Update spaCy pipeline
Browse files- .gitattributes +5 -0
- README.md +57 -0
- config.cfg +197 -0
- meta.json +650 -0
- morphologizer/cfg +412 -0
- morphologizer/model +3 -0
- nb_nocy_trf-any-py3-none-any.whl +3 -0
- ner/cfg +13 -0
- ner/model +3 -0
- ner/moves +1 -0
- parser/cfg +13 -0
- parser/model +3 -0
- parser/moves +1 -0
- tagger/cfg +21 -0
- tagger/model +3 -0
- tokenizer +3 -0
- transformer/cfg +3 -0
- transformer/model/config.json +24 -0
- transformer/model/pytorch_model.bin +3 -0
- transformer/model/special_tokens_map.json +1 -0
- transformer/model/tokenizer.json +0 -0
- transformer/model/tokenizer_config.json +1 -0
- transformer/model/vocab.txt +0 -0
- vocab/key2row +1 -0
- vocab/lookups.bin +3 -0
- vocab/strings.json +3 -0
- vocab/vectors +3 -0
.gitattributes
CHANGED
|
@@ -15,3 +15,8 @@
|
|
| 15 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 16 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 17 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 16 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 17 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.whl filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*strings.json filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
vectors filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
model filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- spacy
|
| 4 |
+
- token-classification
|
| 5 |
+
language:
|
| 6 |
+
- nb
|
| 7 |
+
model-index:
|
| 8 |
+
- name: nb_nocy_trf
|
| 9 |
+
results:
|
| 10 |
+
- tasks:
|
| 11 |
+
name: NER
|
| 12 |
+
type: token-classification
|
| 13 |
+
metrics:
|
| 14 |
+
- name: Precision
|
| 15 |
+
type: precision
|
| 16 |
+
value: 0.9021803182
|
| 17 |
+
- name: Recall
|
| 18 |
+
type: recall
|
| 19 |
+
value: 0.9069905213
|
| 20 |
+
- name: F Score
|
| 21 |
+
type: f_score
|
| 22 |
+
value: 0.9045790251
|
| 23 |
+
- tasks:
|
| 24 |
+
name: POS
|
| 25 |
+
type: token-classification
|
| 26 |
+
metrics:
|
| 27 |
+
- name: Accuracy
|
| 28 |
+
type: accuracy
|
| 29 |
+
value: 0.987973053
|
| 30 |
+
- tasks:
|
| 31 |
+
name: SENTER
|
| 32 |
+
type: token-classification
|
| 33 |
+
metrics:
|
| 34 |
+
- name: Precision
|
| 35 |
+
type: precision
|
| 36 |
+
value: 0.9679276316
|
| 37 |
+
- name: Recall
|
| 38 |
+
type: recall
|
| 39 |
+
value: 0.9767634855
|
| 40 |
+
- name: F Score
|
| 41 |
+
type: f_score
|
| 42 |
+
value: 0.9723254853
|
| 43 |
+
- tasks:
|
| 44 |
+
name: UNLABELED_DEPENDENCIES
|
| 45 |
+
type: token-classification
|
| 46 |
+
metrics:
|
| 47 |
+
- name: Accuracy
|
| 48 |
+
type: accuracy
|
| 49 |
+
value: 0.9433838463
|
| 50 |
+
- tasks:
|
| 51 |
+
name: LABELED_DEPENDENCIES
|
| 52 |
+
type: token-classification
|
| 53 |
+
metrics:
|
| 54 |
+
- name: Accuracy
|
| 55 |
+
type: accuracy
|
| 56 |
+
value: 0.9433838463
|
| 57 |
+
---
|
config.cfg
ADDED
|
@@ -0,0 +1,197 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[paths]
|
| 2 |
+
train = "corpus/norne/train.spacy"
|
| 3 |
+
dev = "corpus/norne/dev.spacy"
|
| 4 |
+
vectors = null
|
| 5 |
+
init_tok2vec = null
|
| 6 |
+
|
| 7 |
+
[system]
|
| 8 |
+
gpu_allocator = "pytorch"
|
| 9 |
+
seed = 0
|
| 10 |
+
|
| 11 |
+
[nlp]
|
| 12 |
+
lang = "nb"
|
| 13 |
+
pipeline = ["transformer","tagger","morphologizer","parser","ner"]
|
| 14 |
+
batch_size = 128
|
| 15 |
+
disabled = []
|
| 16 |
+
before_creation = null
|
| 17 |
+
after_creation = null
|
| 18 |
+
after_pipeline_creation = null
|
| 19 |
+
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
| 20 |
+
|
| 21 |
+
[components]
|
| 22 |
+
|
| 23 |
+
[components.morphologizer]
|
| 24 |
+
factory = "morphologizer"
|
| 25 |
+
|
| 26 |
+
[components.morphologizer.model]
|
| 27 |
+
@architectures = "spacy.Tagger.v1"
|
| 28 |
+
nO = null
|
| 29 |
+
|
| 30 |
+
[components.morphologizer.model.tok2vec]
|
| 31 |
+
@architectures = "spacy-transformers.TransformerListener.v1"
|
| 32 |
+
grad_factor = 1.0
|
| 33 |
+
pooling = {"@layers":"reduce_mean.v1"}
|
| 34 |
+
upstream = "*"
|
| 35 |
+
|
| 36 |
+
[components.ner]
|
| 37 |
+
factory = "ner"
|
| 38 |
+
incorrect_spans_key = null
|
| 39 |
+
moves = null
|
| 40 |
+
update_with_oracle_cut_size = 100
|
| 41 |
+
|
| 42 |
+
[components.ner.model]
|
| 43 |
+
@architectures = "spacy.TransitionBasedParser.v2"
|
| 44 |
+
state_type = "ner"
|
| 45 |
+
extra_state_tokens = false
|
| 46 |
+
hidden_width = 64
|
| 47 |
+
maxout_pieces = 2
|
| 48 |
+
use_upper = false
|
| 49 |
+
nO = null
|
| 50 |
+
|
| 51 |
+
[components.ner.model.tok2vec]
|
| 52 |
+
@architectures = "spacy-transformers.TransformerListener.v1"
|
| 53 |
+
grad_factor = 1.0
|
| 54 |
+
pooling = {"@layers":"reduce_mean.v1"}
|
| 55 |
+
upstream = "*"
|
| 56 |
+
|
| 57 |
+
[components.parser]
|
| 58 |
+
factory = "parser"
|
| 59 |
+
learn_tokens = false
|
| 60 |
+
min_action_freq = 30
|
| 61 |
+
moves = null
|
| 62 |
+
update_with_oracle_cut_size = 100
|
| 63 |
+
|
| 64 |
+
[components.parser.model]
|
| 65 |
+
@architectures = "spacy.TransitionBasedParser.v2"
|
| 66 |
+
state_type = "parser"
|
| 67 |
+
extra_state_tokens = false
|
| 68 |
+
hidden_width = 128
|
| 69 |
+
maxout_pieces = 3
|
| 70 |
+
use_upper = false
|
| 71 |
+
nO = null
|
| 72 |
+
|
| 73 |
+
[components.parser.model.tok2vec]
|
| 74 |
+
@architectures = "spacy-transformers.TransformerListener.v1"
|
| 75 |
+
grad_factor = 1.0
|
| 76 |
+
pooling = {"@layers":"reduce_mean.v1"}
|
| 77 |
+
upstream = "*"
|
| 78 |
+
|
| 79 |
+
[components.tagger]
|
| 80 |
+
factory = "tagger"
|
| 81 |
+
|
| 82 |
+
[components.tagger.model]
|
| 83 |
+
@architectures = "spacy.Tagger.v1"
|
| 84 |
+
nO = null
|
| 85 |
+
|
| 86 |
+
[components.tagger.model.tok2vec]
|
| 87 |
+
@architectures = "spacy-transformers.TransformerListener.v1"
|
| 88 |
+
grad_factor = 1.0
|
| 89 |
+
pooling = {"@layers":"reduce_mean.v1"}
|
| 90 |
+
upstream = "*"
|
| 91 |
+
|
| 92 |
+
[components.transformer]
|
| 93 |
+
factory = "transformer"
|
| 94 |
+
max_batch_items = 4096
|
| 95 |
+
set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
|
| 96 |
+
|
| 97 |
+
[components.transformer.model]
|
| 98 |
+
@architectures = "spacy-transformers.TransformerModel.v1"
|
| 99 |
+
name = "ltgoslo/norbert"
|
| 100 |
+
|
| 101 |
+
[components.transformer.model.get_spans]
|
| 102 |
+
@span_getters = "spacy-transformers.strided_spans.v1"
|
| 103 |
+
window = 128
|
| 104 |
+
stride = 96
|
| 105 |
+
|
| 106 |
+
[components.transformer.model.tokenizer_config]
|
| 107 |
+
use_fast = true
|
| 108 |
+
|
| 109 |
+
[corpora]
|
| 110 |
+
|
| 111 |
+
[corpora.dev]
|
| 112 |
+
@readers = "spacy.Corpus.v1"
|
| 113 |
+
path = ${paths.dev}
|
| 114 |
+
max_length = 0
|
| 115 |
+
gold_preproc = false
|
| 116 |
+
limit = 0
|
| 117 |
+
augmenter = null
|
| 118 |
+
|
| 119 |
+
[corpora.train]
|
| 120 |
+
@readers = "spacy.Corpus.v1"
|
| 121 |
+
path = ${paths.train}
|
| 122 |
+
max_length = 0
|
| 123 |
+
gold_preproc = false
|
| 124 |
+
limit = 0
|
| 125 |
+
augmenter = null
|
| 126 |
+
|
| 127 |
+
[training]
|
| 128 |
+
accumulate_gradient = 3
|
| 129 |
+
dev_corpus = "corpora.dev"
|
| 130 |
+
train_corpus = "corpora.train"
|
| 131 |
+
seed = ${system.seed}
|
| 132 |
+
gpu_allocator = ${system.gpu_allocator}
|
| 133 |
+
dropout = 0.1
|
| 134 |
+
patience = 1600
|
| 135 |
+
max_epochs = 0
|
| 136 |
+
max_steps = 20000
|
| 137 |
+
eval_frequency = 200
|
| 138 |
+
frozen_components = []
|
| 139 |
+
before_to_disk = null
|
| 140 |
+
annotating_components = []
|
| 141 |
+
|
| 142 |
+
[training.batcher]
|
| 143 |
+
@batchers = "spacy.batch_by_padded.v1"
|
| 144 |
+
discard_oversize = true
|
| 145 |
+
size = 2000
|
| 146 |
+
buffer = 256
|
| 147 |
+
get_length = null
|
| 148 |
+
|
| 149 |
+
[training.logger]
|
| 150 |
+
@loggers = "spacy.ConsoleLogger.v1"
|
| 151 |
+
progress_bar = false
|
| 152 |
+
|
| 153 |
+
[training.optimizer]
|
| 154 |
+
@optimizers = "Adam.v1"
|
| 155 |
+
beta1 = 0.9
|
| 156 |
+
beta2 = 0.999
|
| 157 |
+
L2_is_weight_decay = true
|
| 158 |
+
L2 = 0.01
|
