adrianeboyd commited on
Commit
26f494b
1 Parent(s): 113f397

Update spaCy pipeline

Browse files
.gitattributes CHANGED
@@ -19,3 +19,4 @@
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
+ vocab/key2row filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -14,62 +14,62 @@ model-index:
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
- value: 0.8236700538
18
  - name: NER Recall
19
  type: recall
20
- value: 0.8163507109
21
  - name: NER F Score
22
  type: f_score
23
- value: 0.8199940494
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
- value: 0.9737451099
31
  - task:
32
  name: POS
33
  type: token-classification
34
  metrics:
35
  - name: POS (UPOS) Accuracy
36
  type: accuracy
37
- value: 0.9737451099
38
  - task:
39
  name: MORPH
40
  type: token-classification
41
  metrics:
42
  - name: Morph (UFeats) Accuracy
43
  type: accuracy
44
- value: 0.9592638003
45
  - task:
46
  name: LEMMA
47
  type: token-classification
48
  metrics:
49
  - name: Lemma Accuracy
50
  type: accuracy
51
- value: 0.9709106936
52
  - task:
53
  name: UNLABELED_DEPENDENCIES
54
  type: token-classification
55
  metrics:
56
  - name: Unlabeled Attachment Score (UAS)
57
  type: f_score
58
- value: 0.8943254651
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
- value: 0.8639894956
66
  - task:
67
  name: SENTS
68
  type: token-classification
69
  metrics:
70
  - name: Sentences F-Score
71
  type: f_score
72
- value: 0.9455754051
73
  ---
74
  ### Details: https://spacy.io/models/nb#nb_core_news_md
75
 
@@ -78,8 +78,8 @@ Norwegian (Bokmål) pipeline optimized for CPU. Components: tok2vec, morphologiz
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `nb_core_news_md` |
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, 20000 unique vectors (300 dimensions) |
@@ -91,11 +91,11 @@ Norwegian (Bokmål) pipeline optimized for CPU. Components: tok2vec, morphologiz
91
 
92
  <details>
93
 
94
- <summary>View label scheme (248 labels for 3 components)</summary>
95
 
96
  | Component | Labels |
97
  | --- | --- |
98
- | **`morphologizer`** | `Definite=Ind\|Gender=Neut\|Number=Sing\|POS=NOUN`, `POS=CCONJ`, `Definite=Ind\|Gender=Masc\|Number=Sing\|POS=NOUN`, `POS=SCONJ`, `Definite=Def\|Gender=Masc\|Number=Sing\|POS=NOUN`, `Definite=Ind\|Gender=Neut\|Number=Plur\|POS=NOUN`, `POS=PUNCT`, `Mood=Ind\|POS=VERB\|Tense=Past\|VerbForm=Fin`, `POS=ADP`, `Gender=Masc\|Number=Sing\|POS=DET\|PronType=Dem`, `Definite=Def\|Degree=Pos\|Number=Sing\|POS=ADJ`, `POS=PROPN`, `POS=X`, `Mood=Ind\|POS=VERB\|Tense=Pres\|VerbForm=Fin`, `Definite=Def\|Gender=Neut\|Number=Sing\|POS=NOUN`, `POS=PRON\|PronType=Rel`, `Mood=Ind\|POS=AUX\|Tense=Pres\|VerbForm=Fin`, `Definite=Ind\|Gender=Neut\|Number=Sing\|POS=ADJ\|VerbForm=Part`, `Definite=Ind\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Definite=Ind\|Gender=Fem\|Number=Sing\|POS=NOUN`, `Number=Plur\|POS=ADJ\|VerbForm=Part`, `Definite=Ind\|Gender=Fem\|Number=Plur\|POS=NOUN`, `POS=ADV`, `Gender=Neut\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Definite=Ind\|Number=Sing\|POS=ADJ\|VerbForm=Part`, `POS=VERB\|VerbForm=Part`, `Definite=Ind\|Gender=Masc\|Number=Plur\|POS=NOUN`, `Definite=Ind\|Degree=Pos\|Gender=Neut\|Number=Sing\|POS=ADJ`, `Degree=Pos\|Number=Plur\|POS=ADJ`, `NumType=Card\|Number=Plur\|POS=NUM`, `Definite=Def\|Gender=Masc\|Number=Plur\|POS=NOUN`, `Case=Acc\|POS=PRON\|PronType=Prs\|Reflex=Yes`, `Case=Gen\|Definite=Ind\|Gender=Neut\|Number=Sing\|POS=NOUN`, `POS=PART`, `POS=VERB\|VerbForm=Inf`, `Case=Nom\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Mood=Ind\|POS=AUX\|Tense=Past\|VerbForm=Fin`, `Gender=Fem\|POS=PROPN`, `POS=NOUN`, `Gender=Masc\|POS=PROPN`, `Gender=Neut\|Number=Sing\|POS=DET\|PronType=Dem`, `Gender=Masc\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Gen\|Definite=Def\|Gender=Masc\|Number=Sing\|POS=NOUN`, `Abbr=Yes\|POS=PROPN`, `POS=PART\|Polarity=Neg`, `Number=Plur\|POS=PRON\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Definite=Ind\|Gender=Neut\|Number=Plur\|POS=NOUN`, `Case=Gen\|POS=PROPN`, `Gender=Fem\|Number=Sing\|POS=DET\|PronType=Dem`, `Gender=Masc\|Number=Sing\|POS=PRON\|Poss=Yes\|PronType=Prs`, `Definite=Def\|Degree=Sup\|POS=ADJ`, `Case=Gen\|Gender=Fem\|POS=PROPN`, `Number=Plur\|POS=DET\|PronType=Dem`, `Case=Gen\|Definite=Def\|Gender=Neut\|Number=Sing\|POS=NOUN`, `Definite=Ind\|Degree=Sup\|POS=ADJ`, `Definite=Def\|Gender=Fem\|Number=Plur\|POS=NOUN`, `Gender=Neut\|POS=PROPN`, `Number=Plur\|POS=DET\|PronType=Int`, `Definite=Def\|Gender=Neut\|Number=Plur\|POS=NOUN`, `Definite=Def\|POS=DET\|PronType=Dem`, `Gender=Neut\|Number=Sing\|POS=DET\|PronType=Art`, `Mood=Ind\|POS=VERB\|Tense=Pres\|VerbForm=Fin\|Voice=Pass`, `Abbr=Yes\|Case=Gen\|POS=PROPN`, `Animacy=Hum\|Case=Nom\|Gender=Masc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Degree=Cmp\|POS=ADJ`, `POS=ADJ\|VerbForm=Part`, `Gender=Neut\|Number=Sing\|POS=PRON\|Poss=Yes\|PronType=Prs`, `Abbr=Yes\|POS=ADP`, `Definite=Ind\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Prs`, `Case=Gen\|Definite=Def\|Gender=Neut\|Number=Plur\|POS=NOUN`, `POS=AUX\|VerbForm=Part`, `POS=PRON\|PronType=Int`, `Gender=Fem\|Number=Sing\|POS=PRON\|Poss=Yes\|PronType=Prs`, `Number=Plur\|POS=PRON\|Person=3\|PronType=Ind,Prs`, `Number=Plur\|POS=DET\|PronType=Ind`, `Degree=Pos\|POS=ADJ`, `Animacy=Hum\|Case=Nom\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `POS=VERB\|VerbForm=Inf\|Voice=Pass`, `Definite=Ind\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Dem`, `Gender=Neut\|Number=Sing\|POS=DET\|PronType=Ind`, `Animacy=Hum\|Case=Acc\|Gender=Masc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Animacy=Hum\|Case=Nom\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Number=Plur\|POS=DET\|Polarity=Neg\|PronType=Neg`, `NumType=Card\|POS=NUM`, `Gender=Masc\|Number=Sing\|POS=DET\|PronType=Ind`, `POS=DET\|PronType=Prs`, `Gender=Fem\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Gen\|Gender=Neut\|POS=PROPN`, `Gender=Masc\|Number=Sing\|POS=DET\|Polarity=Neg\|PronType=Neg`, `Definite=Def\|Number=Sing\|POS=ADJ\|VerbForm=Part`, `Gender=Fem,Masc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `POS=AUX\|VerbForm=Inf`, `Case=Acc\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Gen\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Number=Plur\|POS=DET\|PronType=Tot`, `Case=Gen\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Dem`, `Number=Plur\|POS=DET\|PronType=Prs`, `POS=SYM`, `Gender=Neut\|NumType=Card\|Number=Sing\|POS=NUM`, `Animacy=Hum\|Case=Nom\|Number=Sing\|POS=PRON\|PronType=Prs`, `Definite=Ind\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Prs`, `Case=Gen\|Definite=Ind\|Gender=Masc\|Number=Sing\|POS=NOUN`, `Abbr=Yes\|POS=ADV`, `Definite=Ind\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Dem`, `Gender=Masc\|Number=Sing\|POS=DET\|PronType=Tot`, `Definite=Def\|POS=DET\|PronType=Prs`, `Animacy=Hum\|Case=Nom\|Gender=Fem\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Gender=Neut\|POS=NOUN`, `Gender=Neut\|Number=Sing\|POS=DET\|PronType=Int`, `Definite=Def\|NumType=Card\|POS=NUM`, `Mood=Imp\|POS=VERB\|VerbForm=Fin`, `Definite=Ind\|Number=Plur\|POS=NOUN`, `Gender=Neut\|Number=Sing\|POS=DET\|PronType=Tot`, `Gender=Fem\|Number=Sing\|POS=DET\|PronType=Tot`, `Animacy=Hum\|Case=Acc\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `Gender=Fem,Masc\|Number=Sing\|POS=PRON\|Person=3\|Polarity=Neg\|PronType=Neg,Prs`, `Number=Plur\|POS=PRON\|Person=3\|Polarity=Neg\|PronType=Neg,Prs`, `Definite=Def\|NumType=Card\|Number=Sing\|POS=NUM`, `Gender=Masc\|NumType=Card\|Number=Sing\|POS=NUM`, `Definite=Ind\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Dem`, `Case=Gen\|Definite=Def\|Gender=Fem\|Number=Plur\|POS=NOUN`, `Case=Gen\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Dem`, `Animacy=Hum\|Number=Sing\|POS=PRON\|PronType=Art,Prs`, `Mood=Imp\|POS=AUX\|VerbForm=Fin`, `Number=Plur\|POS=PRON\|Person=3\|PronType=Prs,Tot`, `Number=Plur\|POS=ADJ`, `Gender=Masc\|POS=NOUN`, `Abbr=Yes\|POS=NOUN`, `Case=Gen\|Definite=Ind\|Gender=Masc\|Number=Plur\|POS=NOUN`, `Gender=Neut\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind,Prs`, `POS=INTJ`, `Animacy=Hum\|Case=Nom\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Animacy=Hum\|Case=Acc\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Gen\|Definite=Def\|Gender=Masc\|Number=Plur\|POS=NOUN`, `POS=ADJ`, `Animacy=Hum\|Case=Acc\|Gender=Fem\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Animacy=Hum\|Case=Acc\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Definite=Def\|Gender=Fem\|Number=Sing\|POS=NOUN`, `Number=Sing\|POS=PRON\|Polarity=Neg\|PronType=Neg`, `Case=Gen\|POS=NOUN`, `Definite=Ind\|Number=Sing\|POS=ADJ`, `Case=Gen\|Gender=Masc\|POS=PROPN`, `Animacy=Hum\|Number=Plur\|POS=PRON\|PronType=Rcp`, `Case=Gen\|Definite=Ind\|Gender=Fem\|Number=Sing\|POS=NOUN`, `Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Gender=Fem,Masc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind,Prs`, `Definite=Ind\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Prs`, `Case=Gen\|Definite=Def\|Gender=Fem\|Number=Sing\|POS=NOUN`, `Gender=Fem\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Gen\|Definite=Def\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Gender=Masc\|Number=Sing\|POS=DET\|PronType=Int`, `NumType=Card\|Number=Sing\|POS=NUM`, `Animacy=Hum\|Case=Acc\|Number=Plur\|POS=PRON\|Person=2\|PronType=Prs`, `Animacy=Hum\|Case=Nom\|Number=Plur\|POS=PRON\|Person=2\|PronType=Prs`, `Case=Gen\|Definite=Ind\|Degree=Pos\|Gender=Neut\|Number=Sing\|POS=ADJ`, `Degree=Sup\|POS=ADJ`, `Animacy=Hum\|POS=PRON\|PronType=Int`, `POS=DET\|PronType=Ind`, `Definite=Def\|Number=Sing\|POS=DET\|PronType=Dem`, `Gender=Fem\|POS=NOUN`, `Case=Gen\|Number=Plur\|POS=DET\|PronType=Dem`, `Gender=Fem,Masc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs,Tot`, `Case=Gen\|Definite=Ind\|Gender=Fem\|Number=Plur\|POS=NOUN`, `Gender=Neut\|Number=Sing\|POS=DET\|Polarity=Neg\|PronType=Neg`, `Number=Plur\|POS=NOUN`, `POS=PRON\|PronType=Prs`, `Case=Gen\|Definite=Ind\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Definite=Ind\|Number=Sing\|POS=VERB\|VerbForm=Part`, `Case=Gen\|Definite=Def\|Number=Sing\|POS=ADJ\|VerbForm=Part`, `Mood=Ind\|POS=VERB\|Tense=Past\|VerbForm=Fin\|Voice=Pass`, `Gender=Neut\|Number=Sing\|POS=DET\|PronType=Dem,Ind`, `Animacy=Hum\|POS=PRON\|Poss=Yes\|PronType=Int`, `Abbr=Yes\|POS=ADJ`, `Case=Gen\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Art`, `Abbr=Yes\|Definite=Def,Ind\|Gender=Masc\|Number=Sing\|POS=NOUN`, `Case=Gen\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Dem`, `Number=Plur\|POS=PRON\|Poss=Yes\|PronType=Rcp`, `Definite=Ind\|Degree=Pos\|POS=ADJ`, `Number=Plur\|POS=DET\|PronType=Art`, `Case=Gen\|NumType=Card\|Number=Plur\|POS=NUM`, `Abbr=Yes\|Definite=Def,Ind\|Gender=Neut\|Number=Plur,Sing\|POS=NOUN`, `Case=Gen\|Number=Plur\|POS=DET\|PronType=Tot`, `Abbr=Yes\|Definite=Def,Ind\|Gender=Masc\|Number=Plur,Sing\|POS=NOUN`, `Gender=Fem\|Number=Sing\|POS=DET\|PronType=Int`, `Definite=Ind\|Gender=Neut\|Number=Sing\|POS=ADJ`, `Case=Gen\|Definite=Ind\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Dem`, `Gender=Fem\|Number=Sing\|POS=DET\|PronType=Prs`, `Animacy=Hum\|Case=Gen,Nom\|Number=Sing\|POS=PRON\|PronType=Art,Prs`, `Definite=Def\|Degree=Pos\|Gender=Masc\|Number=Sing\|POS=ADJ`, `Animacy=Hum\|Case=Gen\|Number=Sing\|POS=PRON\|PronType=Art,Prs`, `Gender=Fem\|NumType=Card\|Number=Sing\|POS=NUM`, `Definite=Ind\|Gender=Masc\|POS=NOUN`, `Definite=Def\|Number=Plur\|POS=NOUN`, `Number=Sing\|POS=ADJ\|VerbForm=Part`, `Definite=Ind\|Gender=Masc\|Number=Sing\|POS=ADJ\|VerbForm=Part`, `Abbr=Yes\|Gender=Masc\|POS=NOUN`, `Abbr=Yes\|Case=Gen\|POS=NOUN`, `Abbr=Yes\|Mood=Ind\|POS=VERB\|Tense=Pres\|VerbForm=Fin`, `Abbr=Yes\|Degree=Pos\|POS=ADJ`, `Case=Gen\|Gender=Fem\|POS=NOUN`, `Case=Gen\|Degree=Cmp\|POS=ADJ`, `Definite=Ind\|Degree=Pos\|Gender=Masc\|Number=Sing\|POS=ADJ`, `Gender=Masc\|Number=Sing\|POS=NOUN` |
99
  | **`parser`** | `ROOT`, `acl`, `acl:cleft`, `acl:relcl`, `advcl`, `advmod`, `amod`, `appos`, `aux`, `aux:pass`, `case`, `cc`, `ccomp`, `compound`, `compound:prt`, `conj`, `cop`, `csubj`, `dep`, `det`, `discourse`, `expl`, `flat:foreign`, `flat:name`, `iobj`, `mark`, `nmod`, `nsubj`, `nsubj:pass`, `nummod`, `obj`, `obl`, `orphan`, `parataxis`, `punct`, `xcomp` |
100
  | **`ner`** | `DRV`, `EVT`, `GPE_LOC`, `GPE_ORG`, `LOC`, `MISC`, `ORG`, `PER`, `PROD` |
101
 
