055,
187
- "f": 0.8308457711
188
  },
189
  "nmod:poss": {
190
- "p": 0.7373737374,
191
- "r": 0.7227722772,
192
- "f": 0.73
193
  },
194
  "ccomp": {
195
- "p": 0.7068965517,
196
- "r": 0.6612903226,
197
- "f": 0.6833333333
198
  },
199
  "nummod": {
200
- "p": 0.8360655738,
201
- "r": 0.85,
202
- "f": 0.8429752066
203
  },
204
  "flat": {
205
- "p": 0.7844311377,
206
- "r": 0.8675496689,
207
- "f": 0.8238993711
208
  },
209
  "compound:prt": {
210
- "p": 0.5,
211
- "r": 0.2926829268,
212
- "f": 0.3692307692
213
  },
214
  "advcl": {
215
- "p": 0.6545454545,
216
- "r": 0.6206896552,
217
- "f": 0.6371681416
218
  },
219
  "mark": {
220
- "p": 0.8781512605,
221
- "r": 0.8583162218,
222
- "f": 0.8681204569
223
  },
224
  "cop": {
225
- "p": 0.8121546961,
226
- "r": 0.84,
227
- "f": 0.8258426966
228
  },
229
  "dep": {
230
- "p": 0.145631068,
231
- "r": 0.2830188679,
232
- "f": 0.1923076923
233
  },
234
  "nmod": {
235
- "p": 0.6549707602,
236
- "r": 0.65625,
237
- "f": 0.6556097561
238
  },
239
  "iobj": {
240
- "p": 0.8125,
241
- "r": 0.5909090909,
242
- "f": 0.6842105263
243
  },
244
  "xcomp": {
245
- "p": 0.4772727273,
246
- "r": 0.3559322034,
247
- "f": 0.4077669903
248
- },
249
- "appos": {
250
- "p": 0.5384615385,
251
- "r": 0.4242424242,
252
- "f": 0.4745762712
253
  },
254
  "list": {
255
- "p": 0.5,
256
- "r": 0.3333333333,
257
- "f": 0.4
258
  },
259
  "vocative": {
260
  "p": 0.0,
@@ -262,57 +257,62 @@
262
  "f": 0.0
263
  },
264
  "fixed": {
265
- "p": 0.8717948718,
266
- "r": 0.8292682927,
267
- "f": 0.85
268
- },
269
- "obl:lmod": {
270
- "p": 0.0,
271
- "r": 0.0,
272
- "f": 0.0
273
  },
274
  "expl": {
275
- "p": 0.8529411765,
276
- "r": 0.8529411765,
277
- "f": 0.8529411765
 
 
 
 
 
278
  },
279
  "obl:tmod": {
280
- "p": 0.6363636364,
281
- "r": 0.3888888889,
282
- "f": 0.4827586207
283
  },
284
  "discourse": {
285
  "p": 0.0,
286
  "r": 0.0,
287
  "f": 0.0
 
 
 
 
 
288
  }
289
  },
290
- "lemma_acc": 0.9516707022,
291
- "tag_acc": 0.9633898305,
292
- "ents_p": 0.8183716075,
293
- "ents_r": 0.8166666667,
294
- "ents_f": 0.8175182482,
295
  "ents_per_type": {
296
  "PER": {
297
- "p": 0.8993710692,
298
- "r": 0.8614457831,
299
- "f": 0.88
300
  },
301
  "ORG": {
302
- "p": 0.7303370787,
303
- "r": 0.7222222222,
304
- "f": 0.7262569832
305
  },
306
  "MISC": {
307
- "p": 0.7288135593,
308
- "r": 0.7610619469,
309
- "f": 0.7445887446
310
  },
311
  "LOC": {
312
- "p": 0.8672566372,
313
- "r": 0.8828828829,
314
- "f": 0.875
315
  }
316
  },
317
- "speed": 10791.2692595094
318
  }
 
3
  "token_p": 0.9977732598,
4
  "token_r": 0.9974835463,
5
  "token_f": 0.997628382,
6
+ "pos_acc": 0.9641646489,
7
+ "morph_acc": 0.9538014528,
8
+ "morph_micro_p": 0.9705792683,
9
+ "morph_micro_r": 0.9641613245,
10
+ "morph_micro_f": 0.9673596516,
11
  "morph_per_feat": {
12
  "Mood": {
13
+ "p": 0.9789473684,
14
+ "r": 0.97521449,
15
+ "f": 0.9770773639
16
  },
17
  "Tense": {
18
+ "p": 0.9743396226,
19
+ "r": 0.9721385542,
20
+ "f": 0.973237844
21
  },
22
  "VerbForm": {
23
+ "p": 0.9649014778,
24
+ "r": 0.958996328,
25
+ "f": 0.9619398404
26
  },
27
  "Voice": {
28
+ "p": 0.9789631856,
29
+ "r": 0.9738415546,
30
+ "f": 0.9763956538
31
  },
32
  "Definite": {
33
+ "p": 0.9642147117,
34
+ "r": 0.9581193204,
35
+ "f": 0.9611573524
36
  },
37
  "Gender": {
38
+ "p": 0.9558823529,
39
+ "r": 0.9504818877,
40
+ "f": 0.9531744709
41
  },
42
  "Number": {
43
+ "p": 0.96478318,
44
+ "r": 0.9574856547,
45
+ "f": 0.9611205655
46
  },
47
  "AdpType": {
48
+ "p": 1.0,
49
  "r": 0.9920424403,
50
+ "f": 0.9960053262
51
  },
52
  "PartType": {
53
+ "p": 1.0,
54
  "r": 1.0,
55
+ "f": 1.0
56
  },
57
  "Case": {
58
+ "p": 0.9791666667,
59
+ "r": 0.9652448657,
60
+ "f": 0.9721559268
61
  },
62
  "Person": {
63
+ "p": 0.9857651246,
64
+ "r": 0.9840142096,
65
+ "f": 0.9848888889
66
  },
67
  "PronType": {
68
+ "p": 0.9868095631,
69
+ "r": 0.984375,
70
+ "f": 0.9855907781
71
  },
72
  "NumType": {
73
+ "p": 0.972972973,
74
+ "r": 0.9536423841,
75
+ "f": 0.9632107023
76
  },
77
  "Degree": {
78
+ "p": 0.9524969549,
79
+ "r": 0.9421686747,
80
+ "f": 0.9473046638
81
  },
82
  "Reflex": {
83
  "p": 1.0,
 
85
  "f": 1.0
86
  },
87
  "Number[psor]": {
88
+ "p": 0.988372093,
89
+ "r": 0.988372093,
90
+ "f": 0.988372093
91
  },
92
  "Poss": {
93
+ "p": 1.0,
94
+ "r": 0.9886363636,
95
+ "f": 0.9942857143
96
  },
97
  "Foreign": {
98
+ "p": 1.0,
99
+ "r": 0.5,
100
+ "f": 0.6666666667
101
  },
102
  "Abbr": {
103
  "p": 0.0,
 