| 159 |
+
grad_clip = 1.0
|
| 160 |
+
use_averages = false
|
| 161 |
+
eps = 0.00000001
|
| 162 |
+
|
| 163 |
+
[training.optimizer.learn_rate]
|
| 164 |
+
@schedules = "warmup_linear.v1"
|
| 165 |
+
warmup_steps = 250
|
| 166 |
+
total_steps = 20000
|
| 167 |
+
initial_rate = 0.00005
|
| 168 |
+
|
| 169 |
+
[training.score_weights]
|
| 170 |
+
tag_acc = 0.26
|
| 171 |
+
pos_acc = 0.12
|
| 172 |
+
morph_acc = 0.12
|
| 173 |
+
morph_per_feat = null
|
| 174 |
+
dep_uas = 0.12
|
| 175 |
+
dep_las = 0.12
|
| 176 |
+
dep_las_per_type = null
|
| 177 |
+
sents_p = null
|
| 178 |
+
sents_r = null
|
| 179 |
+
sents_f = 0.0
|
| 180 |
+
ents_f = 0.26
|
| 181 |
+
ents_p = 0.0
|
| 182 |
+
ents_r = 0.0
|
| 183 |
+
ents_per_type = null
|
| 184 |
+
|
| 185 |
+
[pretraining]
|
| 186 |
+
|
| 187 |
+
[initialize]
|
| 188 |
+
vectors = ${paths.vectors}
|
| 189 |
+
init_tok2vec = ${paths.init_tok2vec}
|
| 190 |
+
vocab_data = null
|
| 191 |
+
lookups = null
|
| 192 |
+
before_init = null
|
| 193 |
+
after_init = null
|
| 194 |
+
|
| 195 |
+
[initialize.components]
|
| 196 |
+
|
| 197 |
+
[initialize.tokenizer]
|
meta.json
ADDED
|
@@ -0,0 +1,650 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"lang":"nb",
|
| 3 |
+
"name":"nocy_trf",
|
| 4 |
+
"version":"0.0.1",
|
| 5 |
+
"description":"",
|
| 6 |
+
"author":"",
|
| 7 |
+
"email":"",
|
| 8 |
+
"url":"",
|
| 9 |
+
"license":"",
|
| 10 |
+
"spacy_version":">=3.1.1,<3.2.0",
|
| 11 |
+
"spacy_git_version":"ffaead8fe",
|
| 12 |
+
"vectors":{
|
| 13 |
+
"width":0,
|
| 14 |
+
"vectors":0,
|
| 15 |
+
"keys":0,
|
| 16 |
+
"name":null
|
| 17 |
+
},
|
| 18 |
+
"labels":{
|
| 19 |
+
"transformer":[
|
| 20 |
+
|
| 21 |
+
],
|
| 22 |
+
"tagger":[
|
| 23 |
+
"ADJ",
|
| 24 |
+
"ADP",
|
| 25 |
+
"ADV",
|
| 26 |
+
"AUX",
|
| 27 |
+
"CCONJ",
|
| 28 |
+
"DET",
|
| 29 |
+
"INTJ",
|
| 30 |
+
"NOUN",
|
| 31 |
+
"NUM",
|
| 32 |
+
"PART",
|
| 33 |
+
"PRON",
|
| 34 |
+
"PROPN",
|
| 35 |
+
"PUNCT",
|
| 36 |
+
"SCONJ",
|
| 37 |
+
"SYM",
|
| 38 |
+
"VERB",
|
| 39 |
+
"X"
|
| 40 |
+
],
|
| 41 |
+
"morphologizer":[
|
| 42 |
+
"Definite=Ind|Gender=Neut|Number=Sing|POS=NOUN",
|
| 43 |
+
"POS=CCONJ",
|
| 44 |
+
"Definite=Ind|Gender=Masc|Number=Sing|POS=NOUN",
|
| 45 |
+
"POS=SCONJ",
|
| 46 |
+
"Definite=Def|Gender=Masc|Number=Sing|POS=NOUN",
|
| 47 |
+
"Definite=Ind|Gender=Neut|Number=Plur|POS=NOUN",
|
| 48 |
+
"POS=PUNCT",
|
| 49 |
+
"Mood=Ind|POS=VERB|Tense=Past|VerbForm=Fin",
|
| 50 |
+
"POS=ADP",
|
| 51 |
+
"Gender=Masc|Number=Sing|POS=DET|PronType=Dem",
|
| 52 |
+
"Definite=Def|Degree=Pos|Number=Sing|POS=ADJ",
|
| 53 |
+
"POS=PROPN",
|
| 54 |
+
"POS=X",
|
| 55 |
+
"Mood=Ind|POS=VERB|Tense=Pres|VerbForm=Fin",
|
| 56 |
+
"Definite=Def|Gender=Neut|Number=Sing|POS=NOUN",
|
| 57 |
+
"POS=PRON|PronType=Rel",
|
| 58 |
+
"Mood=Ind|POS=AUX|Tense=Pres|VerbForm=Fin",
|
| 59 |
+
"Definite=Ind|Gender=Neut|Number=Sing|POS=ADJ|VerbForm=Part",
|
| 60 |
+
"Definite=Ind|Degree=Pos|Number=Sing|POS=ADJ",
|
| 61 |
+
"Definite=Ind|Gender=Fem|Number=Sing|POS=NOUN",
|
| 62 |
+
"Number=Plur|POS=ADJ|VerbForm=Part",
|
| 63 |
+
"Definite=Ind|Gender=Fem|Number=Plur|POS=NOUN",
|
| 64 |
+
"POS=ADV",
|
| 65 |
+
"Gender=Neut|Number=Sing|POS=PRON|Person=3|PronType=Prs",
|
| 66 |
+
"Definite=Ind|Number=Sing|POS=ADJ|VerbForm=Part",
|
| 67 |
+
"POS=VERB|VerbForm=Part",
|
| 68 |
+
"Definite=Ind|Gender=Masc|Number=Plur|POS=NOUN",
|
| 69 |
+
"Definite=Ind|Degree=Pos|Gender=Neut|Number=Sing|POS=ADJ",
|
| 70 |
+
"Degree=Pos|Number=Plur|POS=ADJ",
|
| 71 |
+
"NumType=Card|Number=Plur|POS=NUM",
|
| 72 |
+
"Definite=Def|Gender=Masc|Number=Plur|POS=NOUN",
|
| 73 |
+
"Case=Acc|POS=PRON|PronType=Prs|Reflex=Yes",
|
| 74 |
+
"Case=Gen|Definite=Ind|Gender=Neut|Number=Sing|POS=NOUN",
|
| 75 |
+
"POS=PART",
|
| 76 |
+
"POS=VERB|VerbForm=Inf",
|
| 77 |
+
"Case=Nom|Number=Plur|POS=PRON|Person=3|PronType=Prs",
|
| 78 |
+
"Mood=Ind|POS=AUX|Tense=Past|VerbForm=Fin",
|
| 79 |
+
"Gender=Fem|POS=PROPN",
|
| 80 |
+
"POS=NOUN",
|
| 81 |
+
"Gender=Masc|POS=PROPN",
|
| 82 |
+
"Gender=Neut|Number=Sing|POS=DET|PronType=Dem",
|
| 83 |
+
"Gender=Masc|Number=Sing|POS=DET|PronType=Art",
|
| 84 |
+
"Case=Gen|Definite=Def|Gender=Masc|Number=Sing|POS=NOUN",
|
| 85 |
+
"Abbr=Yes|POS=PROPN",
|
| 86 |
+
"POS=PART|Polarity=Neg",
|
| 87 |
+
"Number=Plur|POS=PRON|Poss=Yes|PronType=Prs",
|
| 88 |
+
"Case=Gen|Definite=Ind|Gender=Neut|Number=Plur|POS=NOUN",
|
| 89 |
+
"Case=Gen|POS=PROPN",
|
| 90 |
+
"Gender=Fem|Number=Sing|POS=DET|PronType=Dem",
|
| 91 |
+
"Gender=Masc|Number=Sing|POS=PRON|Poss=Yes|PronType=Prs",
|
| 92 |
+
"Definite=Def|Degree=Sup|POS=ADJ",
|
| 93 |
+
"Case=Gen|Gender=Fem|POS=PROPN",
|
| 94 |
+
"Number=Plur|POS=DET|PronType=Dem",
|
| 95 |
+
"Case=Gen|Definite=Def|Gender=Neut|Number=Sing|POS=NOUN",
|
| 96 |
+
"Definite=Ind|Degree=Sup|POS=ADJ",
|
| 97 |
+
"Definite=Def|Gender=Fem|Number=Plur|POS=NOUN",
|
| 98 |
+
"Gender=Neut|POS=PROPN",
|
| 99 |
+
"Number=Plur|POS=DET|PronType=Int",
|
| 100 |
+
"Definite=Def|Gender=Neut|Number=Plur|POS=NOUN",
|
| 101 |
+
"Definite=Def|POS=DET|PronType=Dem",
|
| 102 |
+
"Gender=Neut|Number=Sing|POS=DET|PronType=Art",
|
| 103 |
+
"Mood=Ind|POS=VERB|Tense=Pres|VerbForm=Fin|Voice=Pass",
|
| 104 |
+
"Abbr=Yes|Case=Gen|POS=PROPN",
|
| 105 |
+
"Animacy=Hum|Case=Nom|Gender=Masc|Number=Sing|POS=PRON|Person=3|PronType=Prs",
|
| 106 |
+
"Degree=Cmp|POS=ADJ",
|
| 107 |
+
"POS=ADJ|VerbForm=Part",
|
| 108 |
+
"Gender=Neut|Number=Sing|POS=PRON|Poss=Yes|PronType=Prs",
|
| 109 |
+
"Abbr=Yes|POS=ADP",
|
| 110 |
+
"Definite=Ind|Gender=Neut|Number=Sing|POS=DET|PronType=Prs",
|
| 111 |
+
"Case=Gen|Definite=Def|Gender=Neut|Number=Plur|POS=NOUN",
|
| 112 |
+
"POS=AUX|VerbForm=Part",
|
| 113 |
+
"POS=PRON|PronType=Int",
|
| 114 |
+
"Gender=Fem|Number=Sing|POS=PRON|Poss=Yes|PronType=Prs",
|
| 115 |
+
"Number=Plur|POS=PRON|Person=3|PronType=Ind,Prs",
|
| 116 |
+
"Number=Plur|POS=DET|PronType=Ind",
|
| 117 |
+
"Degree=Pos|POS=ADJ",
|
| 118 |
+
"Animacy=Hum|Case=Nom|Number=Plur|POS=PRON|Person=1|PronType=Prs",
|
| 119 |
+
"POS=VERB|VerbForm=Inf|Voice=Pass",
|
| 120 |
+
"Definite=Ind|Gender=Fem|Number=Sing|POS=DET|PronType=Dem",
|
| 121 |
+
"Gender=Neut|Number=Sing|POS=DET|PronType=Ind",
|
| 122 |
+
"Animacy=Hum|Case=Acc|Gender=Masc|Number=Sing|POS=PRON|Person=3|PronType=Prs",
|
| 123 |
+
"Animacy=Hum|Case=Nom|Number=Sing|POS=PRON|Person=1|PronType=Prs",
|
| 124 |
+
"Number=Plur|POS=DET|Polarity=Neg|PronType=Neg",
|
| 125 |
+
"NumType=Card|POS=NUM",
|
| 126 |
+
"Gender=Masc|Number=Sing|POS=DET|PronType=Ind",
|
| 127 |
+
"POS=DET|PronType=Prs",
|
| 128 |
+
"Gender=Fem|Number=Sing|POS=DET|PronType=Ind",
|
| 129 |
+
"Case=Gen|Gender=Neut|POS=PROPN",
|
| 130 |
+
"Gender=Masc|Number=Sing|POS=DET|Polarity=Neg|PronType=Neg",
|
| 131 |
+
"Definite=Def|Number=Sing|POS=ADJ|VerbForm=Part",
|
| 132 |
+
"Gender=Fem,Masc|Number=Sing|POS=PRON|Person=3|PronType=Prs",
|
| 133 |
+
"POS=AUX|VerbForm=Inf",
|
| 134 |
+
"Case=Acc|Number=Plur|POS=PRON|Person=3|PronType=Prs",
|
| 135 |
+
"Case=Gen|Degree=Pos|Number=Plur|POS=ADJ",
|
| 136 |
+
"Number=Plur|POS=DET|PronType=Tot",
|
| 137 |
+
"Case=Gen|Gender=Masc|Number=Sing|POS=DET|PronType=Dem",
|
| 138 |
+
"Number=Plur|POS=DET|PronType=Prs",
|
| 139 |
+
"POS=SYM",
|
| 140 |
+
"Gender=Neut|NumType=Card|Number=Sing|POS=NUM",
|
| 141 |
+
"Animacy=Hum|Case=Nom|Number=Sing|POS=PRON|PronType=Prs",
|
| 142 |
+
"Definite=Ind|Gender=Masc|Number=Sing|POS=DET|PronType=Prs",
|
| 143 |
+
"Case=Gen|Definite=Ind|Gender=Masc|Number=Sing|POS=NOUN",
|
| 144 |
+
"Abbr=Yes|POS=ADV",
|
| 145 |
+
"Definite=Ind|Gender=Neut|Number=Sing|POS=DET|PronType=Dem",
|
| 146 |
+
"Gender=Masc|Number=Sing|POS=DET|PronType=Tot",
|
| 147 |
+
"Definite=Def|POS=DET|PronType=Prs",
|
| 148 |
+
"Animacy=Hum|Case=Nom|Gender=Fem|Number=Sing|POS=PRON|Person=3|PronType=Prs",
|
| 149 |
+
"Gender=Neut|POS=NOUN",
|
| 150 |
+
"Gender=Neut|Number=Sing|POS=DET|PronType=Int",
|
| 151 |
+
"Definite=Def|NumType=Card|POS=NUM",
|
| 152 |
+