@@ -109,18 +109,18 @@ Norwegian (Bokmål) pipeline optimized for CPU. Components: tok2vec, morphologiz
109
  | `TOKEN_P` | 99.71 |
110
  | `TOKEN_R` | 99.53 |
111
  | `TOKEN_F` | 99.62 |
112
- | `POS_ACC` | 97.37 |
113
- | `MORPH_ACC` | 95.93 |
114
- | `MORPH_MICRO_P` | 97.65 |
115
- | `MORPH_MICRO_R` | 96.74 |
116
- | `MORPH_MICRO_F` | 97.19 |
117
- | `SENTS_P` | 94.64 |
118
- | `SENTS_R` | 94.48 |
119
- | `SENTS_F` | 94.56 |
120
- | `DEP_UAS` | 89.43 |
121
- | `DEP_LAS` | 86.40 |
122
- | `LEMMA_ACC` | 97.09 |
123
- | `TAG_ACC` | 97.37 |
124
- | `ENTS_P` | 82.37 |
125
- | `ENTS_R` | 81.64 |
126
- | `ENTS_F` | 82.00 |
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
+ value: 0.8307228916
18
  - name: NER Recall
19
  type: recall
20
+ value: 0.816943128
21
  - name: NER F Score
22
  type: f_score
23
+ value: 0.8237753883
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
+ value: 0.9726155711
31
  - task:
32
  name: POS
33
  type: token-classification
34
  metrics:
35
  - name: POS (UPOS) Accuracy
36
  type: accuracy
37
+ value: 0.9726155711
38
  - task:
39
  name: MORPH
40
  type: token-classification
41
  metrics:
42
  - name: Morph (UFeats) Accuracy
43
  type: accuracy
44
+ value: 0.9588648574
45
  - task:
46
  name: LEMMA
47
  type: token-classification
48
  metrics:
49
  - name: Lemma Accuracy
50
  type: accuracy
51
+ value: 0.9712137072
52
  - task:
53
  name: UNLABELED_DEPENDENCIES
54
  type: token-classification
55
  metrics:
56
  - name: Unlabeled Attachment Score (UAS)
57
  type: f_score
58
+ value: 0.8923091347
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
+ value: 0.8610490461
66
  - task:
67
  name: SENTS
68
  type: token-classification
69
  metrics:
70
  - name: Sentences F-Score
71
  type: f_score
72
+ value: 0.9326446281
73
  ---
74
  ### Details: https://spacy.io/models/nb#nb_core_news_md
75
 
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `nb_core_news_md` |
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, 20000 unique vectors (300 dimensions) |
91
 