118
  "sents_p": 0.9103942652,
119
  "sents_r": 0.9007092199,
120
  "sents_f": 0.9055258467,
121
+ "dep_uas": 0.8220111732,
122
+ "dep_las": 0.7817440366,
123
  "dep_las_per_type": {
124
  "advmod": {
125
+ "p": 0.6882758621,
126
+ "r": 0.7048022599,
127
+ "f": 0.6964410328
128
  },
129
  "root": {
130
+ "p": 0.8369175627,
131
+ "r": 0.8280141844,
132
+ "f": 0.8324420677
133
  },
134
  "nsubj": {
135
+ "p": 0.8381256656,
136
+ "r": 0.8301687764,
137
+ "f": 0.8341282459
138
  },
139
  "case": {
140
+ "p": 0.8997020854,
141
+ "r": 0.8934911243,
142
+ "f": 0.8965858486
143
  },
144
  "obl": {
145
+ "p": 0.7044728435,
146
+ "r": 0.6847826087,
147
+ "f": 0.694488189
148
  },
149
  "cc": {
150
+ "p": 0.7735294118,
151
+ "r": 0.7645348837,
152
+ "f": 0.769005848
153
  },
154
  "conj": {
155
+ "p": 0.6239782016,
156
+ "r": 0.6106666667,
157
+ "f": 0.6172506739
158
  },
159
  "obj": {
160
+ "p": 0.7985347985,
161
+ "r": 0.8466019417,
162
+ "f": 0.821866164
163
  },
164
  "aux": {
165
+ "p": 0.8735294118,
166
+ "r": 0.8658892128,
167
+ "f": 0.8696925329
168
  },
169
  "acl:relcl": {
170
+ "p": 0.6271186441,
171
+ "r": 0.6,
172
+ "f": 0.6132596685
173
  },
174
  "advmod:lmod": {
175
+ "p": 0.7014925373,
176
+ "r": 0.7014925373,
177
+ "f": 0.7014925373
178
  },
179
  "det": {
180
+ "p": 0.9129720854,
181
+ "r": 0.9159802306,
182
+ "f": 0.9144736842
183
  },
184
  "amod": {
185
+ "p": 0.8073089701,
186
+ "r": 0.8293515358,
187
+ "f": 0.8181818182
188
  },
189
  "nmod:poss": {
190
+ "p": 0.7741935484,
191
+ "r": 0.7128712871,
192
+ "f": 0.7422680412
193
  },
194
  "ccomp": {
195
+ "p": 0.6865671642,
196
+ "r": 0.7419354839,
197
+ "f": 0.7131782946
198
  },
199
  "nummod": {
200
+ "p": 0.8536585366,
201
+ "r": 0.875,
202
+ "f": 0.8641975309
203
  },
204
  "flat": {
205
+ "p": 0.7784431138,
206
+ "r": 0.8609271523,
207
+ "f": 0.8176100629
208
  },
209
  "compound:prt": {
210
+ "p": 0.4411764706,
211
+ "r": 0.3658536585,
212
+ "f": 0.4
213
  },
214
  "advcl": {
215
+ "p": 0.6120689655,
216
+ "r": 0.6120689655,
217
+ "f": 0.6120689655
218
  },
219
  "mark": {
220
+ "p": 0.889596603,
221
+ "r": 0.8603696099,
222
+ "f": 0.8747390397
223
  },
224
  "cop": {
225
+ "p": 0.8021978022,
226
+ "r": 0.8342857143,
227
+ "f": 0.8179271709
228
  },
229
  "dep": {
230
+ "p": 0.1304347826,
231
+ "r": 0.2264150943,
232
+ "f": 0.1655172414
233
  },
234
  "nmod": {
235
+ "p": 0.6620825147,
236
+ "r": 0.658203125,
237
+ "f": 0.6601371205
238
  },
239
  "iobj": {
240
+ "p": 0.8333333333,
241
+ "r": 0.4545454545,
242
+ "f": 0.5882352941
243
  },
244
  "xcomp": {
245
+ "p": 0.5365853659,
246
+ "r": 0.3728813559,
247
+ "f": 0.44
 
 
 
 
 
248
  },
249
  "list": {
250
+ "p": 0.3333333333,
251
+ "r": 0.2222222222,
252
+ "f": 0.2666666667
253
  },
254
  "vocative": {
255
  "p": 0.0,
 
257
  "f": 0.0
258
  },
259
  "fixed": {
260
+ "p": 0.8461538462,
261
+ "r": 0.8048780488,
262
+ "f": 0.825
 
 
 
 
 
263
  },
264
  "expl": {
265
+ "p": 0.8484848485,
266
+ "r": 0.8235294118,
267
+ "f": 0.8358208955
268
+ },
269
+ "appos": {
270
+ "p": 0.5862068966,
271
+ "r": 0.5151515152,
272
+ "f": 0.5483870968
273
  },
274
  "obl:tmod": {
275
+ "p": 0.8333333333,
276
+ "r": 0.2777777778,
277
+ "f": 0.4166666667
278
  },
279
  "discourse": {
280
  "p": 0.0,
281
  "r": 0.0,
282
  "f": 0.0
283
+ },
284
+ "obl:lmod": {
285
+ "p": 0.0,
286
+ "r": 0.0,
287
+ "f": 0.0
288
  }
289
  },
290
+ "lemma_acc": 0.9518644068,
291
+ "tag_acc": 0.9641646489,
292
+ "ents_p": 0.8161157025,
293
+ "ents_r": 0.8229166667,
294
+ "ents_f": 0.8195020747,
295
  "ents_per_type": {
296
  "PER": {
297
+ "p": 0.9230769231,
298
+ "r": 0.8674698795,
299
+ "f": 0.8944099379
300
  },
301
  "ORG": {
302
+ "p": 0.7528089888,
303
+ "r": 0.7444444444,
304
+ "f": 0.748603352
305
  },
306
  "MISC": {
307
+ "p": 0.6910569106,
308
+ "r": 0.7522123894,
309
+ "f": 0.7203389831
310
  },
311
  "LOC": {
312
+ "p": 0.8534482759,
313
+ "r": 0.8918918919,
314
+ "f": 0.872246696
315
  }
316
  },
317
+ "speed": 12175.9946774514
318
  }
da_core_news_lg-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70b519f9d735120b8eee33370806c00bdb12214887bf6793783421fbbbff1dc3
3
- size 567085252
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e579a353ad8e99bf8147886c23dd03a8ec936c221a0670eb4d69ead8a2c85e6a
3
+ size 567080666
lemmatizer/cfg CHANGED
@@ -68,382 +68,379 @@
68
  145,
69
  147,
70
  148,
71
- 149,
72
- 153,
73
- 155,
74
- 158,
75
- 161,
76
- 164,
77
- 166,
78
- 168,
79
- 170,
80
- 172,
81
  174,
82
- 175,
83
- 177,
84
- 179,
85
- 182,
86
- 184,
87
- 186,
88
- 188,
89
- 190,
90
- 192,
91
- 194,
92
- 196,
93
- 199,
94
- 201,
95
  203,
96
- 204,
97
  207,
98
- 208,
99
  209,
 