"Mood=Imp|POS=VERB|VerbForm=Fin",
|
| 153 |
+
"Definite=Ind|Number=Plur|POS=NOUN",
|
| 154 |
+
"Gender=Neut|Number=Sing|POS=DET|PronType=Tot",
|
| 155 |
+
"Gender=Fem|Number=Sing|POS=DET|PronType=Tot",
|
| 156 |
+
"Animacy=Hum|Case=Acc|Number=Plur|POS=PRON|Person=1|PronType=Prs",
|
| 157 |
+
"Gender=Fem,Masc|Number=Sing|POS=PRON|Person=3|Polarity=Neg|PronType=Neg,Prs",
|
| 158 |
+
"Number=Plur|POS=PRON|Person=3|Polarity=Neg|PronType=Neg,Prs",
|
| 159 |
+
"Definite=Def|NumType=Card|Number=Sing|POS=NUM",
|
| 160 |
+
"Gender=Masc|NumType=Card|Number=Sing|POS=NUM",
|
| 161 |
+
"Definite=Ind|Gender=Masc|Number=Sing|POS=DET|PronType=Dem",
|
| 162 |
+
"Case=Gen|Definite=Def|Gender=Fem|Number=Plur|POS=NOUN",
|
| 163 |
+
"Case=Gen|Gender=Neut|Number=Sing|POS=DET|PronType=Dem",
|
| 164 |
+
"Animacy=Hum|Number=Sing|POS=PRON|PronType=Art,Prs",
|
| 165 |
+
"Mood=Imp|POS=AUX|VerbForm=Fin",
|
| 166 |
+
"Number=Plur|POS=PRON|Person=3|PronType=Prs,Tot",
|
| 167 |
+
"Number=Plur|POS=ADJ",
|
| 168 |
+
"Gender=Masc|POS=NOUN",
|
| 169 |
+
"Abbr=Yes|POS=NOUN",
|
| 170 |
+
"Case=Gen|Definite=Ind|Gender=Masc|Number=Plur|POS=NOUN",
|
| 171 |
+
"Gender=Neut|Number=Sing|POS=PRON|Person=3|PronType=Ind,Prs",
|
| 172 |
+
"POS=INTJ",
|
| 173 |
+
"Animacy=Hum|Case=Nom|Number=Sing|POS=PRON|Person=2|PronType=Prs",
|
| 174 |
+
"Animacy=Hum|Case=Acc|Number=Sing|POS=PRON|Person=1|PronType=Prs",
|
| 175 |
+
"Case=Gen|Definite=Def|Gender=Masc|Number=Plur|POS=NOUN",
|
| 176 |
+
"POS=ADJ",
|
| 177 |
+
"Animacy=Hum|Case=Acc|Gender=Fem|Number=Sing|POS=PRON|Person=3|PronType=Prs",
|
| 178 |
+
"Animacy=Hum|Case=Acc|Number=Sing|POS=PRON|Person=2|PronType=Prs",
|
| 179 |
+
"Definite=Def|Gender=Fem|Number=Sing|POS=NOUN",
|
| 180 |
+
"Number=Sing|POS=PRON|Polarity=Neg|PronType=Neg",
|
| 181 |
+
"Case=Gen|POS=NOUN",
|
| 182 |
+
"Definite=Ind|Number=Sing|POS=ADJ",
|
| 183 |
+
"Case=Gen|Gender=Masc|POS=PROPN",
|
| 184 |
+
"Animacy=Hum|Number=Plur|POS=PRON|PronType=Rcp",
|
| 185 |
+
"Case=Gen|Definite=Ind|Gender=Fem|Number=Sing|POS=NOUN",
|
| 186 |
+
"Number=Plur|POS=PRON|Person=3|PronType=Prs",
|
| 187 |
+
"Gender=Fem,Masc|Number=Sing|POS=PRON|Person=3|PronType=Ind,Prs",
|
| 188 |
+
"Definite=Ind|Gender=Fem|Number=Sing|POS=DET|PronType=Prs",
|
| 189 |
+
"Case=Gen|Definite=Def|Gender=Fem|Number=Sing|POS=NOUN",
|
| 190 |
+
"Gender=Fem|Number=Sing|POS=DET|PronType=Art",
|
| 191 |
+
"Case=Gen|Definite=Def|Degree=Pos|Number=Sing|POS=ADJ",
|
| 192 |
+
"Gender=Masc|Number=Sing|POS=DET|PronType=Int",
|
| 193 |
+
"NumType=Card|Number=Sing|POS=NUM",
|
| 194 |
+
"Animacy=Hum|Case=Acc|Number=Plur|POS=PRON|Person=2|PronType=Prs",
|
| 195 |
+
"Animacy=Hum|Case=Nom|Number=Plur|POS=PRON|Person=2|PronType=Prs",
|
| 196 |
+
"Case=Gen|Definite=Ind|Degree=Pos|Gender=Neut|Number=Sing|POS=ADJ",
|
| 197 |
+
"Degree=Sup|POS=ADJ",
|
| 198 |
+
"Animacy=Hum|POS=PRON|PronType=Int",
|
| 199 |
+
"POS=DET|PronType=Ind",
|
| 200 |
+
"Definite=Def|Number=Sing|POS=DET|PronType=Dem",
|
| 201 |
+
"Gender=Fem|POS=NOUN",
|
| 202 |
+
"Case=Gen|Number=Plur|POS=DET|PronType=Dem",
|
| 203 |
+
"Gender=Fem,Masc|Number=Sing|POS=PRON|Person=3|PronType=Prs,Tot",
|
| 204 |
+
"Case=Gen|Definite=Ind|Gender=Fem|Number=Plur|POS=NOUN",
|
| 205 |
+
"Gender=Neut|Number=Sing|POS=DET|Polarity=Neg|PronType=Neg",
|
| 206 |
+
"Number=Plur|POS=NOUN",
|
| 207 |
+
"Case=Gen|Definite=Ind|Degree=Pos|Number=Sing|POS=ADJ",
|
| 208 |
+
"Definite=Ind|Number=Sing|POS=VERB|VerbForm=Part",
|
| 209 |
+
"Case=Gen|Definite=Def|Number=Sing|POS=ADJ|VerbForm=Part",
|
| 210 |
+
"Mood=Ind|POS=VERB|Tense=Past|VerbForm=Fin|Voice=Pass",
|
| 211 |
+
"Gender=Neut|Number=Sing|POS=DET|PronType=Dem,Ind",
|
| 212 |
+
"Animacy=Hum|POS=PRON|Poss=Yes|PronType=Int",
|
| 213 |
+
"Abbr=Yes|POS=ADJ",
|
| 214 |
+
"Case=Gen|Gender=Masc|Number=Sing|POS=DET|PronType=Art",
|
| 215 |
+
"Abbr=Yes|Definite=Def,Ind|Gender=Masc|Number=Sing|POS=NOUN",
|
| 216 |
+
"POS=PRON|PronType=Prs",
|
| 217 |
+
"Case=Gen|Gender=Fem|Number=Sing|POS=DET|PronType=Dem",
|
| 218 |
+
"Number=Plur|POS=PRON|Poss=Yes|PronType=Rcp",
|
| 219 |
+
"Definite=Ind|Degree=Pos|POS=ADJ",
|
| 220 |
+
"Number=Plur|POS=DET|PronType=Art",
|
| 221 |
+
"Case=Gen|NumType=Card|Number=Plur|POS=NUM",
|
| 222 |
+
"Abbr=Yes|Definite=Def,Ind|Gender=Neut|Number=Plur,Sing|POS=NOUN",
|
| 223 |
+
"Case=Gen|Number=Plur|POS=DET|PronType=Tot",
|
| 224 |
+
"Abbr=Yes|Definite=Def,Ind|Gender=Masc|Number=Plur,Sing|POS=NOUN",
|
| 225 |
+
"Gender=Fem|Number=Sing|POS=DET|PronType=Int",
|
| 226 |
+
"Definite=Ind|Gender=Neut|Number=Sing|POS=ADJ",
|
| 227 |
+
"Case=Gen|Definite=Ind|Gender=Masc|Number=Sing|POS=DET|PronType=Dem",
|
| 228 |
+
"Gender=Fem|Number=Sing|POS=DET|PronType=Prs",
|
| 229 |
+
"Animacy=Hum|Case=Gen,Nom|Number=Sing|POS=PRON|PronType=Art,Prs",
|
| 230 |
+
"Definite=Def|Degree=Pos|Gender=Masc|Number=Sing|POS=ADJ",
|
| 231 |
+
"Animacy=Hum|Case=Gen|Number=Sing|POS=PRON|PronType=Art,Prs",
|
| 232 |
+
"Gender=Fem|NumType=Card|Number=Sing|POS=NUM",
|
| 233 |
+
"Definite=Ind|Gender=Masc|POS=NOUN",
|
| 234 |
+
"Definite=Def|Number=Plur|POS=NOUN",
|
| 235 |
+
"Number=Sing|POS=ADJ|VerbForm=Part",
|
| 236 |
+
"Definite=Ind|Gender=Masc|Number=Sing|POS=ADJ|VerbForm=Part",
|
| 237 |
+
"Abbr=Yes|Gender=Masc|POS=NOUN",
|
| 238 |
+
"Abbr=Yes|Case=Gen|POS=NOUN",
|
| 239 |
+
"Abbr=Yes|Mood=Ind|POS=VERB|Tense=Pres|VerbForm=Fin",
|
| 240 |
+
"Abbr=Yes|Degree=Pos|POS=ADJ",
|
| 241 |
+
"Case=Gen|Gender=Fem|POS=NOUN",
|
| 242 |
+
"Case=Gen|Degree=Cmp|POS=ADJ",
|
| 243 |
+
"Definite=Ind|Degree=Pos|Gender=Masc|Number=Sing|POS=ADJ",
|
| 244 |
+
"Gender=Masc|Number=Sing|POS=NOUN"
|
| 245 |
+
],
|
| 246 |
+
"parser":[
|
| 247 |
+
"ROOT",
|
| 248 |
+
"acl",
|
| 249 |
+
"acl:cleft",
|
| 250 |
+
"acl:relcl",
|
| 251 |
+
"advcl",
|
| 252 |
+
"advmod",
|
| 253 |
+
"amod",
|
| 254 |
+
"appos",
|
| 255 |
+
"aux",
|
| 256 |
+
"aux:pass",
|
| 257 |
+
"case",
|
| 258 |
+
"cc",
|
| 259 |
+
"ccomp",
|
| 260 |
+
"compound",
|
| 261 |
+
"compound:prt",
|
| 262 |
+
"conj",
|
| 263 |
+
"cop",
|
| 264 |
+
"csubj",
|
| 265 |
+
"dep",
|
| 266 |
+
"det",
|
| 267 |
+
"discourse",
|
| 268 |
+
"expl",
|
| 269 |
+
"flat:foreign",
|
| 270 |
+
"flat:name",
|
| 271 |
+
"iobj",
|
| 272 |
+
"mark",
|
| 273 |
+
"nmod",
|
| 274 |
+
"nsubj",
|
| 275 |
+
"nsubj:pass",
|
| 276 |
+
"nummod",
|
| 277 |
+
"obj",
|
| 278 |
+
"obl",
|
| 279 |
+
"orphan",
|
| 280 |
+
"parataxis",
|
| 281 |
+
"punct",
|
| 282 |
+
"xcomp"
|
| 283 |
+
],
|
| 284 |
+
"ner":[
|
| 285 |
+
"DRV",
|
| 286 |
+
"EVT",
|
| 287 |
+
"GPE_LOC",
|
| 288 |
+
"GPE_ORG",
|
| 289 |
+
"LOC",
|
| 290 |
+
"MISC",
|
| 291 |
+
"ORG",
|
| 292 |
+
"PER",
|
| 293 |
+
"PROD"
|
| 294 |
+
]
|
| 295 |
+
},
|
| 296 |
+
"pipeline":[
|
| 297 |
+
"transformer",
|
| 298 |
+
"tagger",
|
| 299 |
+
"morphologizer",
|
| 300 |
+
"parser",
|
| 301 |
+
"ner"
|
| 302 |
+
],
|
| 303 |
+
"components":[
|
| 304 |
+
"transformer",
|
| 305 |
+
"tagger",
|
| 306 |
+
"morphologizer",
|
| 307 |
+
"parser",
|
| 308 |
+
"ner"
|
| 309 |
+
],
|
| 310 |
+
"disabled":[
|
| 311 |
+
|
| 312 |
+
],
|
| 313 |
+
"_sourced_vectors_hashes":{
|
| 314 |
+
|
| 315 |
+
},
|
| 316 |
+
"performance":{
|
| 317 |
+
"tag_acc":0.987973053,
|
| 318 |
+
"pos_acc":0.9876975216,
|
| 319 |
+
"morph_acc":0.9800788031,
|
| 320 |
+
"morph_per_feat":{
|
| 321 |
+
"Definite":{
|
| 322 |
+
"p":0.9923585766,
|
| 323 |
+
"r":0.9868435976,
|
| 324 |
+
"f":0.9895934035
|
| 325 |
+
},
|
| 326 |
+
"Gender":{
|
| 327 |
+
"p":0.9772163966,
|
| 328 |
+
"r":0.9723038983,
|
| 329 |
+
"f":0.9747539581
|
| 330 |
+
},
|
| 331 |
+
"Number":{
|
| 332 |
+
"p":0.9884938782,
|
| 333 |
+
"r":0.9819034361,
|
| 334 |
+
"f":0.9851876355
|
| 335 |
+
},
|
| 336 |
+
"Mood":{
|
| 337 |
+
"p":0.9984939759,
|
| 338 |
+
"r":0.9947486872,
|
| 339 |
+
"f":0.9966178129
|
| 340 |
+
},
|
| 341 |
+
"Tense":{
|
| 342 |
+
"p":0.9984848485,
|
| 343 |
+
"r":0.9957189625,
|
| 344 |
+
"f":0.9970999874
|
| 345 |
+
},
|
| 346 |
+
"VerbForm":{
|
| 347 |
+
"p":0.9921683798,
|
| 348 |
+
"r":0.9910365059,