92
  <details>
93
 
94
+ <summary>View label scheme (249 labels for 3 components)</summary>
95
 
96
  | Component | Labels |
97
  | --- | --- |
98
+ | **`morphologizer`** | `Definite=Ind\|Gender=Neut\|Number=Sing\|POS=NOUN`, `POS=CCONJ`, `Definite=Ind\|Gender=Masc\|Number=Sing\|POS=NOUN`, `POS=SCONJ`, `Definite=Def\|Gender=Masc\|Number=Sing\|POS=NOUN`, `Definite=Ind\|Gender=Neut\|Number=Plur\|POS=NOUN`, `POS=PUNCT`, `Mood=Ind\|POS=VERB\|Tense=Past\|VerbForm=Fin`, `POS=ADP`, `Gender=Masc\|Number=Sing\|POS=DET\|PronType=Dem`, `Definite=Def\|Degree=Pos\|Number=Sing\|POS=ADJ`, `POS=PROPN`, `POS=X`, `Mood=Ind\|POS=VERB\|Tense=Pres\|VerbForm=Fin`, `Definite=Def\|Gender=Neut\|Number=Sing\|POS=NOUN`, `POS=PRON\|PronType=Rel`, `Mood=Ind\|POS=AUX\|Tense=Pres\|VerbForm=Fin`, `Definite=Ind\|Gender=Neut\|Number=Sing\|POS=ADJ\|VerbForm=Part`, `Definite=Ind\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Definite=Ind\|Gender=Fem\|Number=Sing\|POS=NOUN`, `Number=Plur\|POS=ADJ\|VerbForm=Part`, `Definite=Ind\|Gender=Fem\|Number=Plur\|POS=NOUN`, `POS=ADV`, `Gender=Neut\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Definite=Ind\|Number=Sing\|POS=ADJ\|VerbForm=Part`, `POS=VERB\|VerbForm=Part`, `Definite=Ind\|Gender=Masc\|Number=Plur\|POS=NOUN`, `Definite=Ind\|Degree=Pos\|Gender=Neut\|Number=Sing\|POS=ADJ`, `Degree=Pos\|Number=Plur\|POS=ADJ`, `NumType=Card\|Number=Plur\|POS=NUM`, `Definite=Def\|Gender=Masc\|Number=Plur\|POS=NOUN`, `Case=Acc\|POS=PRON\|PronType=Prs\|Reflex=Yes`, `Case=Gen\|Definite=Ind\|Gender=Neut\|Number=Sing\|POS=NOUN`, `POS=PART`, `POS=VERB\|VerbForm=Inf`, `Case=Nom\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Mood=Ind\|POS=AUX\|Tense=Past\|VerbForm=Fin`, `Gender=Fem\|POS=PROPN`, `POS=NOUN`, `Gender=Masc\|POS=PROPN`, `Gender=Neut\|Number=Sing\|POS=DET\|PronType=Dem`, `Gender=Masc\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Gen\|Definite=Def\|Gender=Masc\|Number=Sing\|POS=NOUN`, `Abbr=Yes\|POS=PROPN`, `POS=PART\|Polarity=Neg`, `Number=Plur\|POS=PRON\|Poss=Yes\|PronType=Prs`, `Case=Gen\|Definite=Ind\|Gender=Neut\|Number=Plur\|POS=NOUN`, `Case=Gen\|POS=PROPN`, `Gender=Fem\|Number=Sing\|POS=DET\|PronType=Dem`, `Gender=Masc\|Number=Sing\|POS=PRON\|Poss=Yes\|PronType=Prs`, `Definite=Def\|Degree=Sup\|POS=ADJ`, `Case=Gen\|Gender=Fem\|POS=PROPN`, `Number=Plur\|POS=DET\|PronType=Dem`, `Case=Gen\|Definite=Def\|Gender=Neut\|Number=Sing\|POS=NOUN`, `Definite=Ind\|Degree=Sup\|POS=ADJ`, `Definite=Def\|Gender=Fem\|Number=Plur\|POS=NOUN`, `Gender=Neut\|POS=PROPN`, `Number=Plur\|POS=DET\|PronType=Int`, `Definite=Def\|Gender=Neut\|Number=Plur\|POS=NOUN`, `Definite=Def\|POS=DET\|PronType=Dem`, `Gender=Neut\|Number=Sing\|POS=DET\|PronType=Art`, `Mood=Ind\|POS=VERB\|Tense=Pres\|VerbForm=Fin\|Voice=Pass`, `Abbr=Yes\|Case=Gen\|POS=PROPN`, `Animacy=Hum\|Case=Nom\|Gender=Masc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Degree=Cmp\|POS=ADJ`, `POS=ADJ\|VerbForm=Part`, `Gender=Neut\|Number=Sing\|POS=PRON\|Poss=Yes\|PronType=Prs`, `Abbr=Yes\|POS=ADP`, `Definite=Ind\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Prs`, `Case=Gen\|Definite=Def\|Gender=Neut\|Number=Plur\|POS=NOUN`, `POS=AUX\|VerbForm=Part`, `POS=PRON\|PronType=Int`, `Gender=Fem\|Number=Sing\|POS=PRON\|Poss=Yes\|PronType=Prs`, `Number=Plur\|POS=PRON\|Person=3\|PronType=Ind,Prs`, `Number=Plur\|POS=DET\|PronType=Ind`, `Degree=Pos\|POS=ADJ`, `Animacy=Hum\|Case=Nom\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `POS=VERB\|VerbForm=Inf\|Voice=Pass`, `Definite=Ind\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Dem`, `Gender=Neut\|Number=Sing\|POS=DET\|PronType=Ind`, `Animacy=Hum\|Case=Acc\|Gender=Masc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Animacy=Hum\|Case=Nom\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Number=Plur\|POS=DET\|Polarity=Neg\|PronType=Neg`, `NumType=Card\|POS=NUM`, `Gender=Masc\|Number=Sing\|POS=DET\|PronType=Ind`, `POS=DET\|PronType=Prs`, `Gender=Fem\|Number=Sing\|POS=DET\|PronType=Ind`, `Case=Gen\|Gender=Neut\|POS=PROPN`, `Gender=Masc\|Number=Sing\|POS=DET\|Polarity=Neg\|PronType=Neg`, `Definite=Def\|Number=Sing\|POS=ADJ\|VerbForm=Part`, `Gender=Fem,Masc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `POS=AUX\|VerbForm=Inf`, `Case=Acc\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Gen\|Degree=Pos\|Number=Plur\|POS=ADJ`, `Number=Plur\|POS=DET\|PronType=Tot`, `Case=Gen\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Dem`, `Number=Plur\|POS=DET\|PronType=Prs`, `POS=SYM`, `Gender=Neut\|NumType=Card\|Number=Sing\|POS=NUM`, `Animacy=Hum\|Case=Nom\|Number=Sing\|POS=PRON\|PronType=Prs`, `Definite=Ind\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Prs`, `Case=Gen\|Definite=Ind\|Gender=Masc\|Number=Sing\|POS=NOUN`, `Abbr=Yes\|POS=ADV`, `Definite=Ind\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Dem`, `Gender=Masc\|Number=Sing\|POS=DET\|PronType=Tot`, `Definite=Def\|POS=DET\|PronType=Prs`, `Animacy=Hum\|Case=Nom\|Gender=Fem\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Gender=Neut\|POS=NOUN`, `Gender=Neut\|Number=Sing\|POS=DET\|PronType=Int`, `Definite=Def\|NumType=Card\|POS=NUM`, `Mood=Imp\|POS=VERB\|VerbForm=Fin`, `Definite=Ind\|Number=Plur\|POS=NOUN`, `Gender=Neut\|Number=Sing\|POS=DET\|PronType=Tot`, `Gender=Fem\|Number=Sing\|POS=DET\|PronType=Tot`, `Animacy=Hum\|Case=Acc\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `Gender=Fem,Masc\|Number=Sing\|POS=PRON\|Person=3\|Polarity=Neg\|PronType=Neg,Prs`, `Number=Plur\|POS=PRON\|Person=3\|Polarity=Neg\|PronType=Neg,Prs`, `Definite=Def\|NumType=Card\|Number=Sing\|POS=NUM`, `Gender=Masc\|NumType=Card\|Number=Sing\|POS=NUM`, `Definite=Ind\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Dem`, `Case=Gen\|Definite=Def\|Gender=Fem\|Number=Plur\|POS=NOUN`, `Case=Gen\|Gender=Neut\|Number=Sing\|POS=DET\|PronType=Dem`, `POS=SPACE`, `Animacy=Hum\|Number=Sing\|POS=PRON\|PronType=Art,Prs`, `Mood=Imp\|POS=AUX\|VerbForm=Fin`, `Number=Plur\|POS=PRON\|Person=3\|PronType=Prs,Tot`, `Number=Plur\|POS=ADJ`, `Gender=Masc\|POS=NOUN`, `Abbr=Yes\|POS=NOUN`, `Case=Gen\|Definite=Ind\|Gender=Masc\|Number=Plur\|POS=NOUN`, `Gender=Neut\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind,Prs`, `POS=INTJ`, `Animacy=Hum\|Case=Nom\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Animacy=Hum\|Case=Acc\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Case=Gen\|Definite=Def\|Gender=Masc\|Number=Plur\|POS=NOUN`, `POS=ADJ`, `Animacy=Hum\|Case=Acc\|Gender=Fem\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Animacy=Hum\|Case=Acc\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Definite=Def\|Gender=Fem\|Number=Sing\|POS=NOUN`, `Number=Sing\|POS=PRON\|Polarity=Neg\|PronType=Neg`, `Case=Gen\|POS=NOUN`, `Definite=Ind\|Number=Sing\|POS=ADJ`, `Case=Gen\|Gender=Masc\|POS=PROPN`, `Animacy=Hum\|Number=Plur\|POS=PRON\|PronType=Rcp`, `Case=Gen\|Definite=Ind\|Gender=Fem\|Number=Sing\|POS=NOUN`, `Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Gender=Fem,Masc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Ind,Prs`, `Definite=Ind\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Prs`, `Case=Gen\|Definite=Def\|Gender=Fem\|Number=Sing\|POS=NOUN`, `Gender=Fem\|Number=Sing\|POS=DET\|PronType=Art`, `Case=Gen\|Definite=Def\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Gender=Masc\|Number=Sing\|POS=DET\|PronType=Int`, `NumType=Card\|Number=Sing\|POS=NUM`, `Animacy=Hum\|Case=Acc\|Number=Plur\|POS=PRON\|Person=2\|PronType=Prs`, `Animacy=Hum\|Case=Nom\|Number=Plur\|POS=PRON\|Person=2\|PronType=Prs`, `Case=Gen\|Definite=Ind\|Degree=Pos\|Gender=Neut\|Number=Sing\|POS=ADJ`, `Degree=Sup\|POS=ADJ`, `Animacy=Hum\|POS=PRON\|PronType=Int`, `POS=DET\|PronType=Ind`, `Definite=Def\|Number=Sing\|POS=DET\|PronType=Dem`, `Gender=Fem\|POS=NOUN`, `Case=Gen\|Number=Plur\|POS=DET\|PronType=Dem`, `Gender=Fem,Masc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs,Tot`, `Case=Gen\|Definite=Ind\|Gender=Fem\|Number=Plur\|POS=NOUN`, `Gender=Neut\|Number=Sing\|POS=DET\|Polarity=Neg\|PronType=Neg`, `Number=Plur\|POS=NOUN`, `POS=PRON\|PronType=Prs`, `Case=Gen\|Definite=Ind\|Degree=Pos\|Number=Sing\|POS=ADJ`, `Definite=Ind\|Number=Sing\|POS=VERB\|VerbForm=Part`, `Case=Gen\|Definite=Def\|Number=Sing\|POS=ADJ\|VerbForm=Part`, `Mood=Ind\|POS=VERB\|Tense=Past\|VerbForm=Fin\|Voice=Pass`, `Gender=Neut\|Number=Sing\|POS=DET\|PronType=Dem,Ind`, `Animacy=Hum\|POS=PRON\|Poss=Yes\|PronType=Int`, `Abbr=Yes\|POS=ADJ`, `Case=Gen\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Art`, `Abbr=Yes\|Definite=Def,Ind\|Gender=Masc\|Number=Sing\|POS=NOUN`, `Case=Gen\|Gender=Fem\|Number=Sing\|POS=DET\|PronType=Dem`, `Number=Plur\|POS=PRON\|Poss=Yes\|PronType=Rcp`, `Definite=Ind\|Degree=Pos\|POS=ADJ`, `Number=Plur\|POS=DET\|PronType=Art`, `Case=Gen\|NumType=Card\|Number=Plur\|POS=NUM`, `Abbr=Yes\|Definite=Def,Ind\|Gender=Neut\|Number=Plur,Sing\|POS=NOUN`, `Case=Gen\|Number=Plur\|POS=DET\|PronType=Tot`, `Abbr=Yes\|Definite=Def,Ind\|Gender=Masc\|Number=Plur,Sing\|POS=NOUN`, `Gender=Fem\|Number=Sing\|POS=DET\|PronType=Int`, `Definite=Ind\|Gender=Neut\|Number=Sing\|POS=ADJ`, `Case=Gen\|Definite=Ind\|Gender=Masc\|Number=Sing\|POS=DET\|PronType=Dem`, `Gender=Fem\|Number=Sing\|POS=DET\|PronType=Prs`, `Animacy=Hum\|Case=Gen,Nom\|Number=Sing\|POS=PRON\|PronType=Art,Prs`, `Definite=Def\|Degree=Pos\|Gender=Masc\|Number=Sing\|POS=ADJ`, `Animacy=Hum\|Case=Gen\|Number=Sing\|POS=PRON\|PronType=Art,Prs`, `Gender=Fem\|NumType=Card\|Number=Sing\|POS=NUM`, `Definite=Ind\|Gender=Masc\|POS=NOUN`, `Definite=Def\|Number=Plur\|POS=NOUN`, `Number=Sing\|POS=ADJ\|VerbForm=Part`, `Definite=Ind\|Gender=Masc\|Number=Sing\|POS=ADJ\|VerbForm=Part`, `Abbr=Yes\|Gender=Masc\|POS=NOUN`, `Abbr=Yes\|Case=Gen\|POS=NOUN`, `Abbr=Yes\|Mood=Ind\|POS=VERB\|Tense=Pres\|VerbForm=Fin`, `Abbr=Yes\|Degree=Pos\|POS=ADJ`, `Case=Gen\|Gender=Fem\|POS=NOUN`, `Case=Gen\|Degree=Cmp\|POS=ADJ`, `Definite=Ind\|Degree=Pos\|Gender=Masc\|Number=Sing\|POS=ADJ`, `Gender=Masc\|Number=Sing\|POS=NOUN` |
99
  | **`parser`** | `ROOT`, `acl`, `acl:cleft`, `acl:relcl`, `advcl`, `advmod`, `amod`, `appos`, `aux`, `aux:pass`, `case`, `cc`, `ccomp`, `compound`, `compound:prt`, `conj`, `cop`, `csubj`, `dep`, `det`, `discourse`, `expl`, `flat:foreign`, `flat:name`, `iobj`, `mark`, `nmod`, `nsubj`, `nsubj:pass`, `nummod`, `obj`, `obl`, `orphan`, `parataxis`, `punct`, `xcomp` |
100
  | **`ner`** | `DRV`, `EVT`, `GPE_LOC`, `GPE_ORG`, `LOC`, `MISC`, `ORG`, `PER`, `PROD` |
101
 
109
  | `TOKEN_P` | 99.71 |
110
  | `TOKEN_R` | 99.53 |
111
  | `TOKEN_F` | 99.62 |
112
+ | `POS_ACC` | 97.26 |
113
+ | `MORPH_ACC` | 95.89 |
114
+ | `MORPH_MICRO_P` | 97.63 |
115
+ | `MORPH_MICRO_R` | 96.78 |
116
+ | `MORPH_MICRO_F` | 97.20 |
117
+ | `SENTS_P` | 92.84 |
118
+ | `SENTS_R` | 93.69 |
119
+ | `SENTS_F` | 93.26 |
120
+ | `DEP_UAS` | 89.23 |
121
+ | `DEP_LAS` | 86.10 |
122
+ | `LEMMA_ACC` | 97.12 |
123
+ | `TAG_ACC` | 97.26 |
124
+ | `ENTS_P` | 83.07 |
125
+ | `ENTS_R` | 81.69 |
126
+ | `ENTS_F` | 82.38 |
accuracy.json CHANGED
@@ -3,61 +3,61 @@
3
  "token_p": 0.997080292,
4
  "token_r": 0.9953256895,
5
  "token_f": 0.9962022181,
6
- "pos_acc": 0.9737451099,
7
- "morph_acc": 0.9592638003,
8
- "morph_micro_p": 0.9765452448,
9
- "morph_micro_r": 0.9673769287,
10
- "morph_micro_f": 0.971939466,
11
  "morph_per_feat": {
12
  "Definite": {
13
- "p": 0.9810039143,
14
- "r": 0.9664284904,
15
- "f": 0.973661658
16
  },
17
  "Gender": {
18
- "p": 0.9486150907,
19
- "r": 0.9420468557,
20
- "f": 0.9453195641
21
  },
22
  "Number": {
23
- "p": 0.9766441759,
24
- "r": 0.9650523848,
25
- "f": 0.9708136792
26
  },
27
  "Mood": {
28
- "p": 0.9866498741,
29
- "r": 0.9794948737,
30
- "f": 0.983059355
31
  },
32
  "Tense": {
33
- "p": 0.9870853381,
34
  "r": 0.9816167212,
35
- "f": 0.9843434343
36
  },
37
  "VerbForm": {
38
- "p": 0.9761203795,
39
- "r": 0.9726205997,
40
- "f": 0.9743673469
41
  },
42
  "Degree": {
43
- "p": 0.9705065926,
44
- "r": 0.9608381999,
45
- "f": 0.9656481961
46
  },
47
  "PronType": {
48
- "p": 0.9924226023,
49
- "r": 0.988783434,
50
- "f": 0.9905996759
51
  },
52
  "Poss": {
53
- "p": 0.9960474308,
54
- "r": 0.9960474308,
55
- "f": 0.9960474308
56
  },
57
  "Case": {
58
- "p": 0.9927536232,
59
- "r": 0.9861572536,
60
- "f": 0.9894444444
61
  },
62
  "Reflex": {
63
  "p": 1.0,
@@ -65,191 +65,196 @@
65
  "f": 1.0
66
  },
67
  "NumType": {
68
- "p": 0.995505618,
69
- "r": 0.9115226337,
70
- "f": 0.9516648765
71
  },
72
  "Polarity": {
73
- "p": 0.9968454259,
74
  "r": 1.0,
75
- "f": 0.9984202212
76
  },
77
  "Person": {
78
- "p": 0.9928741093,
79
- "r": 0.9919316564,
80
- "f": 0.9924026591
81
  },
82
  "Animacy": {
83
- "p": 0.9991452991,
84
- "r": 0.9957410562,
85
- "f": 0.997440273
86
  },
87
  "Voice": {
88
- "p": 0.9847328244,
89
  "r": 0.9347826087,
90
- "f": 0.9591078067
91
  },
92
  "Abbr": {
93
- "p": 1.0,
94
- "r": 0.84375,
95
- "f": 0.9152542373
96
  }
97
  },
98
- "sents_p": 0.9463617464,
99
- "sents_r": 0.9447903694,
100
- "sents_f": 0.9455754051,
101
- "dep_uas": 0.8943254651,
102
- "dep_las": 0.8639894956,
103
  "dep_las_per_type": {
104
  "nmod": {
105
- "p": 0.7818897638,
106
- "r": 0.8149363972,
107
- "f": 0.7980711272
108
  },
109
  "nsubj": {
110
- "p": 0.8936567164,
111
- "r": 0.8856702619,
112
- "f": 0.8896455657
113
  },
114
  "flat:name": {
115
- "p": 0.8613707165,
116
- "r": 0.8904991948,
117
- "f": 0.8756927949
118
  },
119
  "root": {
120
- "p": 0.9095060191,
121
- "r": 0.9095060191,
122
- "f": 0.9095060191
123
  },
124
  "advmod": {
125
- "p": 0.8416267943,
126
- "r": 0.844049904,
127
- "f": 0.8428366076
128
  },
129
  "mark": {
130
- "p": 0.9289311696,
131
- "r": 0.9232480534,
132
- "f": 0.9260808926
133
  },
134
  "advcl": {
135
- "p": 0.7150259067,
136
- "r": 0.7101200686,
137
- "f": 0.7125645439
138
  },
139
  "obj": {
140
- "p": 0.8902513795,
141
- "r": 0.9007444169,
142
- "f": 0.89546716
143
  },
144
  "case": {
145
- "p": 0.9364057673,
146
- "r": 0.9385806452,
147
- "f": 0.9374919448
148
  },
149
  "det": {
150
- "p": 0.9626582278,
151
- "r": 0.9626582278,
152
- "f": 0.9626582278
153
  },
154
  "obl": {
155
- "p": 0.7758702909,
156
- "r": 0.736199095,
157
- "f": 0.7555142791
158
  },
159
  "aux": {
160
- "p": 0.9513513514,
161
- "r": 0.9556561086,
162
- "f": 0.9534988713
163
  },
164
  "acl:relcl": {
165
- "p": 0.7921225383,
166
- "r": 0.8153153153,
167
- "f": 0.8035516093
168
  },
169
  "iobj": {
170
- "p": 0.8115942029,
171
- "r": 0.6363636364,
172
- "f": 0.7133757962
173
  },
174
  "xcomp": {
175
- "p": 0.7305936073,
176
- "r": 0.7256235828,
177
- "f": 0.7281001138
178
  },
179
  "cc": {
180
- "p": 0.9164733179,
181
- "r": 0.9136468774,
182
- "f": 0.9150579151
183
  },
184
  "conj": {
185
- "p": 0.7287043665,
186
- "r": 0.7392883079,
187
- "f": 0.7339581831
188
  },
189
  "amod": {
190
- "p": 0.9394865526,
191
- "r": 0.9309509388,
192
- "f": 0.9351992699
193
  },
194
  "nummod": {
195
- "p": 0.9073359073,
196
- "r": 0.9591836735,
197
- "f": 0.9325396825
198
  },
199
  "compound:prt": {
200
- "p": 0.8237547893,
201
- "r": 0.7761732852,
202
- "f": 0.7992565056
203
  },
204
  "cop": {
205
- "p": 0.8704358068,
206
- "r": 0.8808104887,
207
- "f": 0.8755924171
208
  },
209
  "appos": {
210
- "p": 0.2816901408,
211
- "r": 0.2,
212
- "f": 0.2339181287
213
  },
214
  "ccomp": {
215
- "p": 0.7867132867,
216
- "r": 0.8858267717,
217
- "f": 0.8333333333
218
  },
219
  "expl": {
220
- "p": 0.7329974811,
221
- "r": 0.7864864865,
222
- "f": 0.7588005215
223
  },
224
  "csubj": {
225
- "p": 0.7272727273,
226
- "r": 0.700729927,
227
- "f": 0.7137546468
228
  },
229
  "nsubj:pass": {
230
- "p": 0.890625,
231
- "r": 0.7916666667,
232
- "f": 0.8382352941
233
  },
234
  "aux:pass": {
235
- "p": 0.9159663866,
236
- "r": 0.9083333333,
237
- "f": 0.9121338912
 