100
  211,
101
  213,
102
- 214,
103
- 216,
104
- 218,
105
  220,
106
  222,
107
  224,
108
- 226,
109
  229,
110
- 231,
111
  232,
112
  233,
113
  235,
114
  236,
115
- 238,
116
- 239,
117
- 243,
118
- 249,
119
- 253,
120
- 255,
121
- 257,
122
- 259,
123
  261,
124
  262,
125
  263,
126
- 264,
127
- 267,
128
  269,
129
- 270,
130
- 272,
131
- 274,
132
- 276,
133
- 278,
134
- 280,
135
- 282,
136
  284,
137
  286,
 
138
  290,
139
- 291,
140
  293,
141
  295,
 
142
  297,
143
  299,
144
- 300,
145
- 302,
146
- 303,
147
  304,
148
- 306,
149
- 308,
150
- 311,
151
- 314,
152
  315,
153
- 317,
 
 
154
  320,
155
- 321,
156
  323,
157
- 324,
158
  326,
159
- 327,
160
- 328,
161
  330,
162
- 331,
163
  333,
164
  337,
165
  339,
166
- 340,
167
- 344,
168
  346,
169
- 350,
170
- 353,
 
 
171
  354,
172
  355,
173
- 358,
 
174
  360,
175
- 361,
176
  363,
177
- 365,
178
- 366,
179
- 369,
180
  372,
181
  373,
 
 
182
  376,
183
- 380,
184
- 382,
 
185
  383,
186
- 384,
187
- 386,
188
  387,
 
189
  389,
190
  391,
191
- 392,
192
- 394,
193
  395,
194
- 398,
195
  400,
196
  402,
 
197
  404,
 
198
  406,
 
199
  409,
200
- 411,
201
  412,
202
  413,
203
  415,
204
- 417,
205
- 420,
 
206
  421,
207
  423,
208
- 424,
209
  425,
210
  427,
211
  429,
212
  431,
213
  433,
214
- 434,
215
- 436,
216
  437,
217
  439,
218
- 440,
219
  442,
220
  444,
221
- 445,
222
- 449,
223
- 450,
224
  452,
225
  454,
226
- 457,
227
- 459,
 
 
228
  462,
229
  465,
230
  466,
231
- 468,
232
  470,
233
- 471,
234
  474,
235
  475,
236
  478,
237
- 480,
238
- 483,
239
- 485,
240
- 486,
241
  487,
242
  489,
 
243
  491,
244
  492,
245
  493,
246
- 495,
247
  496,
248
- 498,
249
- 500,
250
  501,
251
  502,
252
  503,
253
  504,
254
  505,
255
- 507,
256
  508,
257
  509,
258
- 510,
259
  511,
260
- 512,
261
- 514,
262
  515,
263
- 516,
264
- 518,
265
  519,
266
  520,
267
  521,
268
  523,
 
269
  525,
270
  526,
271
  528,
 
272
  531,
273
- 533,
274
- 535,
275
- 453,
276
- 536,
277
  538,
278
  539,
279
- 541,
280
- 545,
281
- 547,
282
  548,
283
- 549,
284
  550,
285
  551,
 
286
  553,
287
  554,
288
- 555,
289
- 557,
290
  559,
291
  560,
292
- 561,
293
- 563,
294
  565,
295
  566,
296
  567,
297
- 568,
298
  570,
299
- 571,
300
- 575,
301
- 577,
302
  578,
303
- 579,
304
- 582,
305
- 585,
306
  587,
307
- 589,
308
- 593,
309
  594,
310
- 596,
311
- 597,
312
  601,
 
313
  603,
314
- 605,
315
  609,
316
  611,
317
- 612,
318
- 613,
319
- 614,
320
  615,
321
- 616,
322
  617,
 
323
  619,
 
324
  621,
325
- 622,
326
- 624,
327
  625,
328
- 627,
329
  628,
330
- 629,
331
- 632,
332
- 634,
333
- 638,
 
334
  639,
335
- 640,
336
- 642,
337
- 644,
338
  647,
339
  649,
340
- 650,
341
- 651,
342
- 653,
343
  654,
344
  655,
345
  657,
346
  658,
347
- 659,
348
  661,
349
- 663,
350
- 665,
351
- 667,
352
- 669,
353
  670,
354
- 672,
355
- 674,
 
356
  676,
357
- 677,
358
  678,
359
  680,
360
- 682,
361
  683,
362
  685,
363
- 686,
364
  688,
365
- 689,
366
  690,
367
  691,
368
- 694,
369
- 695,
370
  696,
371
  697,
 
372
  699,
373
- 700,
374
  701,
375
  703,
 
376
  705,
377
  706,
378
- 707,
379
- 708,
380
- 712,
381
  715,
382
  716,
383
- 718,
384
  720,
385
- 724,
 
386
  726,
 
387
  729,
388
  730,
389
  732,
390
- 733,
391
  734,
392
  736,
393
- 738,
394
  739,
395
  740,
396
  741,
397
  742,
398
- 743,
399
- 744,
400
- 747,
401
- 749,
402
- 753,
403
- 756,
404
- 758,
405
  759,
 
406
  761,
407
- 762,
408
  763,
409
  764,
410
- 766,
411
- 768,
412
  769,
 
413
  771,
 
414
  773,
415
  774,
416
  775,
417
  776,
418
- 777,
419
- 781,
420
- 783,
421
  784,
422
  785,
423
- 788,
424
- 791,
 
425
  792,
426
- 794,
427
  796,
428
- 797,
429
  798,
430
- 799,
431
  800,
432
- 802,
433
  803,
434
  804,
435
  805,
436
  806,
437
  808,
438
  809,
439
- 810,
440
  811,
441
  812,
 
442
  814,
443
  815,
444
  817,
445
  819,
446
- 820,
447
  822,
448
  824,
449
  825,
@@ -452,6 +449,8 @@
452
  831,
453
  833,
454
  835,
455
- 837
 
 
456
  ]
457
  }
 
68
  145,
69
  147,
70
  148,
71
+ 152,
72
+ 154,
73
+ 157,
74
+ 160,
75
+ 163,
76
+ 165,
77
+ 167,
78
+ 169,
79
+ 171,
80
+ 173,
81
  174,
82
+ 176,
83
+ 178,
84
+ 181,
85
+ 183,
86
+ 185,
87
+ 187,
88
+ 189,
89
+ 191,
90
+ 193,
91
+ 195,
92
+ 198,
93
+ 200,
94
+ 202,
95
  203,
96
+ 206,
97
  207,
 