|
| 349 |
+
"f":0.9916021199
|
| 350 |
+
},
|
| 351 |
+
"Degree":{
|
| 352 |
+
"p":0.9862258953,
|
| 353 |
+
"r":0.9838543456,
|
| 354 |
+
"f":0.985038693
|
| 355 |
+
},
|
| 356 |
+
"PronType":{
|
| 357 |
+
"p":0.9958918919,
|
| 358 |
+
"r":0.9935289042,
|
| 359 |
+
"f":0.9947089947
|
| 360 |
+
},
|
| 361 |
+
"Poss":{
|
| 362 |
+
"p":1.0,
|
| 363 |
+
"r":0.9920948617,
|
| 364 |
+
"f":0.996031746
|
| 365 |
+
},
|
| 366 |
+
"Case":{
|
| 367 |
+
"p":0.9977814753,
|
| 368 |
+
"r":0.996124031,
|
| 369 |
+
"f":0.9969520643
|
| 370 |
+
},
|
| 371 |
+
"Reflex":{
|
| 372 |
+
"p":1.0,
|
| 373 |
+
"r":1.0,
|
| 374 |
+
"f":1.0
|
| 375 |
+
},
|
| 376 |
+
"NumType":{
|
| 377 |
+
"p":0.9955156951,
|
| 378 |
+
"r":0.9135802469,
|
| 379 |
+
"f":0.9527896996
|
| 380 |
+
},
|
| 381 |
+
"Polarity":{
|
| 382 |
+
"p":1.0,
|
| 383 |
+
"r":1.0,
|
| 384 |
+
"f":1.0
|
| 385 |
+
},
|
| 386 |
+
"Person":{
|
| 387 |
+
"p":0.9966666667,
|
| 388 |
+
"r":0.9933554817,
|
| 389 |
+
"f":0.9950083195
|
| 390 |
+
},
|
| 391 |
+
"Animacy":{
|
| 392 |
+
"p":0.997440273,
|
| 393 |
+
"r":0.9957410562,
|
| 394 |
+
"f":0.9965899403
|
| 395 |
+
},
|
| 396 |
+
"Voice":{
|
| 397 |
+
"p":0.9440559441,
|
| 398 |
+
"r":0.9782608696,
|
| 399 |
+
"f":0.9608540925
|
| 400 |
+
},
|
| 401 |
+
"Abbr":{
|
| 402 |
+
"p":0.9803921569,
|
| 403 |
+
"r":0.9375,
|
| 404 |
+
"f":0.9584664537
|
| 405 |
+
}
|
| 406 |
+
},
|
| 407 |
+
"dep_uas":0.9433838463,
|
| 408 |
+
"dep_las":0.9252015247,
|
| 409 |
+
"dep_las_per_type":{
|
| 410 |
+
"nmod":{
|
| 411 |
+
"p":0.8895348837,
|
| 412 |
+
"r":0.8789495281,
|
| 413 |
+
"f":0.8842105263
|
| 414 |
+
},
|
| 415 |
+
"nsubj":{
|
| 416 |
+
"p":0.9620056057,
|
| 417 |
+
"r":0.9522194821,
|
| 418 |
+
"f":0.957087529
|
| 419 |
+
},
|
| 420 |
+
"flat:name":{
|
| 421 |
+
"p":0.9447949527,
|
| 422 |
+
"r":0.9661290323,
|
| 423 |
+
"f":0.9553429027
|
| 424 |
+
},
|
| 425 |
+
"root":{
|
| 426 |
+
"p":0.9606462303,
|
| 427 |
+
"r":0.9622406639,
|
| 428 |
+
"f":0.9614427861
|
| 429 |
+
},
|
| 430 |
+
"advmod":{
|
| 431 |
+
"p":0.8967339097,
|
| 432 |
+
"r":0.8958733205,
|
| 433 |
+
"f":0.8963034085
|
| 434 |
+
},
|
| 435 |
+
"mark":{
|
| 436 |
+
"p":0.956401766,
|
| 437 |
+
"r":0.9638487208,
|
| 438 |
+
"f":0.9601108033
|
| 439 |
+
},
|
| 440 |
+
"advcl":{
|
| 441 |
+
"p":0.8321799308,
|
| 442 |
+
"r":0.8250428816,
|
| 443 |
+
"f":0.8285960379
|
| 444 |
+
},
|
| 445 |
+
"obj":{
|
| 446 |
+
"p":0.963490099,
|
| 447 |
+
"r":0.9658808933,
|
| 448 |
+
"f":0.9646840149
|
| 449 |
+
},
|
| 450 |
+
"case":{
|
| 451 |
+
"p":0.9759225334,
|
| 452 |
+
"r":0.9623225806,
|
| 453 |
+
"f":0.9690748441
|
| 454 |
+
},
|
| 455 |
+
"det":{
|
| 456 |
+
"p":0.9866666667,
|
| 457 |
+
"r":0.9835443038,
|
| 458 |
+
"f":0.9851030111
|
| 459 |
+
},
|
| 460 |
+
"obl":{
|
| 461 |
+
"p":0.8605922551,
|
| 462 |
+
"r":0.8547511312,
|
| 463 |
+
"f":0.857661748
|
| 464 |
+
},
|
| 465 |
+
"aux":{
|
| 466 |
+
"p":0.9755434783,
|
| 467 |
+
"r":0.9746606335,
|
| 468 |
+
"f":0.975101856
|
| 469 |
+
},
|
| 470 |
+
"acl:relcl":{
|
| 471 |
+
"p":0.8778280543,
|
| 472 |
+
"r":0.8758465011,
|
| 473 |
+
"f":0.8768361582
|
| 474 |
+
},
|
| 475 |
+
"iobj":{
|
| 476 |
+
"p":0.8850574713,
|
| 477 |
+
"r":0.875,
|
| 478 |
+
"f":0.88
|
| 479 |
+
},
|
| 480 |
+
"xcomp":{
|
| 481 |
+
"p":0.825,
|
| 482 |
+
"r":0.825,
|
| 483 |
+
"f":0.825
|
| 484 |
+
},
|
| 485 |
+
"cc":{
|
| 486 |
+
"p":0.9675174014,
|
| 487 |
+
"r":0.9645335389,
|
| 488 |
+
"f":0.966023166
|
| 489 |
+
},
|
| 490 |
+
"conj":{
|
| 491 |
+
"p":0.859114016,
|
| 492 |
+
"r":0.859114016,
|
| 493 |
+
"f":0.859114016
|
| 494 |
+
},
|
| 495 |
+
"amod":{
|
| 496 |
+
"p":0.9679758308,
|
| 497 |
+
"r":0.9703210176,
|
| 498 |
+
"f":0.9691470054
|
| 499 |
+
},
|
| 500 |
+
"nummod":{
|
| 501 |
+
"p":0.955465587,
|
| 502 |
+
"r":0.9632653061,
|
| 503 |
+
"f":0.9593495935
|
| 504 |
+
},
|
| 505 |
+
"compound:prt":{
|
| 506 |
+
"p":0.9122137405,
|
| 507 |
+
"r":0.8628158845,
|
| 508 |
+
"f":0.8868274583
|
| 509 |
+
},
|
| 510 |
+
"cop":{
|
| 511 |
+
"p":0.9363207547,
|
| 512 |
+
"r":0.9463647199,
|
| 513 |
+
"f":0.9413159455
|
| 514 |
+
},
|
| 515 |
+
"appos":{
|
| 516 |
+
"p":0.4938271605,
|
| 517 |
+
"r":0.4,
|
| 518 |
+
"f":0.4419889503
|
| 519 |
+
},
|
| 520 |
+
"ccomp":{
|
| 521 |
+
"p":0.8897338403,
|
| 522 |
+
"r":0.9212598425,
|
| 523 |
+
"f":0.9052224371
|
| 524 |
+
},
|
| 525 |
+
"dep":{
|
| 526 |
+
"p":0.0,
|
| 527 |
+
"r":0.0,
|
| 528 |
+
"f":0.0
|
| 529 |
+
},
|
| 530 |
+
"acl":{
|
| 531 |
+
"p":0.7833333333,
|
| 532 |
+
"r":0.7580645161,
|
| 533 |
+
"f":0.7704918033
|
| 534 |
+
},
|
| 535 |
+
"expl":{
|
| 536 |
+
"p":0.8377659574,
|
| 537 |
+
"r":0.8513513514,
|
| 538 |
+
"f":0.8445040214
|
| 539 |
+
},
|
| 540 |
+
"csubj":{
|
| 541 |
+
"p":0.8201438849,
|
| 542 |
+
"r":0.8321167883,
|
| 543 |
+
"f":0.8260869565
|
| 544 |
+
},
|
| 545 |
+
"nsubj:pass":{
|
| 546 |
+
"p":0.9321266968,
|
| 547 |
+
"r":0.9537037037,
|
| 548 |
+
"f":0.942791762
|
| 549 |
+
},
|
| 550 |
+
"acl:cleft":{
|
| 551 |
+
"p":0.5806451613,
|
| 552 |
+
"r":0.6666666667,
|
| 553 |
+
"f":0.6206896552
|
| 554 |
+
},
|
| 555 |
+
"orphan":{
|
| 556 |
+
"p":0.5555555556,
|
| 557 |
+
"r":0.1923076923,
|
| 558 |
+
"f":0.2857142857
|
| 559 |
+
},
|
| 560 |
+
"aux:pass":{
|
| 561 |
+
"p":0.9674796748,
|
| 562 |
+
"r":0.9916666667,
|
| 563 |
+
"f":0.9794238683
|
| 564 |
+
},
|
| 565 |
+
"goeswith":{
|
| 566 |
+
"p":0.0,
|
| 567 |
+
"r":0.0,
|
| 568 |
+
"f":0.0
|
| 569 |
+
},
|
| 570 |
+
"parataxis":{
|
| 571 |
+
"p":0.9350649351,
|
| 572 |
+
"r":0.7659574468,
|
| 573 |
+
"f":0.8421052632
|
| 574 |
+
},
|
| 575 |
+
"compound":{
|
| 576 |
+
"p":0.8928571429,
|
| 577 |
+
"r":0.5319148936,
|
| 578 |
+
"f":0.6666666667
|
| 579 |
+
},
|
| 580 |
+
"flat:foreign":{
|
| 581 |
+
"p":0.6486486486,
|
| 582 |
+
"r":0.7741935484,
|
| 583 |
+
"f":0.7058823529
|
| 584 |
+
},
|
| 585 |
+
"discourse":{
|
| 586 |
+
"p":0.8461538462,
|
| 587 |
+
"r":0.4782608696,
|
| 588 |
+
"f":0.6111111111
|
| 589 |
+
},
|
| 590 |
+
"csubj:pass":{
|
| 591 |
+
"p":0.0,
|
| 592 |
+
"r":0.0,
|
| 593 |
+
"f":0.0
|
| 594 |
+
}
|
| 595 |
+
},
|
| 596 |
+
"sents_p":0.9679276316,
|
| 597 |
+
"sents_r":0.9767634855,
|
| 598 |
+
"sents_f":0.9723254853,
|
| 599 |
+
"ents_f":0.9045790251,
|
| 600 |
+
"ents_p":0.9021803182,
|
| 601 |
+
"ents_r":0.9069905213,
|
| 602 |
+
"ents_per_type":{
|
| 603 |
+
"PER":{
|
| 604 |
+
"p":0.9689542484,
|
| 605 |
+
"r":0.9705400982,
|
| 606 |
+
"f":0.9697465249
|
| 607 |
+
},
|
| 608 |
+
"PROD":{
|
| 609 |
+
"p":0.82,
|
| 610 |
+
"r":0.7592592593,
|
| 611 |
+
"f":0.7884615385
|
| 612 |
+
},
|
| 613 |
+
"GPE_LOC":{
|
| 614 |
+
"p":0.8935361217,
|
| 615 |
+
"r":0.9073359073,
|
| 616 |
+
"f":0.9003831418
|
| 617 |
+
},
|
| 618 |
+
"ORG":{
|
| 619 |
+
"p":0.9019607843,
|
| 620 |
+
"r":0.9108910891,
|
| 621 |
+
"f":0.9064039409
|
| 622 |
+
},
|
| 623 |
+
"LOC":{
|
| 624 |
+
"p":0.7894736842,
|
| 625 |
+
"r":0.8256880734,
|
| 626 |
+
"f":0.8071748879
|
| 627 |
+
},
|
| 628 |
+
"DRV":{
|
| 629 |
+
"p":0.8765432099,
|
| 630 |
+
"r":0.8987341772,
|
| 631 |
+
"f":0.8875
|
| 632 |
+
},
|
| 633 |
+
"EVT":{
|
| 634 |
+
"p":0.5454545455,
|
| 635 |
+
"r":0.6666666667,
|
| 636 |
+
"f":0.6
|
| 637 |
+
},
|
| 638 |
+
"GPE_ORG":{
|
| 639 |
+
"p":0.775862069,
|
| 640 |
+
"r":0.8181818182,
|
| 641 |
+
"f":0.796460177
|
| 642 |
+
}
|
| 643 |
+
},
|
| 644 |
+
"transformer_loss":14326.7577098147,
|
| 645 |
+
"tagger_loss":879.5400330358,
|
| 646 |
+
"morphologizer_loss":1057.7366806136,
|
| 647 |
+
"parser_loss":18286.3117342454,
|
| 648 |
+
"ner_loss":819.4389321774
|
| 649 |
+
}
|
| 650 |
+
}
|
morphologizer/cfg
ADDED
|
@@ -0,0 +1,412 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"labels_morph":{
|
| 3 |
+
"Definite=Ind|Gender=Neut|Number=Sing|POS=NOUN":"Definite=Ind|Gender=Neut|Number=Sing",
|
| 4 |
+
"POS=CCONJ":"",
|
| 5 |
+
"Definite=Ind|Gender=Masc|Number=Sing|POS=NOUN":"Definite=Ind|Gender=Masc|Number=Sing",
|
| 6 |
+
"POS=SCONJ":"",
|
| 7 |
+