 
 
 
 
238
  },
239
  "acl": {
240
- "p": 0.7198067633,
241
- "r": 0.6008064516,
242
- "f": 0.6549450549
243
  },
244
  "acl:cleft": {
245
- "p": 0.4782608696,
246
- "r": 0.4074074074,
247
- "f": 0.44
248
  },
249
  "orphan": {
250
- "p": 0.25,
251
- "r": 0.0384615385,
252
- "f": 0.0666666667
253
  },
254
  "dep": {
255
  "p": 0.0,
@@ -261,25 +266,20 @@
261
  "r": 0.0,
262
  "f": 0.0
263
  },
264
- "parataxis": {
265
- "p": 0.8661971831,
266
- "r": 0.6542553191,
267
- "f": 0.7454545455
268
- },
269
  "compound": {
270
- "p": 0.8,
271
- "r": 0.1951219512,
272
- "f": 0.3137254902
273
  },
274
  "flat:foreign": {
275
- "p": 0.9655172414,
276
- "r": 0.9032258065,
277
- "f": 0.9333333333
278
  },
279
  "discourse": {
280
- "p": 0.7777777778,
281
- "r": 0.3043478261,
282
- "f": 0.4375
283
  },
284
  "csubj:pass": {
285
  "p": 0.0,
@@ -287,52 +287,52 @@
287
  "f": 0.0
288
  }
289
  },
290
- "lemma_acc": 0.9709106936,
291
- "tag_acc": 0.9737451099,
292
- "ents_p": 0.8236700538,
293
- "ents_r": 0.8163507109,
294
- "ents_f": 0.8199940494,
295
  "ents_per_type": {
296
  "PER": {
297
- "p": 0.8894230769,
298
- "r": 0.9083469722,
299
- "f": 0.8987854251
300
  },
301
- "PROD": {
302
- "p": 0.7,
303
- "r": 0.5185185185,
304
- "f": 0.5957446809
305
  },
306
  "GPE_LOC": {
307
- "p": 0.8243727599,
308
- "r": 0.888030888,
309
- "f": 0.8550185874
310
  },
311
- "ORG": {
312
- "p": 0.8143851508,
313
- "r": 0.8688118812,
314
- "f": 0.8407185629
315
  },
316
  "LOC": {
317
- "p": 0.7875,
318
- "r": 0.5779816514,
319
- "f": 0.6666666667
320
  },
321
  "DRV": {
322
- "p": 0.7466666667,
323
- "r": 0.7088607595,
324
- "f": 0.7272727273
 
 
 
 
 
325
  },
326
  "EVT": {
327
- "p": 0.3571428571,
328
  "r": 0.5555555556,
329
- "f": 0.4347826087
330
- },
331
- "GPE_ORG": {
332
- "p": 0.68,
333
- "r": 0.6181818182,
334
- "f": 0.6476190476
335
  }
336
  },
337
- "speed": 11180.6759357661
338
  }
3
  "token_p": 0.997080292,
4
  "token_r": 0.9953256895,
5
  "token_f": 0.9962022181,
6
+ "pos_acc": 0.9726155711,
7
+ "morph_acc": 0.9588648574,
8
+ "morph_micro_p": 0.9762975408,
9
+ "morph_micro_r": 0.9677851253,
10
+ "morph_micro_f": 0.9720226967,
11
  "morph_per_feat": {
12
  "Definite": {
13
+ "p": 0.9811364159,
14
+ "r": 0.9674492458,
15
+ "f": 0.9742447604
16
  },
17
  "Gender": {
18
+ "p": 0.9491493022,
19
+ "r": 0.9418571564,
20
+ "f": 0.9454891692
21
  },
22
  "Number": {
23
+ "p": 0.9778305034,
24
+ "r": 0.9662246318,
25
+ "f": 0.9719929245
26
  },
27
  "Mood": {
28
+ "p": 0.985434455,
29
+ "r": 0.9812453113,
30
+ "f": 0.9833354216
31
  },
32
  "Tense": {
33
+ "p": 0.9850897144,
34
  "r": 0.9816167212,
35
+ "f": 0.9833501514
36
  },
37
  "VerbForm": {
38
+ "p": 0.9756774404,
39
+ "r": 0.9740873533,
40
+ "f": 0.9748817485
41
  },
42
  "Degree": {
43
+ "p": 0.9691934926,
44
+ "r": 0.9618687736,
45
+ "f": 0.9655172414
46
  },
47
  "PronType": {
48
+ "p": 0.9909130247,
49
+ "r": 0.9879206212,
50
+ "f": 0.9894145604
51
  },
52
  "Poss": {
53
+ "p": 0.9960159363,
54
+ "r": 0.9881422925,
55
+ "f": 0.9920634921
56
  },
57
  "Case": {
58
+ "p": 0.9916294643,
59
+ "r": 0.9839424142,
60
+ "f": 0.9877709839
61
  },
62
  "Reflex": {
63
  "p": 1.0,
65
  "f": 1.0
66
  },
67
  "NumType": {
68
+ "p": 0.9977375566,
69
+ "r": 0.9074074074,
70
+ "f": 0.9504310345
71
  },
72
  "Polarity": {
73
+ "p": 0.9937106918,
74
  "r": 1.0,
75
+ "f": 0.9968454259
76
  },
77
  "Person": {
78
+ "p": 0.99191631,
79
+ "r": 0.9900332226,
80
+ "f": 0.9909738717
81
  },
82
  "Animacy": {
83
+ "p": 0.9982935154,
84
+ "r": 0.996592845,
85
+ "f": 0.9974424552
86
  },
87
  "Voice": {
88
+ "p": 0.9485294118,
89
  "r": 0.9347826087,
90
+ "f": 0.9416058394
91
  },
92
  "Abbr": {
93
+ "p": 0.9851851852,
94
+ "r": 0.83125,
95
+ "f": 0.9016949153
96
  }
97
  },
98
+ "sents_p": 0.9284245167,
99
+ "sents_r": 0.9369032794,
100
+ "sents_f": 0.9326446281,
101
+ "dep_uas": 0.8923091347,
102
+ "dep_las": 0.8610490461,
103
  "dep_las_per_type": {
104
  "nmod": {
105
+ "p": 0.7902772198,
106
+ "r": 0.8071399261,
107
+ "f": 0.7986195696
108
  },
109
  "nsubj": {
110
+ "p": 0.8889232673,
111
+ "r": 0.8853620955,
112
+ "f": 0.8871391076
113
  },
114
  "flat:name": {
115
+ "p": 0.8865814696,
116
+ "r": 0.8937198068,
117
+ "f": 0.8901363272
118
  },
119
  "root": {
120
+ "p": 0.9037344398,
121
+ "r": 0.904109589,
122
+ "f": 0.9039219755
123
  },
124
  "advmod": {
125
+ "p": 0.8367541766,
126
+ "r": 0.8411708253,
127
+ "f": 0.8389566882
128
  },
129
  "mark": {
130
+ "p": 0.9274958171,
131
+ "r": 0.924916574,
132
+ "f": 0.9262043999
133
  },
134
  "advcl": {
135
+ "p": 0.7152658662,
136
+ "r": 0.7152658662,
137
+ "f": 0.7152658662
138
  },
139
  "obj": {
140
+ "p": 0.8852459016,
141
+ "r": 0.9044665012,
142
+ "f": 0.8947529917
143
  },
144
  "case": {
145
+ "p": 0.9379042691,
146
+ "r": 0.935483871,
147
+ "f": 0.9366925065
148
  },
149
  "det": {
150
+ "p": 0.9658444023,
151
+ "r": 0.9664556962,
152
+ "f": 0.9661499525
153
  },
154
  "obl": {
155
+ "p": 0.7677725118,
156
+ "r": 0.7330316742,
157
+ "f": 0.75
158
  },
159
  "aux": {
160
+ "p": 0.9400715564,
161
+ "r": 0.9511312217,
162
+ "f": 0.9455690508
163
  },
164
  "acl:relcl": {
165
+ "p": 0.8079470199,
166
+ "r": 0.8243243243,
167
+ "f": 0.8160535117
168
  },
169
  "iobj": {
170
+ "p": 0.75,
171
+ "r": 0.6136363636,
172
+ "f": 0.675
173
  },
174
  "xcomp": {
175
+ "p": 0.7074829932,
176
+ "r": 0.7074829932,
177
+ "f": 0.7074829932
178
  },
179
  "cc": {
180
+ "p": 0.9115593483,
181
+ "r": 0.9059367772,
182
+ "f": 0.9087393658
183
  },
184
  "conj": {
185
+ "p": 0.7390050469,
186
+ "r": 0.7443718228,
187
+ "f": 0.7416787265
188
  },
189
  "amod": {
190
+ "p": 0.9309090909,
191
+ "r": 0.9303452453,
192
+ "f": 0.9306270827
193
  },
194
  "nummod": {
195
+ "p": 0.9147286822,
196
+ "r": 0.9632653061,
197
+ "f": 0.9383697813
198
  },
199
  "compound:prt": {
200
+ "p": 0.8175182482,
201
+ "r": 0.8086642599,
202
+ "f": 0.8130671506
203
  },
204
  "cop": {
205
+ "p": 0.8709677419,
206
+ "r": 0.8688915375,
207
+ "f": 0.869928401
208
  },
209
  "appos": {
210
+ "p": 0.2643678161,
211
+ "r": 0.23,
212
+ "f": 0.2459893048
213
  },
214
  "ccomp": {
215
+ "p": 0.8051470588,
216
+ "r": 0.8622047244,
217
+ "f": 0.8326996198
218
  },
219
  "expl": {
220
+ "p": 0.6959798995,
221
+ "r": 0.7486486486,
222
+ "f": 0.7213541667
223
  },
224
  "csubj": {
225
+ "p": 0.696,
226
+ "r": 0.6350364964,
227
+ "f": 0.6641221374
228
  },
229
  "nsubj:pass": {
230
+ "p": 0.9100529101,
231
+ "r": 0.7962962963,
232
+ "f": 0.849382716
233
  },
234
  "aux:pass": {
235
+ "p": 0.9464285714,
236
+ "r": 0.8833333333,
237
+ "f": 0.9137931034
238
+ },
239
+ "parataxis": {
240
+ "p": 0.8541666667,
241
+ "r": 0.6542553191,
242
+ "f": 0.7409638554
243
  },
244
  "acl": {
245
+ "p": 0.6740088106,
246
+ "r": 0.6169354839,
247
+ "f": 0.6442105263
248
  },
249
  "acl:cleft": {
250
+ "p": 0.4285714286,
251
+ "r": 0.3333333333,
252
+ "f": 0.375
253
  },
254
  "orphan": {
255
+ "p": 0.0,
256
+ "r": 0.0,
257
+ "f": 0.0
258
  },
259
  "dep": {
260
  "p": 0.0,
266
  "r": 0.0,
267
  "f": 0.0
268
  },
 