98
  209,
99
+ 210,
100
  211,
101
  213,
102
+ 215,
103
+ 217,
104
+ 219,
105
  220,
106
  222,
107
  224,
108
+ 227,
109
  229,
110
+ 230,
111
  232,
112
  233,
113
  235,
114
  236,
115
+ 240,
116
+ 246,
117
+ 250,
118
+ 252,
119
+ 254,
120
+ 256,
121
+ 258,
122
+ 260,
123
  261,
124
  262,
125
  263,
126
+ 266,
127
+ 268,
128
  269,
129
+ 271,
130
+ 273,
131
+ 275,
132
+ 277,
133
+ 279,
134
+ 283,
 
135
  284,
136
  286,
137
+ 288,
138
  290,
139
+ 292,
140
  293,
141
  295,
142
+ 296,
143
  297,
144
  299,
145
+ 301,
 
 
146
  304,
147
+ 307,
148
+ 309,
149
+ 312,
150
+ 313,
151
  315,
152
+ 316,
153
+ 318,
154
+ 319,
155
  320,
156
+ 322,
157
  323,
158
+ 325,
159
  326,
 
 
160
  330,
161
+ 332,
162
  333,
163
  337,
164
  339,
165
+ 343,
 
166
  346,
167
+ 347,
168
+ 348,
169
+ 351,
170
+ 352,
171
  354,
172
  355,
173
+ 356,
174
+ 359,
175
  360,
 
176
  363,
177
+ 364,
178
+ 367,
179
+ 371,
180
  372,
181
  373,
182
+ 374,
183
+ 375,
184
  376,
185
+ 377,
186
+ 379,
187
+ 381,
188
  383,
189
+ 385,
 
190
  387,
191
+ 388,
192
  389,
193
  391,
194
+ 393,
 
195
  395,
196
+ 397,
197
  400,
198
  402,
199
+ 403,
200
  404,
201
+ 405,
202
  406,
203
+ 408,
204
  409,
 
205
  412,
206
  413,
207
  415,
208
+ 416,
209
+ 418,
210
+ 419,
211
  421,
212
  423,
 
213
  425,
214
  427,
215
  429,
216
  431,
217
  433,
218
+ 435,
 
219
  437,
220
  439,
221
+ 441,
222
  442,
223
  444,
224
+ 446,
225
+ 447,
226
+ 451,
227
  452,
228
  454,
229
+ 455,
230
+ 456,
231
+ 458,
232
+ 461,
233
  462,
234
  465,
235
  466,
236
+ 469,
237
  470,
238
+ 472,
239
  474,
240
  475,
241
  478,
242
+ 479,
243
+ 482,
244
+ 484,
 
245
  487,
246
  489,
247
+ 490,
248
  491,
249
  492,
250
  493,
251
+ 494,
252
  496,
253
+ 497,
254
+ 499,
255
  501,
256
  502,
257
  503,
258
  504,
259
  505,
260
+ 506,
261
  508,
262
  509,
 
263
  511,
264
+ 513,
 
265
  515,
266
+ 517,
 
267
  519,
268
  520,
269
  521,
270
  523,
271
+ 524,
272
  525,
273
  526,
274
  528,
275
+ 529,
276
  531,
277
+ 532,
278
+ 534,
279
+ 537,
 
280
  538,
281
  539,
282
+ 540,
283
+ 542,
284
+ 544,
285
  548,
 
286
  550,
287
  551,
288
+ 552,
289
  553,
290
  554,
291
+ 556,
292
+ 558,
293
  559,
294
  560,
295
+ 562,
296
+ 564,
297
  565,
298
  566,
299
  567,
300
+ 569,
301
  570,
302
+ 574,
303
+ 576,
 
304
  578,
305
+ 581,
306
+ 583,
307
+ 584,
308
  587,
309
+ 590,
310
+ 592,
311
  594,
312
+ 598,
313
+ 599,
314
  601,
315
+ 602,
316
  603,
317
+ 607,
318
  609,
319
  611,
 
 
 
320
  615,
 
321
  617,
322
+ 618,
323
  619,
324
+ 620,
325
  621,
326
+ 623,
 
327
  625,
328
+ 626,
329
  628,
330
+ 630,
331
+ 631,
332
+ 633,
333
+ 635,
334
+ 636,
335
  639,
336
+ 641,
337
+ 645,
338
+ 646,
339
  647,
340
  649,
341
+ 652,
 
 
342
  654,
343
  655,
344
  657,
345
  658,
346
+ 660,
347
  661,
348
+ 662,
349
+ 664,
350
+ 666,
351
+ 668,
352
  670,
353
+ 671,
354
+ 673,
355
+ 675,
356
  676,
 
357
  678,
358
  680,
359
+ 681,
360
  683,
361
  685,
362
+ 687,
363
  688,
 
364
  690,
365
  691,
366
+ 692,
367
+ 693,
368
  696,
369
  697,
370
+ 698,
371
  699,
 
372
  701,
373
  703,
374
+ 704,
375
  705,
376
  706,
377
+ 710,
378
+ 713,
 
379
  715,
380
  716,
 
381
  720,
382
+ 722,
383
+ 725,
384
  726,
385
+ 728,
386
  729,
387
  730,
388
  732,
 
389
  734,
390
  736,
391
+ 737,
392
  739,
393
  740,
394
  741,
395
  742,
396
+ 745,
397
+ 746,
398
+ 748,
399
+ 752,
400
+ 755,
401
+ 757,
 
402
  759,
403
+ 760,
404
  761,
 
405
  763,
406
  764,
407
+ 765,
408
+ 767,
409
  769,
410
+ 770,
411
  771,
412
+ 772,
413
  773,
414
  774,
415
  775,
416
  776,
417
+ 780,
418
+ 782,
 
419
  784,
420
  785,
421
+ 786,
422
+ 787,
423
+ 790,
424
  792,
425
+ 795,
426
  796,
 
427
  798,
 
428
  800,
429
+ 801,
430
  803,
431
  804,
432
  805,
433
  806,
434
  808,
435
  809,
 
436
  811,
437
  812,
438
+ 813,
439
  814,
440
  815,
441
  817,
442
  819,
443
+ 821,
444
  822,
445
  824,
446
  825,
 
449
  831,
450
  833,
451
  835,
452
+ 837,
453
+ 839,
454
+ 841
455
  ]
456
  }
lemmatizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd1961075ded3bc09a5a58ead51adad20e36d70d2a099362fe21386796b1521e
3
- size 176206
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3829adc1ce8feafa2cc991916850f93f546fd7a93605155c201240dbc31ea7c7
3
+ size 175818
lemmatizer/trees CHANGED
Binary files a/lemmatizer/trees and b/lemmatizer/trees differ
 
meta.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "lang":"da",
3
  "name":"core_news_lg",
4
- "version":"3.3.0",
5
  "description":"Danish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, lemmatizer (trainable_lemmatizer), senter, ner, attribute_ruler.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"CC BY-SA 4.0",
10
- "spacy_version":">=3.3.0.dev0,<3.4.0",
11
- "spacy_git_version":"849bef2de",
12
  "vectors":{
13
  "width":300,
14
  "vectors":500000,
@@ -106,6 +106,7 @@
106
  "Gender=Com|Number=Sing|Number[psor]=Plur|POS=DET|Person=1|Poss=Yes|PronType=Prs|Style=Form",
107
  "Number=Plur|POS=PRON|PronType=Rcp",
108
  "Case=Gen|Degree=Cmp|POS=ADJ",
 