"Definite=Def|Gender=Masc|Number=Sing|POS=NOUN":"Definite=Def|Gender=Masc|Number=Sing",
|
| 8 |
+
"Definite=Ind|Gender=Neut|Number=Plur|POS=NOUN":"Definite=Ind|Gender=Neut|Number=Plur",
|
| 9 |
+
"POS=PUNCT":"",
|
| 10 |
+
"Mood=Ind|POS=VERB|Tense=Past|VerbForm=Fin":"Mood=Ind|Tense=Past|VerbForm=Fin",
|
| 11 |
+
"POS=ADP":"",
|
| 12 |
+
"Gender=Masc|Number=Sing|POS=DET|PronType=Dem":"Gender=Masc|Number=Sing|PronType=Dem",
|
| 13 |
+
"Definite=Def|Degree=Pos|Number=Sing|POS=ADJ":"Definite=Def|Degree=Pos|Number=Sing",
|
| 14 |
+
"POS=PROPN":"",
|
| 15 |
+
"POS=X":"",
|
| 16 |
+
"Mood=Ind|POS=VERB|Tense=Pres|VerbForm=Fin":"Mood=Ind|Tense=Pres|VerbForm=Fin",
|
| 17 |
+
"Definite=Def|Gender=Neut|Number=Sing|POS=NOUN":"Definite=Def|Gender=Neut|Number=Sing",
|
| 18 |
+
"POS=PRON|PronType=Rel":"PronType=Rel",
|
| 19 |
+
"Mood=Ind|POS=AUX|Tense=Pres|VerbForm=Fin":"Mood=Ind|Tense=Pres|VerbForm=Fin",
|
| 20 |
+
"Definite=Ind|Gender=Neut|Number=Sing|POS=ADJ|VerbForm=Part":"Definite=Ind|Gender=Neut|Number=Sing|VerbForm=Part",
|
| 21 |
+
"Definite=Ind|Degree=Pos|Number=Sing|POS=ADJ":"Definite=Ind|Degree=Pos|Number=Sing",
|
| 22 |
+
"Definite=Ind|Gender=Fem|Number=Sing|POS=NOUN":"Definite=Ind|Gender=Fem|Number=Sing",
|
| 23 |
+
"Number=Plur|POS=ADJ|VerbForm=Part":"Number=Plur|VerbForm=Part",
|
| 24 |
+
"Definite=Ind|Gender=Fem|Number=Plur|POS=NOUN":"Definite=Ind|Gender=Fem|Number=Plur",
|
| 25 |
+
"POS=ADV":"",
|
| 26 |
+
"Gender=Neut|Number=Sing|POS=PRON|Person=3|PronType=Prs":"Gender=Neut|Number=Sing|Person=3|PronType=Prs",
|
| 27 |
+
"Definite=Ind|Number=Sing|POS=ADJ|VerbForm=Part":"Definite=Ind|Number=Sing|VerbForm=Part",
|
| 28 |
+
"POS=VERB|VerbForm=Part":"VerbForm=Part",
|
| 29 |
+
"Definite=Ind|Gender=Masc|Number=Plur|POS=NOUN":"Definite=Ind|Gender=Masc|Number=Plur",
|
| 30 |
+
"Definite=Ind|Degree=Pos|Gender=Neut|Number=Sing|POS=ADJ":"Definite=Ind|Degree=Pos|Gender=Neut|Number=Sing",
|
| 31 |
+
"Degree=Pos|Number=Plur|POS=ADJ":"Degree=Pos|Number=Plur",
|
| 32 |
+
"NumType=Card|Number=Plur|POS=NUM":"NumType=Card|Number=Plur",
|
| 33 |
+
"Definite=Def|Gender=Masc|Number=Plur|POS=NOUN":"Definite=Def|Gender=Masc|Number=Plur",
|
| 34 |
+
"Case=Acc|POS=PRON|PronType=Prs|Reflex=Yes":"Case=Acc|PronType=Prs|Reflex=Yes",
|
| 35 |
+
"Case=Gen|Definite=Ind|Gender=Neut|Number=Sing|POS=NOUN":"Case=Gen|Definite=Ind|Gender=Neut|Number=Sing",
|
| 36 |
+
"POS=PART":"",
|
| 37 |
+
"POS=VERB|VerbForm=Inf":"VerbForm=Inf",
|
| 38 |
+
"Case=Nom|Number=Plur|POS=PRON|Person=3|PronType=Prs":"Case=Nom|Number=Plur|Person=3|PronType=Prs",
|
| 39 |
+
"Mood=Ind|POS=AUX|Tense=Past|VerbForm=Fin":"Mood=Ind|Tense=Past|VerbForm=Fin",
|
| 40 |
+
"Gender=Fem|POS=PROPN":"Gender=Fem",
|
| 41 |
+
"POS=NOUN":"",
|
| 42 |
+
"Gender=Masc|POS=PROPN":"Gender=Masc",
|
| 43 |
+
"Gender=Neut|Number=Sing|POS=DET|PronType=Dem":"Gender=Neut|Number=Sing|PronType=Dem",
|
| 44 |
+
"Gender=Masc|Number=Sing|POS=DET|PronType=Art":"Gender=Masc|Number=Sing|PronType=Art",
|
| 45 |
+
"Case=Gen|Definite=Def|Gender=Masc|Number=Sing|POS=NOUN":"Case=Gen|Definite=Def|Gender=Masc|Number=Sing",
|
| 46 |
+
"Abbr=Yes|POS=PROPN":"Abbr=Yes",
|
| 47 |
+
"POS=PART|Polarity=Neg":"Polarity=Neg",
|
| 48 |
+
"Number=Plur|POS=PRON|Poss=Yes|PronType=Prs":"Number=Plur|Poss=Yes|PronType=Prs",
|
| 49 |
+
"Case=Gen|Definite=Ind|Gender=Neut|Number=Plur|POS=NOUN":"Case=Gen|Definite=Ind|Gender=Neut|Number=Plur",
|
| 50 |
+
"Case=Gen|POS=PROPN":"Case=Gen",
|
| 51 |
+
"Gender=Fem|Number=Sing|POS=DET|PronType=Dem":"Gender=Fem|Number=Sing|PronType=Dem",
|
| 52 |
+
"Gender=Masc|Number=Sing|POS=PRON|Poss=Yes|PronType=Prs":"Gender=Masc|Number=Sing|Poss=Yes|PronType=Prs",
|
| 53 |
+
"Definite=Def|Degree=Sup|POS=ADJ":"Definite=Def|Degree=Sup",
|
| 54 |
+
"Case=Gen|Gender=Fem|POS=PROPN":"Case=Gen|Gender=Fem",
|
| 55 |
+
"Number=Plur|POS=DET|PronType=Dem":"Number=Plur|PronType=Dem",
|
| 56 |
+
"Case=Gen|Definite=Def|Gender=Neut|Number=Sing|POS=NOUN":"Case=Gen|Definite=Def|Gender=Neut|Number=Sing",
|
| 57 |
+
"Definite=Ind|Degree=Sup|POS=ADJ":"Definite=Ind|Degree=Sup",
|
| 58 |
+
"Definite=Def|Gender=Fem|Number=Plur|POS=NOUN":"Definite=Def|Gender=Fem|Number=Plur",
|
| 59 |
+
"Gender=Neut|POS=PROPN":"Gender=Neut",
|
| 60 |
+
"Number=Plur|POS=DET|PronType=Int":"Number=Plur|PronType=Int",
|
| 61 |
+
"Definite=Def|Gender=Neut|Number=Plur|POS=NOUN":"Definite=Def|Gender=Neut|Number=Plur",
|
| 62 |
+
"Definite=Def|POS=DET|PronType=Dem":"Definite=Def|PronType=Dem",
|
| 63 |
+
"Gender=Neut|Number=Sing|POS=DET|PronType=Art":"Gender=Neut|Number=Sing|PronType=Art",
|
| 64 |
+
"Mood=Ind|POS=VERB|Tense=Pres|VerbForm=Fin|Voice=Pass":"Mood=Ind|Tense=Pres|VerbForm=Fin|Voice=Pass",
|
| 65 |
+
"Abbr=Yes|Case=Gen|POS=PROPN":"Abbr=Yes|Case=Gen",
|
| 66 |
+
"Animacy=Hum|Case=Nom|Gender=Masc|Number=Sing|POS=PRON|Person=3|PronType=Prs":"Animacy=Hum|Case=Nom|Gender=Masc|Number=Sing|Person=3|PronType=Prs",
|
| 67 |
+
"Degree=Cmp|POS=ADJ":"Degree=Cmp",
|
| 68 |
+
"POS=ADJ|VerbForm=Part":"VerbForm=Part",
|
| 69 |
+
"Gender=Neut|Number=Sing|POS=PRON|Poss=Yes|PronType=Prs":"Gender=Neut|Number=Sing|Poss=Yes|PronType=Prs",
|
| 70 |
+
"Abbr=Yes|POS=ADP":"Abbr=Yes",
|
| 71 |
+
"Definite=Ind|Gender=Neut|Number=Sing|POS=DET|PronType=Prs":"Definite=Ind|Gender=Neut|Number=Sing|PronType=Prs",
|
| 72 |
+
"Case=Gen|Definite=Def|Gender=Neut|Number=Plur|POS=NOUN":"Case=Gen|Definite=Def|Gender=Neut|Number=Plur",
|
| 73 |
+
"POS=AUX|VerbForm=Part":"VerbForm=Part",
|
| 74 |
+
"POS=PRON|PronType=Int":"PronType=Int",
|
| 75 |
+
"Gender=Fem|Number=Sing|POS=PRON|Poss=Yes|PronType=Prs":"Gender=Fem|Number=Sing|Poss=Yes|PronType=Prs",
|
| 76 |
+
"Number=Plur|POS=PRON|Person=3|PronType=Ind,Prs":"Number=Plur|Person=3|PronType=Ind,Prs",
|
| 77 |
+
"Number=Plur|POS=DET|PronType=Ind":"Number=Plur|PronType=Ind",
|
| 78 |
+
"Degree=Pos|POS=ADJ":"Degree=Pos",
|
| 79 |
+
"Animacy=Hum|Case=Nom|Number=Plur|POS=PRON|Person=1|PronType=Prs":"Animacy=Hum|Case=Nom|Number=Plur|Person=1|PronType=Prs",
|
| 80 |
+
"POS=VERB|VerbForm=Inf|Voice=Pass":"VerbForm=Inf|Voice=Pass",
|
| 81 |
+
"Definite=Ind|Gender=Fem|Number=Sing|POS=DET|PronType=Dem":"Definite=Ind|Gender=Fem|Number=Sing|PronType=Dem",
|
| 82 |
+
"Gender=Neut|Number=Sing|POS=DET|PronType=Ind":"Gender=Neut|Number=Sing|PronType=Ind",
|
| 83 |
+
"Animacy=Hum|Case=Acc|Gender=Masc|Number=Sing|POS=PRON|Person=3|PronType=Prs":"Animacy=Hum|Case=Acc|Gender=Masc|Number=Sing|Person=3|PronType=Prs",
|
| 84 |
+
"Animacy=Hum|Case=Nom|Number=Sing|POS=PRON|Person=1|PronType=Prs":"Animacy=Hum|Case=Nom|Number=Sing|Person=1|PronType=Prs",
|
| 85 |
+
"Number=Plur|POS=DET|Polarity=Neg|PronType=Neg":"Number=Plur|Polarity=Neg|PronType=Neg",
|
| 86 |
+
"NumType=Card|POS=NUM":"NumType=Card",
|
| 87 |
+
"Gender=Masc|Number=Sing|POS=DET|PronType=Ind":"Gender=Masc|Number=Sing|PronType=Ind",
|
| 88 |
+
"POS=DET|PronType=Prs":"PronType=Prs",
|
| 89 |
+
"Gender=Fem|Number=Sing|POS=DET|PronType=Ind":"Gender=Fem|Number=Sing|PronType=Ind",
|
| 90 |
+
"Case=Gen|Gender=Neut|POS=PROPN":"Case=Gen|Gender=Neut",
|
| 91 |
+
"Gender=Masc|Number=Sing|POS=DET|Polarity=Neg|PronType=Neg":"Gender=Masc|Number=Sing|Polarity=Neg|PronType=Neg",
|
| 92 |
+
"Definite=Def|Number=Sing|POS=ADJ|VerbForm=Part":"Definite=Def|Number=Sing|VerbForm=Part",
|
| 93 |
+
"Gender=Fem,Masc|Number=Sing|POS=PRON|Person=3|PronType=Prs":"Gender=Fem,Masc|Number=Sing|Person=3|PronType=Prs",
|
| 94 |
+
"POS=AUX|VerbForm=Inf":"VerbForm=Inf",
|
| 95 |
+
"Case=Acc|Number=Plur|POS=PRON|Person=3|PronType=Prs":"Case=Acc|Number=Plur|Person=3|PronType=Prs",
|
| 96 |
+
"Case=Gen|Degree=Pos|Number=Plur|POS=ADJ":"Case=Gen|Degree=Pos|Number=Plur",
|
| 97 |
+
"Number=Plur|POS=DET|PronType=Tot":"Number=Plur|PronType=Tot",
|
| 98 |
+
"Case=Gen|Gender=Masc|Number=Sing|POS=DET|PronType=Dem":"Case=Gen|Gender=Masc|Number=Sing|PronType=Dem",
|
| 99 |
+
"Number=Plur|POS=DET|PronType=Prs":"Number=Plur|PronType=Prs",
|
| 100 |
+
"POS=SYM":"",
|
| 101 |
+