 
 
 
 
269
  "compound": {
270
+ "p": 0.9090909091,
271
+ "r": 0.243902439,
272
+ "f": 0.3846153846
273
  },
274
  "flat:foreign": {
275
+ "p": 0.8214285714,
276
+ "r": 0.7419354839,
277
+ "f": 0.7796610169
278
  },
279
  "discourse": {
280
+ "p": 0.7272727273,
281
+ "r": 0.347826087,
282
+ "f": 0.4705882353
283
  },
284
  "csubj:pass": {
285
  "p": 0.0,
287
  "f": 0.0
288
  }
289
  },
290
+ "lemma_acc": 0.9712137072,
291
+ "tag_acc": 0.9726155711,
292
+ "ents_p": 0.8307228916,
293
+ "ents_r": 0.816943128,
294
+ "ents_f": 0.8237753883,
295
  "ents_per_type": {
296
  "PER": {
297
+ "p": 0.9011532125,
298
+ "r": 0.8952536825,
299
+ "f": 0.8981937603
300
  },
301
+ "ORG": {
302
+ "p": 0.8111888112,
303
+ "r": 0.8613861386,
304
+ "f": 0.8355342137
305
  },
306
  "GPE_LOC": {
307
+ "p": 0.8587360595,
308
+ "r": 0.8918918919,
309
+ "f": 0.875
310
  },
311
+ "PROD": {
312
+ "p": 0.6492537313,
313
+ "r": 0.537037037,
314
+ "f": 0.5878378378
315
  },
316
  "LOC": {
317
+ "p": 0.7931034483,
318
+ "r": 0.6330275229,
319
+ "f": 0.7040816327
320
  },
321
  "DRV": {
322
+ "p": 0.7714285714,
323
+ "r": 0.6835443038,
324
+ "f": 0.7248322148
325
+ },
326
+ "GPE_ORG": {
327
+ "p": 0.6666666667,
328
+ "r": 0.6909090909,
329
+ "f": 0.6785714286
330
  },
331
  "EVT": {
332
+ "p": 0.7142857143,
333
  "r": 0.5555555556,
334
+ "f": 0.625
 
 
 
 
 
335
  }
336
  },
337
+ "speed": 9847.9572403325
338
  }
lemmatizer/cfg CHANGED
@@ -37,213 +37,214 @@
37
  67,
38
  69,
39
  70,
40
- 72,
41
- 74,
42
- 77,
43
- 80,
44
- 82,
45
- 86,
46
- 88,
47
- 92,
48
- 94,
49
  95,
50
  96,
51
- 98,
52
- 100,
53
- 102,
54
- 106,
55
- 108,
56
- 111,
57
  112,
58
- 114,
59
- 116,
60
- 118,
61
- 120,
62
- 124,
63
- 126,
64
- 128,
65
- 130,
66
- 133,
67
- 135,
68
  136,
69
  137,
70
  138,
71
- 140,
72
- 142,
73
- 144,
74
- 146,
75
- 148,
76
- 150,
77
- 152,
78
  153,
79
- 156,
80
- 159,
81
  160,
82
- 162,
83
  163,
84
- 165,
85
- 167,
86
- 169,
87
- 171,
88
- 173,
89
  174,
90
- 176,
91
- 178,
92
  179,
93
  180,
94
  181,
95
- 183,
96
  184,
97
- 186,
98
  187,
99
  188,
100
  189,
101
- 192,
102
  193,
103
- 195,
104
- 197,
105
  198,
106
- 201,
107
- 203,
108
- 205,
109
- 208,
110
- 211,
111
  212,
112
  213,
113
  214,
114
- 217,
115
- 219,
116
- 221,
117
  222,
118
  223,
119
- 225,
120
  226,
121
  228,
122
- 229,
123
- 232,
124
- 233,
125
  236,
126
- 239,
127
- 241,
128
- 242,
129
  243,
130
  244,
131
  247,
132
  250,
133
  252,
134
  253,
135
- 256,
 
136
  258,
137
- 259,
138
- 260,
139
  263,
140
  264,
141
- 266,
142
  267,
143
- 268,
144
  269,
145
- 270,
146
  272,
147
- 274,
148
  276,
149
- 278,
150
  279,
 
151
  281,
 
 
152
  285,
153
- 287,
154
  289,
155
- 291,
156
  295,
 
157
  297,
158
- 298,
159
- 299,
160
  302,
161
- 303,
162
- 304,
163
- 307,
164
  308,
165
  309,
166
  311,
167
- 312,
168
- 314,
169
- 46,
170
- 316,
171
- 318,
172
  319,
173
  321,
174
  322,
175
- 323,
176
  324,
177
  326,
178
- 327,
179
  328,
180
- 330,
181
  331,
 
182
  333,
183
- 335,
184
  336,
185
  337,
186
  338,
187
  340,
188
  341,
189
  342,
190
- 343,
191
  345,
192
  347,
193
- 348,
194
  349,
 
195
  351,
196
- 353,
 
 
197
  356,
198
- 358,
199
  359,
200
- 360,
201
  361,
202
  362,
203
- 364,
204
  365,
205
- 368,
206
- 369,
207
- 371,
208
  373,
 
 
209
  376,
210
  378,
211
  379,
212
  382,
 
213
  385,
214
  387,
215
- 389,
216
- 391,
217
- 393,
218
  395,
219
- 397,
220
- 399,
221
  401,
222
  403,
223
- 405,
 
224
  407,
225
- 409,
226
- 411,
227
- 413,
228
  414,
229
- 415,
230
- 417,
231
  418,
232
  419,
233
- 421,
234
  422,
 
235
  424,
236
- 426,
237
- 429,
238
- 431,
 
239
  432,
240
- 434,
241
  436,
242
- 437,
243
  439,
244
  440,
245
  442,
246
- 443,
247
  444,
248
  447,
249
  449,
@@ -253,14 +254,13 @@
253
  453,
254
  456,
255
  457,
256
- 458,
257
  460,
258
- 461,
259
- 463,
260
  466,
261
  467,
262
- 468,
263
- 470,
264
  471,
265
  473,
266
  476,
@@ -277,302 +277,315 @@
277
  490,
278
  491,
279
  492,
 
280
  494,
281
  496,
282
  498,
283
- 499,
284
  501,
285
- 502,
286
  503,
287
  504,
288
- 507,
289
- 508,
 
290
  510,
291
- 511,
292
- 515,
293
- 519,
294
  521,
295
  523,
296
  525,
297
  527,
298
- 528,
299
  529,
300
  530,
301
  531,
 
302
  533,
303
- 534,
304
  536,
305
- 537,
306
  538,
 
307
  540,
308
  541,
309
- 543,
 
310
  545,
311
- 546,
312
- 548,
313
- 552,
314
  553,
315
- 554,
316
- 555,
317
- 556,
318
  558,
319
  559,
320
  560,
321
  562,
322
- 563,
323
  564,
 
324
  566,
325
  568,
326
  569,
327
- 570,
328
  572,
329
  574,
330
  576,
331
- 579,
332
- 580,
333
  581,
 
334
  583,
335
- 584,
336
  586,
337
- 587,
338
  589,
339
- 592,
340
  594,
341
  595,
342
- 596,
343
  598,
344
- 600,
345
- 602,
346
- 604,
 
347
  607,
348
- 608,
349
- 611,
350
- 612,
351
  613,
352
- 616,
 
353
  618,
354
  620,
355
- 621,
356
  623,
357
- 624,
358
  625,
359
  626,
360
  627,
361
- 628,
362
  629,
 
363
  631,
364
  632,
 
365
  635,
366
- 636,
367
- 639,
368
  640,
369
  642,
370
- 644,
371
  646,
372
- 650,
 
373
  652,
374
- 653,
375
  654,
376
  655,
377
  656,
378
  657,
 
379
  659,
380
- 660,
381
  662,
382
- 663,
383
  664,
 
384
  666,
385
  668,
386
  670,
387
  672,
388
- 673,
389
  674,
390
  675,
 
391
  677,
392
  679,
393
- 680,
394
  682,
395
  683,
396
- 685,
397
  686,
398
  687,
399
- 688,
400
  689,
 
401
  691,
 
 
402
  694,
403
  695,
404
- 696,
405
  697,
406
- 698,
407
  700,
408
  701,
 
409
  703,
410
  704,
411
  705,
412
- 706,
413
  708,
414
  710,
415
  711,
416
  712,
417
- 713,
418
- 715,
419
  716,
420
  717,
421
  718,
422
- 719,
423
  720,
424
  721,
425
- 722,
426
  724,
427
  725,
 
428
  727,
429
  728,
430
  729,
431
  730,
 
432
  733,
433
  735,
434
- 737,
435
  738,
436
  740,
437
  742,
438
  743,
439
  744,
440
- 745,
441
  746,
442
- 747,
443
  749,
444
  750,
445
  751,
446
  752,
 
447
  754,
448
  756,
449
  757,
450
  758,
451
  760,
452
- 761,
453
  762,
454
  763,
455
  764,
456
- 765,
457
  766,
458
- 767,
459
  768,
460
  769,
461
  770,
 
 
462
  773,
463
  774,
464
  775,
465
  776,
466
  777,
467
  778,
468
- 779,
469
- 780,
470
  781,
471
  783,
472
  784,
 
473
  786,
 
 
474
  789,
 
475
  792,
476
- 793,
477
  795,
478
- 796,
479
  798,
480
- 799,
481
- 800,
482
  801,
483
- 803,
484
  804,
 
 
 
 
485
  808,
486
  809,
487
  811,
488
  812,
489
  813,
490
- 814,
491
- 816,
492
  818,
493
  819,
494
- 820,
495
- 113,
496
- 41,
497
  821,
498
  822,
499
  823,
500
- 825,
501
- 827,
502
  828,
 
 
503
  831,
504
  832,
505
  833,
506
- 834,
507
  837,
508
  838,
509
  839,
510
- 840,
511
  842,
 
512
  844,
513
  845,
514
  847,
515
- 848,
516
  850,
517
  851,
 
518
  853,
519
- 855,
520
  856,
521
- 857,
522
  858,
 
523
  860,
524
- 861,
525
  862,
526
  863,
 
527
  865,
528
- 868,
 
 
529
  872,
530
  873,
531
- 875,
532
  876,
533
  877,
534
- 880,
535
- 881,
536
  882,
537
- 883,
538
- 885,
539
- 887,
540
  886,
 
541
  888,
542
  889,
543
  890,
 
544
  892,
545
- 894,
546
  895,
 
547
  897,
548
  898,
549
  899,
 
550
  901,
551
  902,
552
- 904,
553
- 906,
 
554
  908,
555
- 910,
 
556
  912,
557
  913,
558
  915,
559
- 919,
 
560
  920,
561
  922,
562
- 923,
563
  924,
564
- 925,
565
  926,
566
- 927,
567
  928,
568
- 930,
569
- 932,
570
- 933,
571
- 934,
572
  937,
 
573
  939,
 
574
  941,
575
  942,
576
- 943
 
 
 
 
 
 
 
 
 
 
577
  ]
578
  }
37
  67,
38
  69,
39
  70,
40
+ 71,
41
+ 73,
42
+ 75,
43
+ 78,
44
+ 81,
45
+ 83,
46
+ 87,
47
+ 89,
48
+ 93,
49
  95,
50
  96,
51
+ 97,
52
+ 99,
53
+ 101,
54
+ 103,
55
+ 107,
56
+ 109,
57
  112,
58
+ 113,
59
+ 115,
60
+ 117,
61
+ 119,
62
+ 121,
63
+ 125,
64
+ 127,
65
+ 129,
66
+ 131,
67
+ 134,
68
  136,
69
  137,
70
  138,
71
+ 139,
72
+ 141,
73
+ 143,
74
+ 145,
75
+ 147,
76
+ 149,
77
+ 151,
78
  153,
79
+ 154,
80
+ 157,
81
  160,
82
+ 161,
83
  163,
84
+ 164,
85
+ 166,
86
+ 168,
87
+ 170,
88
+ 172,
89
  174,
90
+ 175,
91
+ 177,
92
  179,
93
  180,
94
  181,
95
+ 182,
96
  184,
97
+ 185,
98
  187,
99
  188,
100
  189,
101
+ 190,
102
  193,
103
+ 194,
104
+ 196,
105
  198,
106
+ 199,
107
+ 202,
108
+ 204,
109
+ 206,
110
+ 209,
111
  212,
112
  213,
113
  214,
114
+ 215,
115
+ 218,
116
+ 220,
117
  222,
118
  223,
119
+ 224,
120
  226,
121
  228,
122
+ 230,
123
+ 234,
 