109
  "Case=Gen|Definite=Def|Gender=Neut|Number=Plur|POS=NOUN",
110
  "Number[psor]=Plur|POS=DET|Person=3|Poss=Yes|PronType=Prs",
111
  "POS=INTJ",
@@ -247,81 +248,81 @@
247
  "token_p":0.9977732598,
248
  "token_r":0.9974835463,
249
  "token_f":0.997628382,
250
- "pos_acc":0.9633898305,
251
- "morph_acc":0.9568038741,
252
- "morph_micro_p":0.9727434528,
253
- "morph_micro_r":0.9655746807,
254
- "morph_micro_f":0.9691458101,
255
  "morph_per_feat":{
256
  "Mood":{
257
- "p":0.9799043062,
258
- "r":0.9761677788,
259
- "f":0.9780324737
260
  },
261
  "Tense":{
262
- "p":0.9772727273,
263
- "r":0.9713855422,
264
- "f":0.9743202417
265
  },
266
  "VerbForm":{
267
- "p":0.9686153846,
268
- "r":0.9632802938,
269
- "f":0.9659404725
270
  },
271
  "Voice":{
272
- "p":0.9798206278,
273
- "r":0.9798206278,
274
- "f":0.9798206278
275
  },
276
  "Definite":{
277
- "p":0.968812475,
278
- "r":0.9573291189,
279
- "f":0.963036566
280
  },
281
  "Gender":{
282
- "p":0.9597720416,
283
- "r":0.9514788966,
284
- "f":0.9556074766
285
  },
286
  "Number":{
287
- "p":0.9683961022,
288
- "r":0.9590505999,
289
- "f":0.9637006945
290
  },
291
  "AdpType":{
292
- "p":0.9982206406,
293
  "r":0.9920424403,
294
- "f":0.9951219512
295
  },
296
  "PartType":{
297
- "p":0.996763754,
298
  "r":1.0,
299
- "f":0.9983792545
300
  },
301
  "Case":{
302
- "p":0.9806451613,
303
- "r":0.9605055292,
304
- "f":0.9704708699
305
  },
306
  "Person":{
307
- "p":0.9804270463,
308
- "r":0.9786856128,
309
- "f":0.9795555556
310
  },
311
  "PronType":{
312
- "p":0.9835390947,
313
- "r":0.9827302632,
314
- "f":0.9831345125
315
  },
316
  "NumType":{
317
- "p":0.9931506849,
318
- "r":0.9602649007,
319
- "f":0.9764309764
320
  },
321
  "Degree":{
322
- "p":0.9578313253,
323
- "r":0.9578313253,
324
- "f":0.9578313253
325
  },
326
  "Reflex":{
327
  "p":1.0,
@@ -329,19 +330,19 @@
329
  "f":1.0
330
  },
331
  "Number[psor]":{
332
- "p":0.9772727273,
333
- "r":1.0,
334
- "f":0.9885057471
335
  },
336
  "Poss":{
337
- "p":0.9887640449,
338
- "r":1.0,
339
- "f":0.9943502825
340
  },
341
  "Foreign":{
342
- "p":0.6,
343
- "r":0.3,
344
- "f":0.4
345
  },
346
  "Abbr":{
347
  "p":0.0,
@@ -362,143 +363,138 @@
362
  "sents_p":0.9103942652,
363
  "sents_r":0.9007092199,
364
  "sents_f":0.9055258467,
365
- "dep_uas":0.8195787003,
366
- "dep_las":0.7807576266,
367
  "dep_las_per_type":{
368
  "advmod":{
369
- "p":0.6955345061,
370
- "r":0.7259887006,
371
- "f":0.7104353836
372
  },
373
  "root":{
374
- "p":0.824686941,
375
- "r":0.8173758865,
376
- "f":0.821015138
377
  },
378
  "nsubj":{
379
- "p":0.8361884368,
380
- "r":0.8238396624,
381
- "f":0.829968119
382
  },
383
  "case":{
384
- "p":0.9003984064,
385
- "r":0.8915187377,
386
- "f":0.8959365709
387
  },
388
  "obl":{
389
- "p":0.7221297837,
390
- "r":0.6739130435,
391
- "f":0.697188755
392
  },
393
  "cc":{
394
- "p":0.7630057803,
395
- "r":0.7674418605,
396
- "f":0.7652173913
397
  },
398
  "conj":{
399
- "p":0.6106442577,
400
- "r":0.5813333333,
401
- "f":0.5956284153
402
  },
403
  "obj":{
404
- "p":0.7893772894,
405
- "r":0.8368932039,
406
- "f":0.8124410933
407
  },
408
  "aux":{
409
- "p":0.8764705882,
410
- "r":0.8688046647,
411
- "f":0.8726207906
412
  },
413
  "acl:relcl":{
414
- "p":0.6300578035,
415
- "r":0.5891891892,
416
- "f":0.6089385475
417
  },
418
  "advmod:lmod":{
419
- "p":0.7272727273,
420
- "r":0.7164179104,
421
- "f":0.7218045113
422
  },
423
  "det":{
424
- "p":0.9140495868,
425
- "r":0.9110378913,
426
- "f":0.9125412541
427
  },
428
  "amod":{
429
- "p":0.8080645161,
430
- "r":0.8549488055,
431
- "f":0.8308457711
432
  },
433
  "nmod:poss":{
434
- "p":0.7373737374,
435
- "r":0.7227722772,
436
- "f":0.73
437
  },
438
  "ccomp":{
439
- "p":0.7068965517,
440
- "r":0.6612903226,
441
- "f":0.6833333333
442
  },
443
  "nummod":{
444
- "p":0.8360655738,
445
- "r":0.85,
446
- "f":0.8429752066
447
  },
448
  "flat":{
449
- "p":0.7844311377,
450
- "r":0.8675496689,
451
- "f":0.8238993711
452
  },
453
  "compound:prt":{
454
- "p":0.5,
455
- "r":0.2926829268,
456
- "f":0.3692307692
457
  },
458
  "advcl":{
459
- "p":0.6545454545,
460
- "r":0.6206896552,
461
- "f":0.6371681416
462
  },
463
  "mark":{
464
- "p":0.8781512605,
465
- "r":0.8583162218,
466
- "f":0.8681204569
467
  },
468
  "cop":{
469
- "p":0.8121546961,
470
- "r":0.84,
471
- "f":0.8258426966
472
  },
473
  "dep":{
474
- "p":0.145631068,
475
- "r":0.2830188679,
476
- "f":0.1923076923
477
  },
478
  "nmod":{
479
- "p":0.6549707602,
480
- "r":0.65625,
481
- "f":0.6556097561
482
  },
483
  "iobj":{
484
- "p":0.8125,
485
- "r":0.5909090909,
486
- "f":0.6842105263
487
  },
488
  "xcomp":{
489
- "p":0.4772727273,
490
- "r":0.3559322034,
491
- "f":0.4077669903
492
- },
493
- "appos":{
494
- "p":0.5384615385,
495
- "r":0.4242424242,
496
- "f":0.4745762712
497
  },
498
  "list":{
499
- "p":0.5,
500
- "r":0.3333333333,
501
- "f":0.4
502
  },
503
  "vocative":{
504
  "p":0.0,
@@ -506,59 +502,64 @@
506
  "f":0.0
507
  },
508
  "fixed":{
509
- "p":0.8717948718,
510
- "r":0.8292682927,
511
- "f":0.85
512
- },
513
- "obl:lmod":{
514
- "p":0.0,
515
- "r":0.0,
516
- "f":0.0
517
  },
518
  "expl":{
519
- "p":0.8529411765,
520
- "r":0.8529411765,
521
- "f":0.8529411765
 