"Gender=Neut|NumType=Card|Number=Sing|POS=NUM":"Gender=Neut|NumType=Card|Number=Sing",
|
| 102 |
+
"Animacy=Hum|Case=Nom|Number=Sing|POS=PRON|PronType=Prs":"Animacy=Hum|Case=Nom|Number=Sing|PronType=Prs",
|
| 103 |
+
"Definite=Ind|Gender=Masc|Number=Sing|POS=DET|PronType=Prs":"Definite=Ind|Gender=Masc|Number=Sing|PronType=Prs",
|
| 104 |
+
"Case=Gen|Definite=Ind|Gender=Masc|Number=Sing|POS=NOUN":"Case=Gen|Definite=Ind|Gender=Masc|Number=Sing",
|
| 105 |
+
"Abbr=Yes|POS=ADV":"Abbr=Yes",
|
| 106 |
+
"Definite=Ind|Gender=Neut|Number=Sing|POS=DET|PronType=Dem":"Definite=Ind|Gender=Neut|Number=Sing|PronType=Dem",
|
| 107 |
+
"Gender=Masc|Number=Sing|POS=DET|PronType=Tot":"Gender=Masc|Number=Sing|PronType=Tot",
|
| 108 |
+
"Definite=Def|POS=DET|PronType=Prs":"Definite=Def|PronType=Prs",
|
| 109 |
+
"Animacy=Hum|Case=Nom|Gender=Fem|Number=Sing|POS=PRON|Person=3|PronType=Prs":"Animacy=Hum|Case=Nom|Gender=Fem|Number=Sing|Person=3|PronType=Prs",
|
| 110 |
+
"Gender=Neut|POS=NOUN":"Gender=Neut",
|
| 111 |
+
"Gender=Neut|Number=Sing|POS=DET|PronType=Int":"Gender=Neut|Number=Sing|PronType=Int",
|
| 112 |
+
"Definite=Def|NumType=Card|POS=NUM":"Definite=Def|NumType=Card",
|
| 113 |
+
"Mood=Imp|POS=VERB|VerbForm=Fin":"Mood=Imp|VerbForm=Fin",
|
| 114 |
+
"Definite=Ind|Number=Plur|POS=NOUN":"Definite=Ind|Number=Plur",
|
| 115 |
+
"Gender=Neut|Number=Sing|POS=DET|PronType=Tot":"Gender=Neut|Number=Sing|PronType=Tot",
|
| 116 |
+
"Gender=Fem|Number=Sing|POS=DET|PronType=Tot":"Gender=Fem|Number=Sing|PronType=Tot",
|
| 117 |
+
"Animacy=Hum|Case=Acc|Number=Plur|POS=PRON|Person=1|PronType=Prs":"Animacy=Hum|Case=Acc|Number=Plur|Person=1|PronType=Prs",
|
| 118 |
+
"Gender=Fem,Masc|Number=Sing|POS=PRON|Person=3|Polarity=Neg|PronType=Neg,Prs":"Gender=Fem,Masc|Number=Sing|Person=3|Polarity=Neg|PronType=Neg,Prs",
|
| 119 |
+
"Number=Plur|POS=PRON|Person=3|Polarity=Neg|PronType=Neg,Prs":"Number=Plur|Person=3|Polarity=Neg|PronType=Neg,Prs",
|
| 120 |
+
"Definite=Def|NumType=Card|Number=Sing|POS=NUM":"Definite=Def|NumType=Card|Number=Sing",
|
| 121 |
+
"Gender=Masc|NumType=Card|Number=Sing|POS=NUM":"Gender=Masc|NumType=Card|Number=Sing",
|
| 122 |
+
"Definite=Ind|Gender=Masc|Number=Sing|POS=DET|PronType=Dem":"Definite=Ind|Gender=Masc|Number=Sing|PronType=Dem",
|
| 123 |
+
"Case=Gen|Definite=Def|Gender=Fem|Number=Plur|POS=NOUN":"Case=Gen|Definite=Def|Gender=Fem|Number=Plur",
|
| 124 |
+
"Case=Gen|Gender=Neut|Number=Sing|POS=DET|PronType=Dem":"Case=Gen|Gender=Neut|Number=Sing|PronType=Dem",
|
| 125 |
+
"Animacy=Hum|Number=Sing|POS=PRON|PronType=Art,Prs":"Animacy=Hum|Number=Sing|PronType=Art,Prs",
|
| 126 |
+
"Mood=Imp|POS=AUX|VerbForm=Fin":"Mood=Imp|VerbForm=Fin",
|
| 127 |
+
"Number=Plur|POS=PRON|Person=3|PronType=Prs,Tot":"Number=Plur|Person=3|PronType=Prs,Tot",
|
| 128 |
+
"Number=Plur|POS=ADJ":"Number=Plur",
|
| 129 |
+
"Gender=Masc|POS=NOUN":"Gender=Masc",
|
| 130 |
+
"Abbr=Yes|POS=NOUN":"Abbr=Yes",
|
| 131 |
+
"Case=Gen|Definite=Ind|Gender=Masc|Number=Plur|POS=NOUN":"Case=Gen|Definite=Ind|Gender=Masc|Number=Plur",
|
| 132 |
+
"Gender=Neut|Number=Sing|POS=PRON|Person=3|PronType=Ind,Prs":"Gender=Neut|Number=Sing|Person=3|PronType=Ind,Prs",
|
| 133 |
+
"POS=INTJ":"",
|
| 134 |
+
"Animacy=Hum|Case=Nom|Number=Sing|POS=PRON|Person=2|PronType=Prs":"Animacy=Hum|Case=Nom|Number=Sing|Person=2|PronType=Prs",
|
| 135 |
+
"Animacy=Hum|Case=Acc|Number=Sing|POS=PRON|Person=1|PronType=Prs":"Animacy=Hum|Case=Acc|Number=Sing|Person=1|PronType=Prs",
|
| 136 |
+
"Case=Gen|Definite=Def|Gender=Masc|Number=Plur|POS=NOUN":"Case=Gen|Definite=Def|Gender=Masc|Number=Plur",
|
| 137 |
+
"POS=ADJ":"",
|
| 138 |
+
"Animacy=Hum|Case=Acc|Gender=Fem|Number=Sing|POS=PRON|Person=3|PronType=Prs":"Animacy=Hum|Case=Acc|Gender=Fem|Number=Sing|Person=3|PronType=Prs",
|
| 139 |
+
"Animacy=Hum|Case=Acc|Number=Sing|POS=PRON|Person=2|PronType=Prs":"Animacy=Hum|Case=Acc|Number=Sing|Person=2|PronType=Prs",
|
| 140 |
+
"Definite=Def|Gender=Fem|Number=Sing|POS=NOUN":"Definite=Def|Gender=Fem|Number=Sing",
|
| 141 |
+
"Number=Sing|POS=PRON|Polarity=Neg|PronType=Neg":"Number=Sing|Polarity=Neg|PronType=Neg",
|
| 142 |
+
"Case=Gen|POS=NOUN":"Case=Gen",
|
| 143 |
+
"Definite=Ind|Number=Sing|POS=ADJ":"Definite=Ind|Number=Sing",
|
| 144 |
+
"Case=Gen|Gender=Masc|POS=PROPN":"Case=Gen|Gender=Masc",
|
| 145 |
+
"Animacy=Hum|Number=Plur|POS=PRON|PronType=Rcp":"Animacy=Hum|Number=Plur|PronType=Rcp",
|
| 146 |
+
"Case=Gen|Definite=Ind|Gender=Fem|Number=Sing|POS=NOUN":"Case=Gen|Definite=Ind|Gender=Fem|Number=Sing",
|
| 147 |
+
"Number=Plur|POS=PRON|Person=3|PronType=Prs":"Number=Plur|Person=3|PronType=Prs",
|
| 148 |
+
"Gender=Fem,Masc|Number=Sing|POS=PRON|Person=3|PronType=Ind,Prs":"Gender=Fem,Masc|Number=Sing|Person=3|PronType=Ind,Prs",
|
| 149 |
+
"Definite=Ind|Gender=Fem|Number=Sing|POS=DET|PronType=Prs":"Definite=Ind|Gender=Fem|Number=Sing|PronType=Prs",
|
| 150 |
+
"Case=Gen|Definite=Def|Gender=Fem|Number=Sing|POS=NOUN":"Case=Gen|Definite=Def|Gender=Fem|Number=Sing",
|
| 151 |
+
"Gender=Fem|Number=Sing|POS=DET|PronType=Art":"Gender=Fem|Number=Sing|PronType=Art",
|
| 152 |
+
"Case=Gen|Definite=Def|Degree=Pos|Number=Sing|POS=ADJ":"Case=Gen|Definite=Def|Degree=Pos|Number=Sing",
|
| 153 |
+
"Gender=Masc|Number=Sing|POS=DET|PronType=Int":"Gender=Masc|Number=Sing|PronType=Int",
|
| 154 |
+
"NumType=Card|Number=Sing|POS=NUM":"NumType=Card|Number=Sing",
|
| 155 |
+
"Animacy=Hum|Case=Acc|Number=Plur|POS=PRON|Person=2|PronType=Prs":"Animacy=Hum|Case=Acc|Number=Plur|Person=2|PronType=Prs",
|
| 156 |
+
"Animacy=Hum|Case=Nom|Number=Plur|POS=PRON|Person=2|PronType=Prs":"Animacy=Hum|Case=Nom|Number=Plur|Person=2|PronType=Prs",
|
| 157 |
+
"Case=Gen|Definite=Ind|Degree=Pos|Gender=Neut|Number=Sing|POS=ADJ":"Case=Gen|Definite=Ind|Degree=Pos|Gender=Neut|Number=Sing",
|
| 158 |
+
"Degree=Sup|POS=ADJ":"Degree=Sup",
|
| 159 |
+
"Animacy=Hum|POS=PRON|PronType=Int":"Animacy=Hum|PronType=Int",
|
| 160 |
+
"POS=DET|PronType=Ind":"PronType=Ind",
|
| 161 |
+
"Definite=Def|Number=Sing|POS=DET|PronType=Dem":"Definite=Def|Number=Sing|PronType=Dem",
|
| 162 |
+
"Gender=Fem|POS=NOUN":"Gender=Fem",
|
| 163 |
+
"Case=Gen|Number=Plur|POS=DET|PronType=Dem":"Case=Gen|Number=Plur|PronType=Dem",
|
| 164 |
+
"Gender=Fem,Masc|Number=Sing|POS=PRON|Person=3|PronType=Prs,Tot":"Gender=Fem,Masc|Number=Sing|Person=3|PronType=Prs,Tot",
|
| 165 |
+
"Case=Gen|Definite=Ind|Gender=Fem|Number=Plur|POS=NOUN":"Case=Gen|Definite=Ind|Gender=Fem|Number=Plur",
|
| 166 |
+
"Gender=Neut|Number=Sing|POS=DET|Polarity=Neg|PronType=Neg":"Gender=Neut|Number=Sing|Polarity=Neg|PronType=Neg",
|
| 167 |
+
"Number=Plur|POS=NOUN":"Number=Plur",
|
| 168 |
+
"Case=Gen|Definite=Ind|Degree=Pos|Number=Sing|POS=ADJ":"Case=Gen|Definite=Ind|Degree=Pos|Number=Sing",
|
| 169 |
+
"Definite=Ind|Number=Sing|POS=VERB|VerbForm=Part":"Definite=Ind|Number=Sing|VerbForm=Part",
|
| 170 |
+
"Case=Gen|Definite=Def|Number=Sing|POS=ADJ|VerbForm=Part":"Case=Gen|Definite=Def|Number=Sing|VerbForm=Part",
|
| 171 |
+
"Mood=Ind|POS=VERB|Tense=Past|VerbForm=Fin|Voice=Pass":"Mood=Ind|Tense=Past|VerbForm=Fin|Voice=Pass",
|
| 172 |
+
"Gender=Neut|Number=Sing|POS=DET|PronType=Dem,Ind":"Gender=Neut|Number=Sing|PronType=Dem,Ind",
|
| 173 |
+
"Animacy=Hum|POS=PRON|Poss=Yes|PronType=Int":"Animacy=Hum|Poss=Yes|PronType=Int",
|
| 174 |
+
"Abbr=Yes|POS=ADJ":"Abbr=Yes",
|
| 175 |
+
"Case=Gen|Gender=Masc|Number=Sing|POS=DET|PronType=Art":"Case=Gen|Gender=Masc|Number=Sing|PronType=Art",
|
| 176 |
+
"Abbr=Yes|Definite=Def,Ind|Gender=Masc|Number=Sing|POS=NOUN":"Abbr=Yes|Definite=Def,Ind|Gender=Masc|Number=Sing",
|
| 177 |
+
"POS=PRON|PronType=Prs":"PronType=Prs",
|
| 178 |
+
"Case=Gen|Gender=Fem|Number=Sing|POS=DET|PronType=Dem":"Case=Gen|Gender=Fem|Number=Sing|PronType=Dem",
|
| 179 |
+
"Number=Plur|POS=PRON|Poss=Yes|PronType=Rcp":"Number=Plur|Poss=Yes|PronType=Rcp",
|
| 180 |
+
"Definite=Ind|Degree=Pos|POS=ADJ":"Definite=Ind|Degree=Pos",
|
| 181 |
+
"Number=Plur|POS=DET|PronType=Art":"Number=Plur|PronType=Art",