124
  236,
125
+ 237,
126
+ 238,
127
+ 240,
128
  243,
129
  244,
130
  247,
131
  250,
132
  252,
133
  253,
134
+ 254,
135
+ 255,
136
  258,
137
+ 261,
 
138
  263,
139
  264,
 
140
  267,
 
141
  269,
142
+ 271,
143
  272,
144
+ 273,
145
  276,
146
+ 277,
147
  279,
148
+ 280,
149
  281,
150
+ 282,
151
+ 283,
152
  285,
 
153
  289,
154
+ 293,
155
  295,
156
+ 296,
157
  297,
158
+ 300,
159
+ 301,
160
  302,
161
+ 305,
162
+ 306,
163
+ 46,
164
  308,
165
  309,
166
  311,
167
+ 313,
168
+ 315,
169
+ 317,
 
 
170
  319,
171
  321,
172
  322,
 
173
  324,
174
  326,
 
175
  328,
176
+ 329,
177
  331,
178
+ 332,
179
  333,
180
+ 334,
181
  336,
182
  337,
183
  338,
184
  340,
185
  341,
186
  342,
187
+ 344,
188
  345,
189
  347,
 
190
  349,
191
+ 350,
192
  351,
193
+ 352,
194
+ 354,
195
+ 355,
196
  356,
197
+ 357,
198
  359,
 
199
  361,
200
  362,
201
+ 363,
202
  365,
203
+ 367,
204
+ 370,
205
+ 372,
206
  373,
207
+ 374,
208
+ 375,
209
  376,
210
  378,
211
  379,
212
  382,
213
+ 383,
214
  385,
215
  387,
216
+ 390,
217
+ 392,
218
+ 394,
219
  395,
220
+ 398,
 
221
  401,
222
  403,
223
+ 404,
224
+ 406,
225
  407,
226
+ 408,
227
+ 410,
228
+ 412,
229
  414,
230
+ 416,
 
231
  418,
232
  419,
233
+ 420,
234
  422,
235
+ 423,
236
  424,
237
+ 425,
238
+ 427,
239
+ 428,
240
+ 430,
241
  432,
242
+ 435,
243
  436,
244
+ 438,
245
  439,
246
  440,
247
  442,
 
248
  444,
249
  447,
250
  449,
254
  453,
255
  456,
256
  457,
257
+ 459,
258
  460,
259
+ 462,
260
+ 465,
261
  466,
262
  467,
263
+ 469,
 
264
  471,
265
  473,
266
  476,
277
  490,
278
  491,
279
  492,
280
+ 493,
281
  494,
282
  496,
283
  498,
284
+ 500,
285
  501,
 
286
  503,
287
  504,
288
+ 505,
289
+ 506,
290
+ 509,
291
  510,
292
+ 512,
293
+ 513,
294
+ 517,
295
  521,
296
  523,
297
  525,
298
  527,
 
299
  529,
300
  530,
301
  531,
302
+ 532,
303
  533,
304
+ 535,
305
  536,
 
306
  538,
307
+ 539,
308
  540,
309
  541,
310
+ 542,
311
+ 544,
312
  545,
313
+ 547,
314
+ 549,
315
+ 551,
316
  553,
317
+ 557,
 
 
318
  558,
319
  559,
320
  560,
321
  562,
 
322
  564,
323
+ 565,
324
  566,
325
  568,
326
  569,
327
+ 571,
328
  572,
329
  574,
330
  576,
331
+ 578,
 
332
  581,
333
+ 582,
334
  583,
335
+ 585,
336
  586,
337
+ 588,
338
  589,
339
+ 591,
340
  594,
341
  595,
342
+ 597,
343
  598,
344
+ 599,
345
+ 601,
346
+ 603,
347
+ 605,
348
  607,
349
+ 610,
 
 
350
  613,
351
+ 614,
352
+ 617,
353
  618,
354
  620,
355
+ 622,
356
  623,
 
357
  625,
358
  626,
359
  627,
 
360
  629,
361
+ 630,
362
  631,
363
  632,
364
+ 634,
365
  635,
366
+ 638,
 
367
  640,
368
  642,
369
+ 645,
370
  646,
371
+ 647,
372
+ 651,
373
  652,
 
374
  654,
375
  655,
376
  656,
377
  657,
378
+ 658,
379
  659,
380
+ 661,
381
  662,
 
382
  664,
383
+ 665,
384
  666,
385
  668,
386
  670,
387
  672,
 
388
  674,
389
  675,
390
+ 676,
391
  677,
392
  679,
393
+ 681,
394
  682,
395
  683,
396
+ 684,
397
  686,
398
  687,
 
399
  689,
400
+ 690,
401
  691,
402
+ 692,
403
+ 693,
404
  694,
405
  695,
 
406
  697,
 
407
  700,
408
  701,
409
+ 702,
410
  703,
411
  704,
412
  705,
413
+ 707,
414
  708,
415
  710,
416
  711,
417
  712,
418
+ 714,
 
419
  716,
420
  717,
421
  718,
 
422
  720,
423
  721,
424
+ 723,
425
  724,
426
  725,
427
+ 726,
428
  727,
429
  728,
430
  729,
431
  730,
432
+ 732,
433
  733,
434
  735,
 
435
  738,
436
  740,
437
  742,
438
  743,
439
  744,
 
440
  746,
441
+ 748,
442
  749,
443
  750,
444
  751,
445
  752,
446
+ 753,
447
  754,
448
  756,
449
  757,
450
  758,
451
  760,
 
452
  762,
453
  763,
454
  764,
 
455
  766,
 
456
  768,
457
  769,
458
  770,
459
+ 771,
460
+ 772,
461
  773,
462
  774,
463
  775,
464
  776,
465
  777,
466
  778,
 
 
467
  781,
468
  783,
469
  784,
470
+ 785,
471
  786,
472
+ 787,
473
+ 788,
474
  789,
475
+ 791,
476
  792,
477
+ 794,
478
  795,
 
479
  798,
 
 
480
  801,
481
+ 802,
482
  804,
483
+ 805,
484
+ 807,
485
+ 391,
486
+ 232,
487
  808,
488
  809,
489
  811,
490
  812,
491
  813,
492
+ 817,
 
493
  818,
494
  819,
 
 
 
495
  821,
496
  822,
497
  823,
498
+ 824,
499
+ 826,
500
  828,
501
+ 829,
502
+ 830,
503
  831,
504
  832,
505
  833,
506
+ 835,
507
  837,
508
  838,
509
  839,
 
510
  842,
511
+ 843,
512
  844,
513
  845,
514
  847,
 
515
  850,
516
  851,
517
+ 852,
518
  853,
519
+ 854,
520
  856,
 
521
  858,
522
+ 859,
523
  860,
 
524
  862,
525
  863,
526
+ 864,
527
  865,
528
+ 867,
529
+ 869,
530
+ 870,
531
  872,
532
  873,
533
+ 874,
534
  876,
535
  877,
536
+ 879,
 
537
  882,
 
 
 
538
  886,
539
+ 887,
540
  888,
541
  889,
542
  890,
543
+ 891,
544
  892,
 
545
  895,
546
+ 896,
547
  897,
548
  898,
549
  899,
550
+ 900,
551
  901,
552
  902,
553
+ 903,
554
+ 905,
555
+ 907,
556
  908,
557
+ 909,
558
+ 911,
559
  912,
560
  913,
561
  915,
562
+ 916,
563
+ 918,
564
  920,
565
  922,
 
566
  924,
 
567
  926,
 
568
  928,
569
+ 927,
570
+ 929,
571
+ 931,
572
+ 935,
573
  937,
574
+ 938,
575
  939,
576
+ 940,
577
  941,
578
  942,
579
+ 943,
580
+ 944,
581
+ 946,
582
+ 948,
583
+ 949,
584
+ 952,
585
+ 953,
586
+ 955,
587
+ 312,
588
+ 956,
589
+ 957
590
  ]
591
  }
lemmatizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:308418ddce9129421d4ac4f1f342d3034df0025accd10d3d2eab91fba178f420
3
- size 223154
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47e7af6a857797bf29c60b577e898ce0592883d94e5037eeb734f214d4b48810
3
+ size 228198
lemmatizer/trees CHANGED
Binary files a/lemmatizer/trees and b/lemmatizer/trees differ
meta.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "lang":"nb",
3
  "name":"core_news_md",
4
- "version":"3.3.0",
5
  "description":"Norwegian (Bokm\u00e5l) 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":"MIT",
10
- "spacy_version":">=3.3.0.dev0,<3.4.0",
11
- "spacy_git_version":"849bef2de",
12
  "vectors":{
13
  "width":300,
14
  "vectors":20000,
@@ -142,6 +142,7 @@
142
  "Definite=Ind|Gender=Masc|Number=Sing|POS=DET|PronType=Dem",
143
  "Case=Gen|Definite=Def|Gender=Fem|Number=Plur|POS=NOUN",
144
  "Case=Gen|Gender=Neut|Number=Sing|POS=DET|PronType=Dem",
 
145
  "Animacy=Hum|Number=Sing|POS=PRON|PronType=Art,Prs",
146
  "Mood=Imp|POS=AUX|VerbForm=Fin",
147
  "Number=Plur|POS=PRON|Person=3|PronType=Prs,Tot",
@@ -302,61 +303,61 @@
302
  "token_p":0.997080292,
303
  "token_r":0.9953256895,
304
  "token_f":0.9962022181,
305
- "pos_acc":0.9737451099,
306
- "morph_acc":0.9592638003,
307
- "morph_micro_p":0.9765452448,
308
- "morph_micro_r":0.9673769287,
309
- "morph_micro_f":0.971939466,
310
  "morph_per_feat":{
311
  "Definite":{
312
- "p":0.9810039143,
313
- "r":0.9664284904,
314
- "f":0.973661658
315
  },
316
  "Gender":{
317
- "p":0.9486150907,
318
- "r":0.9420468557,
319
- "f":0.9453195641
320
  },
321
  "Number":{
322
- "p":0.9766441759,
323
- "r":0.9650523848,
324
- "f":0.9708136792
325
  },
326
  "Mood":{
327
- "p":0.9866498741,
328
- "r":0.9794948737,
329
- "f":0.983059355
330
  },
331
  "Tense":{
332
- "p":0.9870853381,
333
  "r":0.9816167212,
334
- "f":0.9843434343
335
  },
336
  "VerbForm":{
337
- "p":0.9761203795,
338
- "r":0.9726205997,
339
- "f":0.9743673469
340
  },
341
  "Degree":{
342
- "p":0.9705065926,
343
- "r":0.9608381999,
344
- "f":0.9656481961
345
  },
346
  "PronType":{
347
- "p":0.9924226023,
348
- "r":0.988783434,
349
- "f":0.9905996759
350
  },
351
  "Poss":{
352
- "p":0.9960474308,
353
- "r":0.9960474308,
354
- "f":0.9960474308
355
  },
356
  "Case":{
357
- "p":0.9927536232,
358
- "r":0.9861572536,
359
- "f":0.9894444444
360
  },
361
  "Reflex":{
362
  "p":1.0,
@@ -364,191 +365,196 @@
364
  "f":1.0
365
  },
366
  "NumType":{
367
- "p":0.995505618,
368
- "r":0.9115226337,
369
- "f":0.9516648765
370
  },
371
  "Polarity":{
372
- "p":0.9968454259,
373
  "r":1.0,
374
- "f":0.9984202212
375
  },
376
  "Person":{
377
- "p":0.9928741093,
378
- "r":0.9919316564,
379
- "f":0.9924026591
380
  },
381
  "Animacy":{
382
- "p":0.9991452991,
383
- "r":0.9957410562,
384
- "f":0.997440273
385
  },
386
  "Voice":{
387
- "p":0.9847328244,
388
  "r":0.9347826087,
389
- "f":0.9591078067
390
  },
391
  "Abbr":{
392
- "p":1.0,
393
- "r":0.84375,
394
- "f":0.9152542373
395
  }
396
  },
397
- "sents_p":0.9463617464,
398
- "sents_r":0.9447903694,
399
- "sents_f":0.9455754051,
400
- "dep_uas":0.8943254651,
401
- "dep_las":0.8639894956,
402
  "dep_las_per_type":{
403
  "nmod":{
404
- "p":0.7818897638,
405
- "r":0.8149363972,
406
- "f":0.7980711272
407
  },
408
  "nsubj":{
409
- "p":0.8936567164,
410
- "r":0.8856702619,
411
- "f":0.8896455657
412
  },
413
  "flat:name":{
414
- "p":0.8613707165,
415
- "r":0.8904991948,
416
- "f":0.8756927949
417
  },
418
  "root":{
419
- "p":0.9095060191,
420
- "r":0.9095060191,
421
- "f":0.9095060191
422
  },
423
  "advmod":{
424
- "p":0.8416267943,
425
- "r":0.844049904,
426
- "f":0.8428366076
427
  },
428
  "mark":{
429
- "p":0.9289311696,
430
- "r":0.9232480534,
431
- "f":0.9260808926
432
  },
433
  "advcl":{
434
- "p":0.7150259067,
435
- "r":0.7101200686,
436
- "f":0.7125645439
437
  },
438
  "obj":{
439
- "p":0.8902513795,
440
- "r":0.9007444169,
441
- "f":0.89546716
442
  },
443
  "case":{
444
- "p":0.9364057673,
445
- "r":0.9385806452,
446
- "f":0.9374919448
447
  },
448
  "det":{
449
- "p":0.9626582278,
450
- "r":0.9626582278,
451
- "f":0.9626582278
452
  },
453
  "obl":{
454
- "p":0.7758702909,
455
- "r":0.736199095,
456
- "f":0.7555142791
457
  },
458
  "aux":{
459
- "p":0.9513513514,
460
- "r":0.9556561086,
461
- "f":0.9534988713
462
  },
463
  "acl:relcl":{
464
- "p":0.7921225383,
465
- "r":0.8153153153,
466
- "f":0.8035516093
467
  },
468
  "iobj":{
469
- "p":0.8115942029,
470
- "r":0.6363636364,
471
- "f":0.7133757962
472
  },
473
  "xcomp":{
474
- "p":0.7305936073,
475
- "r":0.7256235828,
476
- "f":0.7281001138
477
  },
478
  "cc":{
479
- "p":0.9164733179,
480
- "r":0.9136468774,
481
- "f":0.9150579151
482
  },
483
  "conj":{
484
- "p":0.7287043665,
485
- "r":0.7392883079,
486
- "f":0.7339581831
487
  },
488
  "amod":{
489
- "p":0.9394865526,
490
- "r":0.9309509388,
491
- "f":0.9351992699
492
  },
493
  "nummod":{
494
- "p":0.9073359073,
495
- "r":0.9591836735,
496
- "f":0.9325396825
497
  },
498
  "compound:prt":{
499
- "p":0.8237547893,
500
- "r":0.7761732852,
501
- "f":0.7992565056
502
  },
503
  "cop":{
504
- "p":0.8704358068,
505
- "r":0.8808104887,
506
- "f":0.8755924171
507
  },
508
  "appos":{
509
- "p":0.2816901408,
510
- "r":0.2,
511
- "f":0.2339181287
512
  },
513
  "ccomp":{
514
- "p":0.7867132867,
515
- "r":0.8858267717,
516
- "f":0.8333333333
517
  },
518
  "expl":{
519
- "p":0.7329974811,
520
- "r":0.7864864865,
521
- "f":0.7588005215
522
  },
523
  "csubj":{
524
- "p":0.7272727273,
525
- "r":0.700729927,
526
- "f":0.7137546468
527
  },
528
  "nsubj:pass":{
529
- "p":0.890625,
530
- "r":0.7916666667,
531
- "f":0.8382352941
532
  },
533
  "aux:pass":{
534
- "p":0.9159663866,
535
- "r":0.9083333333,
536
- "f":0.9121338912
 