 
 
 
 
522
  },
523
  "obl:tmod":{
524
- "p":0.6363636364,
525
- "r":0.3888888889,
526
- "f":0.4827586207
527
  },
528
  "discourse":{
529
  "p":0.0,
530
  "r":0.0,
531
  "f":0.0
 
 
 
 
 
532
  }
533
  },
534
- "lemma_acc":0.9516707022,
535
- "tag_acc":0.9633898305,
536
- "ents_p":0.8183716075,
537
- "ents_r":0.8166666667,
538
- "ents_f":0.8175182482,
539
  "ents_per_type":{
540
  "PER":{
541
- "p":0.8993710692,
542
- "r":0.8614457831,
543
- "f":0.88
544
  },
545
  "ORG":{
546
- "p":0.7303370787,
547
- "r":0.7222222222,
548
- "f":0.7262569832
549
  },
550
  "MISC":{
551
- "p":0.7288135593,
552
- "r":0.7610619469,
553
- "f":0.7445887446
554
  },
555
  "LOC":{
556
- "p":0.8672566372,
557
- "r":0.8828828829,
558
- "f":0.875
559
  }
560
  },
561
- "speed":10791.2692595094
562
  },
563
  "sources":[
564
  {
 
1
  {
2
  "lang":"da",
3
  "name":"core_news_lg",
4
+ "version":"3.4.0",
5
  "description":"Danish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, lemmatizer (trainable_lemmatizer), senter, ner, attribute_ruler.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"CC BY-SA 4.0",
10
+ "spacy_version":">=3.4.0,<3.5.0",
11
+ "spacy_git_version":"dd038b536",
12
  "vectors":{
13
  "width":300,
14
  "vectors":500000,
 
106
  "Gender=Com|Number=Sing|Number[psor]=Plur|POS=DET|Person=1|Poss=Yes|PronType=Prs|Style=Form",
107
  "Number=Plur|POS=PRON|PronType=Rcp",
108
  "Case=Gen|Degree=Cmp|POS=ADJ",
109
+ "POS=SPACE",
110
  "Case=Gen|Definite=Def|Gender=Neut|Number=Plur|POS=NOUN",
111
  "Number[psor]=Plur|POS=DET|Person=3|Poss=Yes|PronType=Prs",
112
  "POS=INTJ",
 
248
  "token_p":0.9977732598,
249
  "token_r":0.9974835463,
250
  "token_f":0.997628382,
251
+ "pos_acc":0.9641646489,
252
+ "morph_acc":0.9538014528,
253
+ "morph_micro_p":0.9705792683,
254
+ "morph_micro_r":0.9641613245,
255
+ "morph_micro_f":0.9673596516,
256
  "morph_per_feat":{
257
  "Mood":{
258
+ "p":0.9789473684,
259
+ "r":0.97521449,
260
+ "f":0.9770773639
261
  },
262
  "Tense":{
263
+ "p":0.9743396226,
264
+ "r":0.9721385542,
265
+ "f":0.973237844
266
  },
267
  "VerbForm":{
268
+ "p":0.9649014778,
269
+ "r":0.958996328,
270
+ "f":0.9619398404
271
  },
272
  "Voice":{
273
+ "p":0.9789631856,
274
+ "r":0.9738415546,
275
+ "f":0.9763956538
276
  },
277
  "Definite":{
278
+ "p":0.9642147117,
279
+ "r":0.9581193204,
280
+ "f":0.9611573524
281
  },
282
  "Gender":{
283
+ "p":0.9558823529,
284
+ "r":0.9504818877,
285
+ "f":0.9531744709
286
  },
287
  "Number":{
288
+ "p":0.96478318,
289
+ "r":0.9574856547,
290
+ "f":0.9611205655
291
  },
292
  "AdpType":{
293
+ "p":1.0,
294
  "r":0.9920424403,
295
+ "f":0.9960053262
296
  },
297
  "PartType":{
298
+ "p":1.0,
299
  "r":1.0,
300
+ "f":1.0
301
  },
302
  "Case":{
303
+ "p":0.9791666667,
304
+ "r":0.9652448657,
305
+ "f":0.9721559268
306
  },
307
  "Person":{
308
+ "p":0.9857651246,
309
+ "r":0.9840142096,
310
+ "f":0.9848888889
311
  },
312
  "PronType":{
313
+ "p":0.9868095631,
314
+ "r":0.984375,
315
+ "f":0.9855907781
316
  },
317
  "NumType":{
318
+ "p":0.972972973,
319
+ "r":0.9536423841,
320
+ "f":0.9632107023
321
  },
322
  "Degree":{
323
+ "p":0.9524969549,
324
+ "r":0.9421686747,
325
+ "f":0.9473046638
326
  },
327
  "Reflex":{
328
  "p":1.0,
 
330
  "f":1.0
331
  },
332
  "Number[psor]":{
333
+ "p":0.988372093,
334
+ "r":0.988372093,
335
+ "f":0.988372093
336
  },
337
  "Poss":{
338
+ "p":1.0,
339
+ "r":0.9886363636,
340
+ "f":0.9942857143
341
  },
342
  "Foreign":{
343
+ "p":1.0,
344
+ "r":0.5,
345
+ "f":0.6666666667
346
  },
347
  "Abbr":{
348
  "p":0.0,
 