|
| 182 |
+
"Case=Gen|NumType=Card|Number=Plur|POS=NUM":"Case=Gen|NumType=Card|Number=Plur",
|
| 183 |
+
"Abbr=Yes|Definite=Def,Ind|Gender=Neut|Number=Plur,Sing|POS=NOUN":"Abbr=Yes|Definite=Def,Ind|Gender=Neut|Number=Plur,Sing",
|
| 184 |
+
"Case=Gen|Number=Plur|POS=DET|PronType=Tot":"Case=Gen|Number=Plur|PronType=Tot",
|
| 185 |
+
"Abbr=Yes|Definite=Def,Ind|Gender=Masc|Number=Plur,Sing|POS=NOUN":"Abbr=Yes|Definite=Def,Ind|Gender=Masc|Number=Plur,Sing",
|
| 186 |
+
"Gender=Fem|Number=Sing|POS=DET|PronType=Int":"Gender=Fem|Number=Sing|PronType=Int",
|
| 187 |
+
"Definite=Ind|Gender=Neut|Number=Sing|POS=ADJ":"Definite=Ind|Gender=Neut|Number=Sing",
|
| 188 |
+
"Case=Gen|Definite=Ind|Gender=Masc|Number=Sing|POS=DET|PronType=Dem":"Case=Gen|Definite=Ind|Gender=Masc|Number=Sing|PronType=Dem",
|
| 189 |
+
"Gender=Fem|Number=Sing|POS=DET|PronType=Prs":"Gender=Fem|Number=Sing|PronType=Prs",
|
| 190 |
+
"Animacy=Hum|Case=Gen,Nom|Number=Sing|POS=PRON|PronType=Art,Prs":"Animacy=Hum|Case=Gen,Nom|Number=Sing|PronType=Art,Prs",
|
| 191 |
+
"Definite=Def|Degree=Pos|Gender=Masc|Number=Sing|POS=ADJ":"Definite=Def|Degree=Pos|Gender=Masc|Number=Sing",
|
| 192 |
+
"Animacy=Hum|Case=Gen|Number=Sing|POS=PRON|PronType=Art,Prs":"Animacy=Hum|Case=Gen|Number=Sing|PronType=Art,Prs",
|
| 193 |
+
"Gender=Fem|NumType=Card|Number=Sing|POS=NUM":"Gender=Fem|NumType=Card|Number=Sing",
|
| 194 |
+
"Definite=Ind|Gender=Masc|POS=NOUN":"Definite=Ind|Gender=Masc",
|
| 195 |
+
"Definite=Def|Number=Plur|POS=NOUN":"Definite=Def|Number=Plur",
|
| 196 |
+
"Number=Sing|POS=ADJ|VerbForm=Part":"Number=Sing|VerbForm=Part",
|
| 197 |
+
"Definite=Ind|Gender=Masc|Number=Sing|POS=ADJ|VerbForm=Part":"Definite=Ind|Gender=Masc|Number=Sing|VerbForm=Part",
|
| 198 |
+
"Abbr=Yes|Gender=Masc|POS=NOUN":"Abbr=Yes|Gender=Masc",
|
| 199 |
+
"Abbr=Yes|Case=Gen|POS=NOUN":"Abbr=Yes|Case=Gen",
|
| 200 |
+
"Abbr=Yes|Mood=Ind|POS=VERB|Tense=Pres|VerbForm=Fin":"Abbr=Yes|Mood=Ind|Tense=Pres|VerbForm=Fin",
|
| 201 |
+
"Abbr=Yes|Degree=Pos|POS=ADJ":"Abbr=Yes|Degree=Pos",
|
| 202 |
+
"Case=Gen|Gender=Fem|POS=NOUN":"Case=Gen|Gender=Fem",
|
| 203 |
+
"Case=Gen|Degree=Cmp|POS=ADJ":"Case=Gen|Degree=Cmp",
|
| 204 |
+
"Definite=Ind|Degree=Pos|Gender=Masc|Number=Sing|POS=ADJ":"Definite=Ind|Degree=Pos|Gender=Masc|Number=Sing",
|
| 205 |
+
"Gender=Masc|Number=Sing|POS=NOUN":"Gender=Masc|Number=Sing"
|
| 206 |
+
},
|
| 207 |
+
"labels_pos":{
|
| 208 |
+
"Definite=Ind|Gender=Neut|Number=Sing|POS=NOUN":92,
|
| 209 |
+
"POS=CCONJ":89,
|
| 210 |
+
"Definite=Ind|Gender=Masc|Number=Sing|POS=NOUN":92,
|
| 211 |
+
"POS=SCONJ":98,
|
| 212 |
+
"Definite=Def|Gender=Masc|Number=Sing|POS=NOUN":92,
|
| 213 |
+
"Definite=Ind|Gender=Neut|Number=Plur|POS=NOUN":92,
|
| 214 |
+
"POS=PUNCT":97,
|
| 215 |
+
"Mood=Ind|POS=VERB|Tense=Past|VerbForm=Fin":100,
|
| 216 |
+
"POS=ADP":85,
|
| 217 |
+
"Gender=Masc|Number=Sing|POS=DET|PronType=Dem":90,
|
| 218 |
+
"Definite=Def|Degree=Pos|Number=Sing|POS=ADJ":84,
|
| 219 |
+
"POS=PROPN":96,
|
| 220 |
+
"POS=X":101,
|
| 221 |
+
"Mood=Ind|POS=VERB|Tense=Pres|VerbForm=Fin":100,
|
| 222 |
+
"Definite=Def|Gender=Neut|Number=Sing|POS=NOUN":92,
|
| 223 |
+
"POS=PRON|PronType=Rel":95,
|
| 224 |
+
"Mood=Ind|POS=AUX|Tense=Pres|VerbForm=Fin":87,
|
| 225 |
+
"Definite=Ind|Gender=Neut|Number=Sing|POS=ADJ|VerbForm=Part":84,
|
| 226 |
+
"Definite=Ind|Degree=Pos|Number=Sing|POS=ADJ":84,
|
| 227 |
+
"Definite=Ind|Gender=Fem|Number=Sing|POS=NOUN":92,
|
| 228 |
+
"Number=Plur|POS=ADJ|VerbForm=Part":84,
|
| 229 |
+
"Definite=Ind|Gender=Fem|Number=Plur|POS=NOUN":92,
|
| 230 |
+
"POS=ADV":86,
|
| 231 |
+
"Gender=Neut|Number=Sing|POS=PRON|Person=3|PronType=Prs":95,
|
| 232 |
+
"Definite=Ind|Number=Sing|POS=ADJ|VerbForm=Part":84,
|
| 233 |
+
"POS=VERB|VerbForm=Part":100,
|
| 234 |
+
"Definite=Ind|Gender=Masc|Number=Plur|POS=NOUN":92,
|
| 235 |
+
"Definite=Ind|Degree=Pos|Gender=Neut|Number=Sing|POS=ADJ":84,
|
| 236 |
+
"Degree=Pos|Number=Plur|POS=ADJ":84,
|
| 237 |
+
"NumType=Card|Number=Plur|POS=NUM":93,
|
| 238 |
+
"Definite=Def|Gender=Masc|Number=Plur|POS=NOUN":92,
|
| 239 |
+
"Case=Acc|POS=PRON|PronType=Prs|Reflex=Yes":95,
|
| 240 |
+
"Case=Gen|Definite=Ind|Gender=Neut|Number=Sing|POS=NOUN":92,
|
| 241 |
+
"POS=PART":94,
|
| 242 |
+
"POS=VERB|VerbForm=Inf":100,
|
| 243 |
+
"Case=Nom|Number=Plur|POS=PRON|Person=3|PronType=Prs":95,
|
| 244 |
+
"Mood=Ind|POS=AUX|Tense=Past|VerbForm=Fin":87,
|
| 245 |
+
"Gender=Fem|POS=PROPN":96,
|
| 246 |
+
"POS=NOUN":92,
|
| 247 |
+
"Gender=Masc|POS=PROPN":96,
|
| 248 |
+
"Gender=Neut|Number=Sing|POS=DET|PronType=Dem":90,
|
| 249 |
+
"Gender=Masc|Number=Sing|POS=DET|PronType=Art":90,
|
| 250 |
+
"Case=Gen|Definite=Def|Gender=Masc|Number=Sing|POS=NOUN":92,
|
| 251 |
+
"Abbr=Yes|POS=PROPN":96,
|
| 252 |
+
"POS=PART|Polarity=Neg":94,
|
| 253 |
+
"Number=Plur|POS=PRON|Poss=Yes|PronType=Prs":95,
|
| 254 |
+
"Case=Gen|Definite=Ind|Gender=Neut|Number=Plur|POS=NOUN":92,
|
| 255 |
+
"Case=Gen|POS=PROPN":96,
|
| 256 |
+
"Gender=Fem|Number=Sing|POS=DET|PronType=Dem":90,
|
| 257 |
+
"Gender=Masc|Number=Sing|POS=PRON|Poss=Yes|PronType=Prs":95,
|
| 258 |
+
"Definite=Def|Degree=Sup|POS=ADJ":84,
|
| 259 |
+
"Case=Gen|Gender=Fem|POS=PROPN":96,
|
| 260 |
+
"Number=Plur|POS=DET|PronType=Dem":90,
|
| 261 |
+
"Case=Gen|Definite=Def|Gender=Neut|Number=Sing|POS=NOUN":92,
|
| 262 |
+
"Definite=Ind|Degree=Sup|POS=ADJ":84,
|
| 263 |
+
"Definite=Def|Gender=Fem|Number=Plur|POS=NOUN":92,
|
| 264 |
+
"Gender=Neut|POS=PROPN":96,
|
| 265 |
+
"Number=Plur|POS=DET|PronType=Int":90,
|
| 266 |
+
"Definite=Def|Gender=Neut|Number=Plur|POS=NOUN":92,
|
| 267 |
+
"Definite=Def|POS=DET|PronType=Dem":90,
|
| 268 |
+
"Gender=Neut|Number=Sing|POS=DET|PronType=Art":90,
|
| 269 |
+
"Mood=Ind|POS=VERB|Tense=Pres|VerbForm=Fin|Voice=Pass":100,
|
| 270 |
+
"Abbr=Yes|Case=Gen|POS=PROPN":96,
|
| 271 |
+
"Animacy=Hum|Case=Nom|Gender=Masc|Number=Sing|POS=PRON|Person=3|PronType=Prs":95,
|
| 272 |
+
"Degree=Cmp|POS=ADJ":84,
|
| 273 |
+
"POS=ADJ|VerbForm=Part":84,
|
| 274 |
+
"Gender=Neut|Number=Sing|POS=PRON|Poss=Yes|PronType=Prs":95,
|
| 275 |
+
"Abbr=Yes|POS=ADP":85,
|
| 276 |
+
"Definite=Ind|Gender=Neut|Number=Sing|POS=DET|PronType=Prs":90,
|
| 277 |
+
"Case=Gen|Definite=Def|Gender=Neut|Number=Plur|POS=NOUN":92,
|
| 278 |
+
"POS=AUX|VerbForm=Part":87,
|
| 279 |
+
"POS=PRON|PronType=Int":95,
|
| 280 |
+
"Gender=Fem|Number=Sing|POS=PRON|Poss=Yes|PronType=Prs":95,
|
| 281 |
+
"Number=Plur|POS=PRON|Person=3|PronType=Ind,Prs":95,
|
| 282 |
+
"Number=Plur|POS=DET|PronType=Ind":90,
|
| 283 |
+
"Degree=Pos|POS=ADJ":84,
|
| 284 |
+
"Animacy=Hum|Case=Nom|Number=Plur|POS=PRON|Person=1|PronType=Prs":95,
|
| 285 |
+
"POS=VERB|VerbForm=Inf|Voice=Pass":100,
|
| 286 |
+
"Definite=Ind|Gender=Fem|Number=Sing|POS=DET|PronType=Dem":90,
|
| 287 |
+
"Gender=Neut|Number=Sing|POS=DET|PronType=Ind":90,
|
| 288 |
+
"Animacy=Hum|Case=Acc|Gender=Masc|Number=Sing|POS=PRON|Person=3|PronType=Prs":95,
|
| 289 |
+
"Animacy=Hum|Case=Nom|Number=Sing|POS=PRON|Person=1|PronType=Prs":95,
|
| 290 |
+
"Number=Plur|POS=DET|Polarity=Neg|PronType=Neg":90,
|
| 291 |
+
"NumType=Card|POS=NUM":93,
|
| 292 |
+
"Gender=Masc|Number=Sing|POS=DET|PronType=Ind":90,
|
| 293 |
+
"POS=DET|PronType=Prs":90,
|
| 294 |
+
"Gender=Fem|Number=Sing|POS=DET|PronType=Ind":90,
|
| 295 |
+
"Case=Gen|Gender=Neut|POS=PROPN":96,
|
| 296 |
+
"Gender=Masc|Number=Sing|POS=DET|Polarity=Neg|PronType=Neg":90,
|
| 297 |
+
"Definite=Def|Number=Sing|POS=ADJ|VerbForm=Part":84,
|
| 298 |
+
"Gender=Fem,Masc|Number=Sing|POS=PRON|Person=3|PronType=Prs":95,
|
| 299 |
+
"POS=AUX|VerbForm=Inf":87,
|
| 300 |
+
"Case=Acc|Number=Plur|POS=PRON|Person=3|PronType=Prs":95,
|
| 301 |
+
"Case=Gen|Degree=Pos|Number=Plur|POS=ADJ":84,
|
| 302 |
+
"Number=Plur|POS=DET|PronType=Tot":90,
|
| 303 |
+
"Case=Gen|Gender=Masc|Number=Sing|POS=DET|PronType=Dem":90,
|
| 304 |
+
"Number=Plur|POS=DET|PronType=Prs":90,
|
| 305 |
+
"POS=SYM":99,
|
| 306 |
+
"Gender=Neut|NumType=Card|Number=Sing|POS=NUM":93,