 
 
 
 
537
  },
538
  "acl":{
539
- "p":0.7198067633,
540
- "r":0.6008064516,
541
- "f":0.6549450549
542
  },
543
  "acl:cleft":{
544
- "p":0.4782608696,
545
- "r":0.4074074074,
546
- "f":0.44
547
  },
548
  "orphan":{
549
- "p":0.25,
550
- "r":0.0384615385,
551
- "f":0.0666666667
552
  },
553
  "dep":{
554
  "p":0.0,
@@ -560,25 +566,20 @@
560
  "r":0.0,
561
  "f":0.0
562
  },
563
- "parataxis":{
564
- "p":0.8661971831,
565
- "r":0.6542553191,
566
- "f":0.7454545455
567
- },
568
  "compound":{
569
- "p":0.8,
570
- "r":0.1951219512,
571
- "f":0.3137254902
572
  },
573
  "flat:foreign":{
574
- "p":0.9655172414,
575
- "r":0.9032258065,
576
- "f":0.9333333333
577
  },
578
  "discourse":{
579
- "p":0.7777777778,
580
- "r":0.3043478261,
581
- "f":0.4375
582
  },
583
  "csubj:pass":{
584
  "p":0.0,
@@ -586,54 +587,54 @@
586
  "f":0.0
587
  }
588
  },
589
- "lemma_acc":0.9709106936,
590
- "tag_acc":0.9737451099,
591
- "ents_p":0.8236700538,
592
- "ents_r":0.8163507109,
593
- "ents_f":0.8199940494,
594
  "ents_per_type":{
595
  "PER":{
596
- "p":0.8894230769,
597
- "r":0.9083469722,
598
- "f":0.8987854251
599
  },
600
- "PROD":{
601
- "p":0.7,
602
- "r":0.5185185185,
603
- "f":0.5957446809
604
  },
605
  "GPE_LOC":{
606
- "p":0.8243727599,
607
- "r":0.888030888,
608
- "f":0.8550185874
609
  },
610
- "ORG":{
611
- "p":0.8143851508,
612
- "r":0.8688118812,
613
- "f":0.8407185629
614
  },
615
  "LOC":{
616
- "p":0.7875,
617
- "r":0.5779816514,
618
- "f":0.6666666667
619
  },
620
  "DRV":{
621
- "p":0.7466666667,
622
- "r":0.7088607595,
623
- "f":0.7272727273
 
 
 
 
 
624
  },
625
  "EVT":{
626
- "p":0.3571428571,
627
  "r":0.5555555556,
628
- "f":0.4347826087
629
- },
630
- "GPE_ORG":{
631
- "p":0.68,
632
- "r":0.6181818182,
633
- "f":0.6476190476
634
  }
635
  },
636
- "speed":11180.6759357661
637
  },
638
  "sources":[
639
  {
1
  {
2
  "lang":"nb",
3
  "name":"core_news_md",
4
+ "version":"3.4.0",
5
  "description":"Norwegian (Bokm\u00e5l) 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":"MIT",
10
+ "spacy_version":">=3.4.0,<3.5.0",
11
+ "spacy_git_version":"dd038b536",
12
  "vectors":{
13
  "width":300,
14
  "vectors":20000,
142
  "Definite=Ind|Gender=Masc|Number=Sing|POS=DET|PronType=Dem",
143
  "Case=Gen|Definite=Def|Gender=Fem|Number=Plur|POS=NOUN",
144
  "Case=Gen|Gender=Neut|Number=Sing|POS=DET|PronType=Dem",
145
+ "POS=SPACE",
146
  "Animacy=Hum|Number=Sing|POS=PRON|PronType=Art,Prs",
147
  "Mood=Imp|POS=AUX|VerbForm=Fin",
148
  "Number=Plur|POS=PRON|Person=3|PronType=Prs,Tot",
303
  "token_p":0.997080292,
304
  "token_r":0.9953256895,
305
  "token_f":0.9962022181,
306
+ "pos_acc":0.9726155711,
307
+ "morph_acc":0.9588648574,
308
+ "morph_micro_p":0.9762975408,
309
+ "morph_micro_r":0.9677851253,
310
+ "morph_micro_f":0.9720226967,
311
  "morph_per_feat":{
312
  "Definite":{
313
+ "p":0.9811364159,
314
+ "r":0.9674492458,
315
+ "f":0.9742447604
316
  },
317
  "Gender":{
318
+ "p":0.9491493022,
319
+ "r":0.9418571564,
320
+ "f":0.9454891692
321
  },
322
  "Number":{
323
+ "p":0.9778305034,
324
+ "r":0.9662246318,
325
+ "f":0.9719929245
326
  },
327
  "Mood":{
328
+ "p":0.985434455,
329
+ "r":0.9812453113,
330
+ "f":0.9833354216
331
  },
332
  "Tense":{
333
+ "p":0.9850897144,
334
  "r":0.9816167212,
335
+ "f":0.9833501514
336
  },
337
  "VerbForm":{
338
+ "p":0.9756774404,
339
+ "r":0.9740873533,
340
+ "f":0.9748817485
341
  },
342
  "Degree":{
343
+ "p":0.9691934926,
344
+ "r":0.9618687736,
345
+ "f":0.9655172414
346
  },
347
  "PronType":{
348
+ "p":0.9909130247,
349
+ "r":0.9879206212,
350
+ "f":0.9894145604
351
  },
352
  "Poss":{
353
+ "p":0.9960159363,
354
+ "r":0.9881422925,
355
+ "f":0.9920634921
356
  },
357
  "Case":{
358
+ "p":0.9916294643,
359
+ "r":0.9839424142,
360
+ "f":0.9877709839
361
  },
362
  "Reflex":{
363
  "p":1.0,
365
  "f":1.0
366
  },
367
  "NumType":{
368
+ "p":0.9977375566,
369
+ "r":0.9074074074,
370
+ "f":0.9504310345
371
  },
372
  "Polarity":{
373
+ "p":0.9937106918,
374
  "r":1.0,
375
+ "f":0.9968454259
376
  },
377
  "Person":{
378
+ "p":0.99191631,
379
+ "r":0.9900332226,
380
+ "f":0.9909738717
381
  },
382
  "Animacy":{
383
+ "p":0.9982935154,
384
+ "r":0.996592845,
385
+ "f":0.9974424552
386
  },
387
  "Voice":{
388
+ "p":0.9485294118,
389
  "r":0.9347826087,
390
+ "f":0.9416058394
391
  },
392
  "Abbr":{
393
+ "p":0.9851851852,
394
+ "r":0.83125,
395
+ "f":0.9016949153
396
  }
397
  },
398
+ "sents_p":0.9284245167,
399
+ "sents_r":0.9369032794,
400
+ "sents_f":0.9326446281,
401
+ "dep_uas":0.8923091347,
402
+ "dep_las":0.8610490461,
403
  "dep_las_per_type":{
404
  "nmod":{
405
+ "p":0.7902772198,
406
+ "r":0.8071399261,
407
+ "f":0.7986195696
408
  },
409
  "nsubj":{
410
+ "p":0.8889232673,
411
+ "r":0.8853620955,
412
+ "f":0.8871391076
413
  },
414
  "flat:name":{
415
+ "p":0.8865814696,
416
+ "r":0.8937198068,
417
+ "f":0.8901363272
418
  },
419
  "root":{
420
+ "p":0.9037344398,
421
+ "r":0.904109589,
422
+ "f":0.9039219755
423
  },
424
  "advmod":{
425
+ "p":0.8367541766,
426
+ "r":0.8411708253,
427
+ "f":0.8389566882
428
  },
429
  "mark":{
430
+ "p":0.9274958171,
431
+ "r":0.924916574,
432
+ "f":0.9262043999
433
  },
434
  "advcl":{
435
+ "p":0.7152658662,
436
+ "r":0.7152658662,
437
+ "f":0.7152658662
438
  },
439
  "obj":{
440
+ "p":0.8852459016,
441
+ "r":0.9044665012,
442
+ "f":0.8947529917
443
  },
444
  "case":{
445
+ "p":0.9379042691,
446
+ "r":0.935483871,
447
+ "f":0.9366925065
448
  },
449
  "det":{
450
+ "p":0.9658444023,
451
+ "r":0.9664556962,
452
+ "f":0.9661499525
453
  },
454
  "obl":{
455
+ "p":0.7677725118,
456
+ "r":0.7330316742,
457
+ "f":0.75
458
  },
459
  "aux":{
460
+ "p":0.9400715564,
461
+ "r":0.9511312217,
462
+ "f":0.9455690508
463
  },
464
  "acl:relcl":{
465
+ "p":0.8079470199,
466
+ "r":0.8243243243,
467
+ "f":0.8160535117
468
  },
469
  "iobj":{
470
+ "p":0.75,
471
+ "r":0.6136363636,
472
+ "f":0.675
473
  },
474
  "xcomp":{
475
+ "p":0.7074829932,
476
+ "r":0.7074829932,
477
+ "f":0.7074829932
478
  },
479
  "cc":{
480
+ "p":0.9115593483,
481
+ "r":0.9059367772,
482
+ "f":0.9087393658
483
  },
484
  "conj":{
485
+ "p":0.7390050469,
486
+ "r":0.7443718228,
487
+ "f":0.7416787265
488
  },
489
  "amod":{
490
+ "p":0.9309090909,
491
+ "r":0.9303452453,
492
+ "f":0.9306270827
493
  },
494
  "nummod":{
495
+ "p":0.9147286822,
496
+ "r":0.9632653061,
497
+ "f":0.9383697813
498
  },
499
  "compound:prt":{
500
+ "p":0.8175182482,
501
+ "r":0.8086642599,
502
+ "f":0.8130671506
503
  },
504
  "cop":{
505
+ "p":0.8709677419,
506
+ "r":0.8688915375,
507
+ "f":0.869928401
508
  },
509
  "appos":{
510
+ "p":0.2643678161,
511
+ "r":0.23,
512
+ "f":0.2459893048
513
  },
514
  "ccomp":{
515
+ "p":0.8051470588,
516
+ "r":0.8622047244,
517
+ "f":0.8326996198
518
  },
519
  "expl":{
520
+ "p":0.6959798995,
521
+ "r":0.7486486486,
522
+ "f":0.7213541667
523
  },
524
  "csubj":{
525
+ "p":0.696,
526
+ "r":0.6350364964,
527
+ "f":0.6641221374
528
  },
529
  "nsubj:pass":{
530
+ "p":0.9100529101,
531
+ "r":0.7962962963,
532
+ "f":0.849382716
533
  },
534
  "aux:pass":{
535
+ "p":0.9464285714,
536
+ "r":0.8833333333,
537
+ "f":0.9137931034
538
+ },
539
+ "parataxis":{
540
+ "p":0.8541666667,
541
+ "r":0.6542553191,
542
+ "f":0.7409638554
543
  },
544
  "acl":{
545
+ "p":0.6740088106,
546
+ "r":0.6169354839,
547
+ "f":0.6442105263
548
  },
549
  "acl:cleft":{
550
+ "p":0.4285714286,
551
+ "r":0.3333333333,
552
+ "f":0.375
553
  },
554
  "orphan":{
555
+ "p":0.0,
556
+ "r":0.0,
557
+ "f":0.0
558
  },
559
  "dep":{
560
  "p":0.0,
566
  "r":0.0,
567
  "f":0.0
568
  },
 