363
  "sents_p":0.9103942652,
364
  "sents_r":0.9007092199,
365
  "sents_f":0.9055258467,
366
+ "dep_uas":0.8220111732,
367
+ "dep_las":0.7817440366,
368
  "dep_las_per_type":{
369
  "advmod":{
370
+ "p":0.6882758621,
371
+ "r":0.7048022599,
372
+ "f":0.6964410328
373
  },
374
  "root":{
375
+ "p":0.8369175627,
376
+ "r":0.8280141844,
377
+ "f":0.8324420677
378
  },
379
  "nsubj":{
380
+ "p":0.8381256656,
381
+ "r":0.8301687764,
382
+ "f":0.8341282459
383
  },
384
  "case":{
385
+ "p":0.8997020854,
386
+ "r":0.8934911243,
387
+ "f":0.8965858486
388
  },
389
  "obl":{
390
+ "p":0.7044728435,
391
+ "r":0.6847826087,
392
+ "f":0.694488189
393
  },
394
  "cc":{
395
+ "p":0.7735294118,
396
+ "r":0.7645348837,
397
+ "f":0.769005848
398
  },
399
  "conj":{
400
+ "p":0.6239782016,
401
+ "r":0.6106666667,
402
+ "f":0.6172506739
403
  },
404
  "obj":{
405
+ "p":0.7985347985,
406
+ "r":0.8466019417,
407
+ "f":0.821866164
408
  },
409
  "aux":{
410
+ "p":0.8735294118,
411
+ "r":0.8658892128,
412
+ "f":0.8696925329
413
  },
414
  "acl:relcl":{
415
+ "p":0.6271186441,
416
+ "r":0.6,
417
+ "f":0.6132596685
418
  },
419
  "advmod:lmod":{
420
+ "p":0.7014925373,
421
+ "r":0.7014925373,
422
+ "f":0.7014925373
423
  },
424
  "det":{
425
+ "p":0.9129720854,
426
+ "r":0.9159802306,
427
+ "f":0.9144736842
428
  },
429
  "amod":{
430
+ "p":0.8073089701,
431
+ "r":0.8293515358,
432
+ "f":0.8181818182
433
  },
434
  "nmod:poss":{
435
+ "p":0.7741935484,
436
+ "r":0.7128712871,
437
+ "f":0.7422680412
438
  },
439
  "ccomp":{
440
+ "p":0.6865671642,
441
+ "r":0.7419354839,
442
+ "f":0.7131782946
443
  },
444
  "nummod":{
445
+ "p":0.8536585366,
446
+ "r":0.875,
447
+ "f":0.8641975309
448
  },
449
  "flat":{
450
+ "p":0.7784431138,
451
+ "r":0.8609271523,
452
+ "f":0.8176100629
453
  },
454
  "compound:prt":{
455
+ "p":0.4411764706,
456
+ "r":0.3658536585,
457
+ "f":0.4
458
  },
459
  "advcl":{
460
+ "p":0.6120689655,
461
+ "r":0.6120689655,
462
+ "f":0.6120689655
463
  },
464
  "mark":{
465
+ "p":0.889596603,
466
+ "r":0.8603696099,
467
+ "f":0.8747390397
468
  },
469
  "cop":{
470
+ "p":0.8021978022,
471
+ "r":0.8342857143,
472
+ "f":0.8179271709
473
  },
474
  "dep":{
475
+ "p":0.1304347826,
476
+ "r":0.2264150943,
477
+ "f":0.1655172414
478
  },
479
  "nmod":{
480
+ "p":0.6620825147,
481
+ "r":0.658203125,
482
+ "f":0.6601371205
483
  },
484
  "iobj":{
485
+ "p":0.8333333333,
486
+ "r":0.4545454545,
487
+ "f":0.5882352941
488
  },
489
  "xcomp":{
490
+ "p":0.5365853659,
491
+ "r":0.3728813559,
492
+ "f":0.44
 
 
 
 
 
493
  },
494
  "list":{
495
+ "p":0.3333333333,
496
+ "r":0.2222222222,
497
+ "f":0.2666666667
498
  },
499
  "vocative":{
500
  "p":0.0,
 
502
  "f":0.0
503
  },
504
  "fixed":{
505
+ "p":0.8461538462,
506
+ "r":0.8048780488,
507
+ "f":0.825
 
 
 
 
 
508
  },
509
  "expl":{
510
+ "p":0.8484848485,
511
+ "r":0.8235294118,
512
+ "f":0.8358208955
513
+ },
514
+ "appos":{
515
+ "p":0.5862068966,
516
+ "r":0.5151515152,
517
+ "f":0.5483870968
518
  },
519
  "obl:tmod":{
520
+ "p":0.8333333333,
521
+ "r":0.2777777778,
522
+ "f":0.4166666667
523
  },
524
  "discourse":{
525
  "p":0.0,
526
  "r":0.0,
527
  "f":0.0
528
+ },
529
+ "obl:lmod":{
530
+ "p":0.0,
531
+ "r":0.0,
532
+ "f":0.0
533
  }
534
  },
535
+ "lemma_acc":0.9518644068,
536
+ "tag_acc":0.9641646489,
537
+ "ents_p":0.8161157025,
538
+ "ents_r":0.8229166667,
539
+ "ents_f":0.8195020747,
540
  "ents_per_type":{
541
  "PER":{
542
+ "p":0.9230769231,
543
+ "r":0.8674698795,
544
+ "f":0.8944099379
545
  },
546
  "ORG":{
547
+ "p":0.7528089888,
548
+ "r":0.7444444444,
549
+ "f":0.748603352
550
  },
551
  "MISC":{
552
+ "p":0.6910569106,
553
+ "r":0.7522123894,
554
+ "f":0.7203389831
555
  },
556
  "LOC":{
557
+ "p":0.8534482759,
558
+ "r":0.8918918919,
559
+ "f":0.872246696
560
  }
561
  },
562
+ "speed":12175.9946774514
563
  },
564
  "sources":[
565
  {
morphologizer/cfg CHANGED
@@ -87,6 +87,7 @@
87
  "Gender=Com|Number=Sing|Number[psor]=Plur|POS=DET|Person=1|Poss=Yes|PronType=Prs|Style=Form":"Gender=Com|Number=Sing|Number[psor]=Plur|Person=1|Poss=Yes|PronType=Prs|Style=Form",
88
  "Number=Plur|POS=PRON|PronType=Rcp":"Number=Plur|PronType=Rcp",
89
  "Case=Gen|Degree=Cmp|POS=ADJ":"Case=Gen|Degree=Cmp",
 
90
  "Case=Gen|Definite=Def|Gender=Neut|Number=Plur|POS=NOUN":"Case=Gen|Definite=Def|Gender=Neut|Number=Plur",
91
  "Number[psor]=Plur|POS=DET|Person=3|Poss=Yes|PronType=Prs":"Number[psor]=Plur|Person=3|Poss=Yes|PronType=Prs",
92
  "POS=INTJ":"",
@@ -246,6 +247,7 @@
246
  "Gender=Com|Number=Sing|Number[psor]=Plur|POS=DET|Person=1|Poss=Yes|PronType=Prs|Style=Form":90,
247
  "Number=Plur|POS=PRON|PronType=Rcp":95,
248
  "Case=Gen|Degree=Cmp|POS=ADJ":84,
 
249
  "Case=Gen|Definite=Def|Gender=Neut|Number=Plur|POS=NOUN":92,
250
  "Number[psor]=Plur|POS=DET|Person=3|Poss=Yes|PronType=Prs":90,
251
  "POS=INTJ":91,
 
87
  "Gender=Com|Number=Sing|Number[psor]=Plur|POS=DET|Person=1|Poss=Yes|PronType=Prs|Style=Form":"Gender=Com|Number=Sing|Number[psor]=Plur|Person=1|Poss=Yes|PronType=Prs|Style=Form",
88
  "Number=Plur|POS=PRON|PronType=Rcp":"Number=Plur|PronType=Rcp",
89
  "Case=Gen|Degree=Cmp|POS=ADJ":"Case=Gen|Degree=Cmp",
90
+ "POS=SPACE":"",
91
  "Case=Gen|Definite=Def|Gender=Neut|Number=Plur|POS=NOUN":"Case=Gen|Definite=Def|Gender=Neut|Number=Plur",
92
  "Number[psor]=Plur|POS=DET|Person=3|Poss=Yes|PronType=Prs":"Number[psor]=Plur|Person=3|Poss=Yes|PronType=Prs",
93
  "POS=INTJ":"",
 
247
  "Gender=Com|Number=Sing|Number[psor]=Plur|POS=DET|Person=1|Poss=Yes|PronType=Prs|Style=Form":90,
248
  "Number=Plur|POS=PRON|PronType=Rcp":95,
249
  "Case=Gen|Degree=Cmp|POS=ADJ":84,
250
+ "POS=SPACE":103,
251
  "Case=Gen|Definite=Def|Gender=Neut|Number=Plur|POS=NOUN":92,
252
  "Number[psor]=Plur|POS=DET|Person=3|Poss=Yes|PronType=Prs":90,
253
  "POS=INTJ":91,
morphologizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9a904d06964b6afa205f053f74bc3b869bab70872d9265d38fadd867450df26
3
- size 61351
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1883862e52aaf5c8afafe1cea486f9e330d9ad501ae6de50be9a5890c45507be
3
+ size 61739
ner/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d60d6db1813b3f2d8de3dea75ed89b12bf168bb820f9bda6630e5a51d4d1ecb
3
  size 6496592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bae7b8d1ea36a33a0b9bf5eba7943dc15bff312d18d5cca83978f5fcaf2eca12
3
  size 6496592
ner/moves CHANGED
@@ -1 +1 @@
1
- ��moves��{"0":{},"1":{"PER":2146,"MISC":1273,"ORG":1267,"LOC":1144},"2":{"PER":2146,"MISC":1273,"ORG":1267,"LOC":1144},"3":{"PER":2146,"MISC":1273,"ORG":1267,"LOC":1144},"4":{"PER":2146,"MISC":1273,"ORG":1267,"LOC":1144,"":1},"5":{"":1}}�cfg��neg_key�
 
1
+ ��moves��{"0":{},"1":{"PER":2147,"MISC":1275,"ORG":1268,"LOC":1145},"2":{"PER":2147,"MISC":1275,"ORG":1268,"LOC":1145},"3":{"PER":2147,"MISC":1275,"ORG":1268,"LOC":1145},"4":{"PER":2147,"MISC":1275,"ORG":1268,"LOC":1145,"":1},"5":{"":1}}�cfg��neg_key�
parser/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c112c2427b1cfb0608eb1ef39d0206558de657c031eca80773d43e578f7517f8
3
  size 308728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b771fefca92f3487eb2f030cfd74df06ebf5f2a1d83418942285089ce82e8180
3
  size 308728
parser/moves CHANGED
@@ -1 +1 @@
1
- ��moves�D{"0":{"":41615},"1":{"":34382},"2":{"case":7526,"nsubj":6005,"det":4341,"amod":3967,"advmod":3662,"mark":3530,"aux":2436,"cc":2264,"punct":2187,"cop":1330,"obl":894,"nummod":834,"nmod:poss":656,"nmod":463,"expl":291,"ccomp":203,"obj":195,"xcomp":122,"case||nmod":73,"obl:tmod":53,"dep":48,"acl:relcl":43},"3":{"punct":8693,"obl":3951,"obj":3760,"nmod":3569,"conj":2747,"advmod":2087,"flat":1302,"nsubj":1169,"acl:relcl":1132,"advcl":809,"amod":622,"advmod:lmod":423,"fixed":390,"dep":322,"xcomp":272,"appos":268,"compound:prt":261,"ccomp":252,"acl:relcl||nsubj":237,"case":202,"nummod":168,"list":159,"nmod:poss":156,"punct||conj":151,"cc":135,"mark":133,"iobj":107,"expl":77,"cop":69,"nmod||case":60,"aux":48,"obl:tmod":45,"obl:lmod":44,"cc||case":43,"advcl||advmod":43,"cc||conj":40,"case||obl":38,"punct||case":33},"4":{"ROOT":4383}}�cfg��neg_key�
 
1
+ ��moves�D{"0":{"":41618},"1":{"":34694},"2":{"case":7526,"nsubj":6005,"det":4341,"amod":3967,"advmod":3662,"mark":3530,"aux":2436,"cc":2264,"punct":2187,"cop":1330,"obl":894,"nummod":834,"nmod:poss":656,"nmod":463,"expl":291,"ccomp":203,"obj":195,"xcomp":122,"case||nmod":73,"obl:tmod":53,"dep":51,"acl:relcl":43},"3":{"punct":8693,"obl":3951,"obj":3760,"nmod":3569,"conj":2747,"advmod":2087,"flat":1302,"nsubj":1169,"acl:relcl":1132,"advcl":809,"dep":634,"amod":622,"advmod:lmod":423,"fixed":390,"xcomp":272,"appos":268,"compound:prt":261,"ccomp":252,"acl:relcl||nsubj":237,"case":202,"nummod":168,"list":159,"nmod:poss":156,"punct||conj":151,"cc":135,"mark":133,"iobj":107,"expl":77,"cop":69,"nmod||case":60,"aux":48,"obl:tmod":45,"obl:lmod":44,"cc||case":43,"advcl||advmod":43,"cc||conj":40,"case||obl":38,"punct||case":33},"4":{"ROOT":4383}}�cfg��neg_key�
senter/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5afa93a8f788243e6c02d5ab57762e55511fbfa00f89ee3c21bd75cea7ae6bc
3
  size 219953
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abbf6466e28bf155126cd68c6be2543ec6789a3fd20efbeb781e2138b4921972
3
  size 219953
tok2vec/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:afa9aae853e4d60a66837dd127015d27d43c8f772b22c8c7b172238e5dfaa846
3
  size 6365604
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed33c877ffd457539da81a8853be55873ff2b2dd8d76714183c9fbe87250550f
3
  size 6365604
vocab/strings.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:528d1a6bb62dc4d608b0ea1be75d557f41cdd76867460448bbbc174d34ae193a
3
- size 10081139
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d087b63907f4906a9582161d47cb1148e5cd6ba59a630b1d17af613f516adfd2
3
+ size 10086471