 
 
 
 
569
  "compound":{
570
+ "p":0.9090909091,
571
+ "r":0.243902439,
572
+ "f":0.3846153846
573
  },
574
  "flat:foreign":{
575
+ "p":0.8214285714,
576
+ "r":0.7419354839,
577
+ "f":0.7796610169
578
  },
579
  "discourse":{
580
+ "p":0.7272727273,
581
+ "r":0.347826087,
582
+ "f":0.4705882353
583
  },
584
  "csubj:pass":{
585
  "p":0.0,
587
  "f":0.0
588
  }
589
  },
590
+ "lemma_acc":0.9712137072,
591
+ "tag_acc":0.9726155711,
592
+ "ents_p":0.8307228916,
593
+ "ents_r":0.816943128,
594
+ "ents_f":0.8237753883,
595
  "ents_per_type":{
596
  "PER":{
597
+ "p":0.9011532125,
598
+ "r":0.8952536825,
599
+ "f":0.8981937603
600
  },
601
+ "ORG":{
602
+ "p":0.8111888112,
603
+ "r":0.8613861386,
604
+ "f":0.8355342137
605
  },
606
  "GPE_LOC":{
607
+ "p":0.8587360595,
608
+ "r":0.8918918919,
609
+ "f":0.875
610
  },
611
+ "PROD":{
612
+ "p":0.6492537313,
613
+ "r":0.537037037,
614
+ "f":0.5878378378
615
  },
616
  "LOC":{
617
+ "p":0.7931034483,
618
+ "r":0.6330275229,
619
+ "f":0.7040816327
620
  },
621
  "DRV":{
622
+ "p":0.7714285714,
623
+ "r":0.6835443038,
624
+ "f":0.7248322148
625
+ },
626
+ "GPE_ORG":{
627
+ "p":0.6666666667,
628
+ "r":0.6909090909,
629
+ "f":0.6785714286
630
  },
631
  "EVT":{
632
+ "p":0.7142857143,
633
  "r":0.5555555556,
634
+ "f":0.625
 
 
 
 
 
635
  }
636
  },
637
+ "speed":9847.9572403325
638
  },
639
  "sources":[
640
  {
morphologizer/cfg CHANGED
@@ -123,6 +123,7 @@
123
  "Definite=Ind|Gender=Masc|Number=Sing|POS=DET|PronType=Dem":"Definite=Ind|Gender=Masc|Number=Sing|PronType=Dem",
124
  "Case=Gen|Definite=Def|Gender=Fem|Number=Plur|POS=NOUN":"Case=Gen|Definite=Def|Gender=Fem|Number=Plur",
125
  "Case=Gen|Gender=Neut|Number=Sing|POS=DET|PronType=Dem":"Case=Gen|Gender=Neut|Number=Sing|PronType=Dem",
 
126
  "Animacy=Hum|Number=Sing|POS=PRON|PronType=Art,Prs":"Animacy=Hum|Number=Sing|PronType=Art,Prs",
127
  "Mood=Imp|POS=AUX|VerbForm=Fin":"Mood=Imp|VerbForm=Fin",
128
  "Number=Plur|POS=PRON|Person=3|PronType=Prs,Tot":"Number=Plur|Person=3|PronType=Prs,Tot",
@@ -328,6 +329,7 @@
328
  "Definite=Ind|Gender=Masc|Number=Sing|POS=DET|PronType=Dem":90,
329
  "Case=Gen|Definite=Def|Gender=Fem|Number=Plur|POS=NOUN":92,
330
  "Case=Gen|Gender=Neut|Number=Sing|POS=DET|PronType=Dem":90,
 
331
  "Animacy=Hum|Number=Sing|POS=PRON|PronType=Art,Prs":95,
332
  "Mood=Imp|POS=AUX|VerbForm=Fin":87,
333
  "Number=Plur|POS=PRON|Person=3|PronType=Prs,Tot":95,
123
  "Definite=Ind|Gender=Masc|Number=Sing|POS=DET|PronType=Dem":"Definite=Ind|Gender=Masc|Number=Sing|PronType=Dem",
124
  "Case=Gen|Definite=Def|Gender=Fem|Number=Plur|POS=NOUN":"Case=Gen|Definite=Def|Gender=Fem|Number=Plur",
125
  "Case=Gen|Gender=Neut|Number=Sing|POS=DET|PronType=Dem":"Case=Gen|Gender=Neut|Number=Sing|PronType=Dem",
126
+ "POS=SPACE":"",
127
  "Animacy=Hum|Number=Sing|POS=PRON|PronType=Art,Prs":"Animacy=Hum|Number=Sing|PronType=Art,Prs",
128
  "Mood=Imp|POS=AUX|VerbForm=Fin":"Mood=Imp|VerbForm=Fin",
129
  "Number=Plur|POS=PRON|Person=3|PronType=Prs,Tot":"Number=Plur|Person=3|PronType=Prs,Tot",
329
  "Definite=Ind|Gender=Masc|Number=Sing|POS=DET|PronType=Dem":90,
330
  "Case=Gen|Definite=Def|Gender=Fem|Number=Plur|POS=NOUN":92,
331
  "Case=Gen|Gender=Neut|Number=Sing|POS=DET|PronType=Dem":90,
332
+ "POS=SPACE":103,
333
  "Animacy=Hum|Number=Sing|POS=PRON|PronType=Art,Prs":95,
334
  "Mood=Imp|POS=AUX|VerbForm=Fin":87,
335
  "Number=Plur|POS=PRON|Person=3|PronType=Prs,Tot":95,
morphologizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:953b18c4041f56c8e81ab1e72f368d334703ce15aeacb3d49d0b8ca860063a10
3
- size 79201
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27ab81c14e33e41e076056007c622fefc994097b3281280bd49607c4916207f6
3
+ size 79589
nb_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:fc39e74e42eb116f4a80d05e1e5cf158351d03daa73515afbb343cb6b7904d93
3
- size 42323085
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b507de99f8d3a727ec17123e4be257d0a97094501829627fa56ac2e962a9a97e
3
+ size 42334448
ner/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03c65e018e1e5638ac53553e407d6a541039c479205c7a59932f774031590a65
3
  size 6501792
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb92ec4122116b225dc6349268e7d880f4a47f6bd1a3a841cd9abca3c1571b52
3
  size 6501792
ner/moves CHANGED
@@ -1 +1 @@
1
- ��moves��{"0":{},"1":{"PER":6378,"ORG":3793,"GPE_LOC":2278,"PROD":1284,"LOC":842,"DRV":640,"GPE_ORG":410,"EVT":201,"MISC":12},"2":{"PER":6378,"ORG":3793,"GPE_LOC":2278,"PROD":1284,"LOC":842,"DRV":640,"GPE_ORG":410,"EVT":201,"MISC":12},"3":{"PER":6378,"ORG":3793,"GPE_LOC":2278,"PROD":1284,"LOC":842,"DRV":640,"GPE_ORG":410,"EVT":201,"MISC":12},"4":{"PER":6378,"ORG":3793,"GPE_LOC":2278,"PROD":1284,"LOC":842,"DRV":640,"GPE_ORG":410,"EVT":201,"MISC":12,"":1},"5":{"":1}}�cfg��neg_key�
1
+ ��moves��{"0":{},"1":{"PER":6387,"ORG":3797,"GPE_LOC":2281,"PROD":1286,"LOC":842,"DRV":641,"GPE_ORG":410,"EVT":201,"MISC":12},"2":{"PER":6387,"ORG":3797,"GPE_LOC":2281,"PROD":1286,"LOC":842,"DRV":641,"GPE_ORG":410,"EVT":201,"MISC":12},"3":{"PER":6387,"ORG":3797,"GPE_LOC":2281,"PROD":1286,"LOC":842,"DRV":641,"GPE_ORG":410,"EVT":201,"MISC":12},"4":{"PER":6387,"ORG":3797,"GPE_LOC":2281,"PROD":1286,"LOC":842,"DRV":641,"GPE_ORG":410,"EVT":201,"MISC":12,"":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:c33f9613428cedf5751008b38dfcc7fc44706457cff3f14a66f0f3b7cbbc122c
3
  size 308989
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54763e5e8877dfb2e40e4e0f88b9283937fc352221e7dfe2b145cd42a1e70303
3
  size 308989
parser/moves CHANGED
@@ -1 +1 @@
1
- ��moves�~{"0":{"":134900},"1":{"":93292},"2":{"case":25334,"nsubj":18615,"mark":12192,"amod":10711,"det":10563,"punct":10025,"advmod":9967,"cc":8383,"aux":6803,"cop":5514,"nmod":5449,"obl":2945,"expl":2092,"nummod":1827,"nsubj:pass":1366,"aux:pass":862,"advcl":759,"obj":572,"compound":239,"discourse":89,"csubj":88,"compound:prt":83,"iobj":77,"xcomp":53,"acl||nsubj":51,"dep":0},"3":{"punct":19146,"obl":11656,"obj":10276,"nmod":10154,"conj":9408,"advmod":4274,"flat:name":4150,"nsubj":3717,"advcl":3241,"xcomp":3108,"acl:relcl":3075,"compound:prt":1947,"ccomp":1749,"acl":1257,"parataxis":1103,"csubj":693,"appos":637,"iobj":469,"expl":457,"flat:foreign":365,"amod":328,"acl:cleft":255,"cop":192,"det":179,"orphan":163,"advcl||advmod":161,"acl||nsubj":161,"case||obl":129,"obl||advmod":87,"nsubj:pass":81,"obl||amod":65,"obl||det":56,"appos||nsubj":38,"acl||nsubj:pass":34,"dep":0},"4":{"ROOT":15696}}�cfg��neg_key�
1
+ ��moves��{"0":{"":134903},"1":{"":94491},"2":{"case":25334,"nsubj":18615,"mark":12192,"amod":10711,"det":10563,"punct":10025,"advmod":9967,"cc":8383,"aux":6803,"cop":5514,"nmod":5449,"obl":2945,"expl":2092,"nummod":1827,"nsubj:pass":1366,"aux:pass":862,"advcl":759,"obj":572,"compound":239,"discourse":89,"csubj":88,"compound:prt":83,"iobj":77,"xcomp":53,"acl||nsubj":51,"dep":0},"3":{"punct":19146,"obl":11656,"obj":10276,"nmod":10154,"conj":9408,"advmod":4274,"flat:name":4150,"nsubj":3717,"advcl":3241,"xcomp":3108,"acl:relcl":3075,"compound:prt":1947,"ccomp":1749,"acl":1257,"dep":1199,"parataxis":1103,"csubj":693,"appos":637,"iobj":469,"expl":457,"flat:foreign":365,"amod":328,"acl:cleft":255,"cop":192,"det":179,"orphan":163,"advcl||advmod":161,"acl||nsubj":161,"case||obl":129,"obl||advmod":87,"nsubj:pass":81,"obl||amod":65,"obl||det":56,"appos||nsubj":38,"acl||nsubj:pass":34},"4":{"ROOT":15696}}�cfg��neg_key�
senter/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ad3301951a8faf36e7fb22262fb6ba5aefb8a57ee835ab0f9409bbc5a36cf0a
3
  size 219953
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7f194fb8ee67f54ce5c1faf8b00bc4227c6f4255e859053cd0b9c79929f2891
3
  size 219953
tok2vec/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ea3f40e42c01de053b3a24a464e2a43af4ca75f08985289941a2bdfa19eea52
3
  size 6365604
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6876b10488e90b847277ebe8a6455f0c6146d5d34489c038881c631e5391d5e4
3
  size 6365604
vocab/key2row CHANGED
Binary files a/vocab/key2row and b/vocab/key2row differ
vocab/strings.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dd5ff311701790799abf0fd90b6c66e266d4a5ee32336365eb98f779dbc219d
3
- size 10228698
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f81e6e1a065dc3ec3f5d4bda8d5151492786a36fd49c99d7765270e48c535f28
3
+ size 10237053