|
| 307 |
+
"Animacy=Hum|Case=Nom|Number=Sing|POS=PRON|PronType=Prs":95,
|
| 308 |
+
"Definite=Ind|Gender=Masc|Number=Sing|POS=DET|PronType=Prs":90,
|
| 309 |
+
"Case=Gen|Definite=Ind|Gender=Masc|Number=Sing|POS=NOUN":92,
|
| 310 |
+
"Abbr=Yes|POS=ADV":86,
|
| 311 |
+
"Definite=Ind|Gender=Neut|Number=Sing|POS=DET|PronType=Dem":90,
|
| 312 |
+
"Gender=Masc|Number=Sing|POS=DET|PronType=Tot":90,
|
| 313 |
+
"Definite=Def|POS=DET|PronType=Prs":90,
|
| 314 |
+
"Animacy=Hum|Case=Nom|Gender=Fem|Number=Sing|POS=PRON|Person=3|PronType=Prs":95,
|
| 315 |
+
"Gender=Neut|POS=NOUN":92,
|
| 316 |
+
"Gender=Neut|Number=Sing|POS=DET|PronType=Int":90,
|
| 317 |
+
"Definite=Def|NumType=Card|POS=NUM":93,
|
| 318 |
+
"Mood=Imp|POS=VERB|VerbForm=Fin":100,
|
| 319 |
+
"Definite=Ind|Number=Plur|POS=NOUN":92,
|
| 320 |
+
"Gender=Neut|Number=Sing|POS=DET|PronType=Tot":90,
|
| 321 |
+
"Gender=Fem|Number=Sing|POS=DET|PronType=Tot":90,
|
| 322 |
+
"Animacy=Hum|Case=Acc|Number=Plur|POS=PRON|Person=1|PronType=Prs":95,
|
| 323 |
+
"Gender=Fem,Masc|Number=Sing|POS=PRON|Person=3|Polarity=Neg|PronType=Neg,Prs":95,
|
| 324 |
+
"Number=Plur|POS=PRON|Person=3|Polarity=Neg|PronType=Neg,Prs":95,
|
| 325 |
+
"Definite=Def|NumType=Card|Number=Sing|POS=NUM":93,
|
| 326 |
+
"Gender=Masc|NumType=Card|Number=Sing|POS=NUM":93,
|
| 327 |
+
"Definite=Ind|Gender=Masc|Number=Sing|POS=DET|PronType=Dem":90,
|
| 328 |
+
"Case=Gen|Definite=Def|Gender=Fem|Number=Plur|POS=NOUN":92,
|
| 329 |
+
"Case=Gen|Gender=Neut|Number=Sing|POS=DET|PronType=Dem":90,
|
| 330 |
+
"Animacy=Hum|Number=Sing|POS=PRON|PronType=Art,Prs":95,
|
| 331 |
+
"Mood=Imp|POS=AUX|VerbForm=Fin":87,
|
| 332 |
+
"Number=Plur|POS=PRON|Person=3|PronType=Prs,Tot":95,
|
| 333 |
+
"Number=Plur|POS=ADJ":84,
|
| 334 |
+
"Gender=Masc|POS=NOUN":92,
|
| 335 |
+
"Abbr=Yes|POS=NOUN":92,
|
| 336 |
+
"Case=Gen|Definite=Ind|Gender=Masc|Number=Plur|POS=NOUN":92,
|
| 337 |
+
"Gender=Neut|Number=Sing|POS=PRON|Person=3|PronType=Ind,Prs":95,
|
| 338 |
+
"POS=INTJ":91,
|
| 339 |
+
"Animacy=Hum|Case=Nom|Number=Sing|POS=PRON|Person=2|PronType=Prs":95,
|
| 340 |
+
"Animacy=Hum|Case=Acc|Number=Sing|POS=PRON|Person=1|PronType=Prs":95,
|
| 341 |
+
"Case=Gen|Definite=Def|Gender=Masc|Number=Plur|POS=NOUN":92,
|
| 342 |
+
"POS=ADJ":84,
|
| 343 |
+
"Animacy=Hum|Case=Acc|Gender=Fem|Number=Sing|POS=PRON|Person=3|PronType=Prs":95,
|
| 344 |
+
"Animacy=Hum|Case=Acc|Number=Sing|POS=PRON|Person=2|PronType=Prs":95,
|
| 345 |
+
"Definite=Def|Gender=Fem|Number=Sing|POS=NOUN":92,
|
| 346 |
+
"Number=Sing|POS=PRON|Polarity=Neg|PronType=Neg":95,
|
| 347 |
+
"Case=Gen|POS=NOUN":92,
|
| 348 |
+
"Definite=Ind|Number=Sing|POS=ADJ":84,
|
| 349 |
+
"Case=Gen|Gender=Masc|POS=PROPN":96,
|
| 350 |
+
"Animacy=Hum|Number=Plur|POS=PRON|PronType=Rcp":95,
|
| 351 |
+
"Case=Gen|Definite=Ind|Gender=Fem|Number=Sing|POS=NOUN":92,
|
| 352 |
+
"Number=Plur|POS=PRON|Person=3|PronType=Prs":95,
|
| 353 |
+
"Gender=Fem,Masc|Number=Sing|POS=PRON|Person=3|PronType=Ind,Prs":95,
|
| 354 |
+
"Definite=Ind|Gender=Fem|Number=Sing|POS=DET|PronType=Prs":90,
|
| 355 |
+
"Case=Gen|Definite=Def|Gender=Fem|Number=Sing|POS=NOUN":92,
|
| 356 |
+
"Gender=Fem|Number=Sing|POS=DET|PronType=Art":90,
|
| 357 |
+
"Case=Gen|Definite=Def|Degree=Pos|Number=Sing|POS=ADJ":84,
|
| 358 |
+
"Gender=Masc|Number=Sing|POS=DET|PronType=Int":90,
|
| 359 |
+
"NumType=Card|Number=Sing|POS=NUM":93,
|
| 360 |
+
"Animacy=Hum|Case=Acc|Number=Plur|POS=PRON|Person=2|PronType=Prs":95,
|
| 361 |
+
"Animacy=Hum|Case=Nom|Number=Plur|POS=PRON|Person=2|PronType=Prs":95,
|
| 362 |
+
"Case=Gen|Definite=Ind|Degree=Pos|Gender=Neut|Number=Sing|POS=ADJ":84,
|
| 363 |
+
"Degree=Sup|POS=ADJ":84,
|
| 364 |
+
"Animacy=Hum|POS=PRON|PronType=Int":95,
|
| 365 |
+
"POS=DET|PronType=Ind":90,
|
| 366 |
+
"Definite=Def|Number=Sing|POS=DET|PronType=Dem":90,
|
| 367 |
+
"Gender=Fem|POS=NOUN":92,
|
| 368 |
+
"Case=Gen|Number=Plur|POS=DET|PronType=Dem":90,
|
| 369 |
+
"Gender=Fem,Masc|Number=Sing|POS=PRON|Person=3|PronType=Prs,Tot":95,
|
| 370 |
+
"Case=Gen|Definite=Ind|Gender=Fem|Number=Plur|POS=NOUN":92,
|
| 371 |
+
"Gender=Neut|Number=Sing|POS=DET|Polarity=Neg|PronType=Neg":90,
|
| 372 |
+
"Number=Plur|POS=NOUN":92,
|
| 373 |
+
"Case=Gen|Definite=Ind|Degree=Pos|Number=Sing|POS=ADJ":84,
|
| 374 |
+
"Definite=Ind|Number=Sing|POS=VERB|VerbForm=Part":100,
|
| 375 |
+
"Case=Gen|Definite=Def|Number=Sing|POS=ADJ|VerbForm=Part":84,
|
| 376 |
+
"Mood=Ind|POS=VERB|Tense=Past|VerbForm=Fin|Voice=Pass":100,
|
| 377 |
+
"Gender=Neut|Number=Sing|POS=DET|PronType=Dem,Ind":90,
|
| 378 |
+
"Animacy=Hum|POS=PRON|Poss=Yes|PronType=Int":95,
|
| 379 |
+
"Abbr=Yes|POS=ADJ":84,
|
| 380 |
+
"Case=Gen|Gender=Masc|Number=Sing|POS=DET|PronType=Art":90,
|
| 381 |
+
"Abbr=Yes|Definite=Def,Ind|Gender=Masc|Number=Sing|POS=NOUN":92,
|
| 382 |
+
"POS=PRON|PronType=Prs":95,
|
| 383 |
+
"Case=Gen|Gender=Fem|Number=Sing|POS=DET|PronType=Dem":90,
|
| 384 |
+
"Number=Plur|POS=PRON|Poss=Yes|PronType=Rcp":95,
|
| 385 |
+
"Definite=Ind|Degree=Pos|POS=ADJ":84,
|
| 386 |
+
"Number=Plur|POS=DET|PronType=Art":90,
|
| 387 |
+
"Case=Gen|NumType=Card|Number=Plur|POS=NUM":93,
|
| 388 |
+
"Abbr=Yes|Definite=Def,Ind|Gender=Neut|Number=Plur,Sing|POS=NOUN":92,
|
| 389 |
+
"Case=Gen|Number=Plur|POS=DET|PronType=Tot":90,
|
| 390 |
+
"Abbr=Yes|Definite=Def,Ind|Gender=Masc|Number=Plur,Sing|POS=NOUN":92,
|
| 391 |
+
"Gender=Fem|Number=Sing|POS=DET|PronType=Int":90,
|
| 392 |
+
"Definite=Ind|Gender=Neut|Number=Sing|POS=ADJ":84,
|
| 393 |
+
"Case=Gen|Definite=Ind|Gender=Masc|Number=Sing|POS=DET|PronType=Dem":90,
|
| 394 |
+
"Gender=Fem|Number=Sing|POS=DET|PronType=Prs":90,
|
| 395 |
+
"Animacy=Hum|Case=Gen,Nom|Number=Sing|POS=PRON|PronType=Art,Prs":95,
|
| 396 |
+
"Definite=Def|Degree=Pos|Gender=Masc|Number=Sing|POS=ADJ":84,
|
| 397 |
+
"Animacy=Hum|Case=Gen|Number=Sing|POS=PRON|PronType=Art,Prs":95,
|
| 398 |
+
"Gender=Fem|NumType=Card|Number=Sing|POS=NUM":93,
|
| 399 |
+
"Definite=Ind|Gender=Masc|POS=NOUN":92,
|
| 400 |
+
"Definite=Def|Number=Plur|POS=NOUN":92,
|
| 401 |
+
"Number=Sing|POS=ADJ|VerbForm=Part":84,
|
| 402 |
+
"Definite=Ind|Gender=Masc|Number=Sing|POS=ADJ|VerbForm=Part":84,
|
| 403 |
+
"Abbr=Yes|Gender=Masc|POS=NOUN":92,
|
| 404 |
+
"Abbr=Yes|Case=Gen|POS=NOUN":92,
|
| 405 |
+
"Abbr=Yes|Mood=Ind|POS=VERB|Tense=Pres|VerbForm=Fin":100,
|
| 406 |
+
"Abbr=Yes|Degree=Pos|POS=ADJ":84,
|
| 407 |
+
"Case=Gen|Gender=Fem|POS=NOUN":92,
|
| 408 |
+
"Case=Gen|Degree=Cmp|POS=ADJ":84,
|
| 409 |
+
"Definite=Ind|Degree=Pos|Gender=Masc|Number=Sing|POS=ADJ":84,
|
| 410 |
+
"Gender=Masc|Number=Sing|POS=NOUN":92
|
| 411 |
+
}
|
| 412 |
+
}
|
morphologizer/model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:013a116dc467fce63bb53710744bace9e80859169fa44a6db7129b2ae34cf394
|
| 3 |
+
size 625024
|
nb_nocy_trf-any-py3-none-any.whl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0bd872f73e49edc39f794f900a51470a32061a20bea4d60de2f6e15c94b786d4
|
| 3 |
+
size 416036052
|
ner/cfg
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"moves":null,
|
| 3 |
+
"update_with_oracle_cut_size":100,
|
| 4 |
+
"multitasks":[
|
| 5 |
+
|
| 6 |
+
],
|
| 7 |
+
"min_action_freq":1,
|
| 8 |
+
"learn_tokens":false,
|
| 9 |
+
"beam_width":1,
|
| 10 |
+
"beam_density":0.0,
|
| 11 |
+
"beam_update_prob":0.0,
|
| 12 |
+
"incorrect_spans_key":null
|
| 13 |
+
}
|
ner/model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f60c8d3413dfa78a4d83f3e180515588140d21214daf2029bcc5b96cba4e5b0
|
| 3 |
+
size 257323
|
ner/moves
ADDED
|
@@ -0,0 +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�
|
parser/cfg
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"moves":null,
|
| 3 |
+
"update_with_oracle_cut_size":100,
|
| 4 |
+
"multitasks":[
|
| 5 |
+
|
| 6 |
+
],
|
| 7 |
+
"min_action_freq":30,
|
| 8 |
+
"learn_tokens":false,
|
| 9 |
+
"beam_width":1,
|
| 10 |
+
"beam_density":0.0,
|
| 11 |
+
"beam_update_prob":0.0,
|
| 12 |
+
"incorrect_spans_key":null
|
| 13 |
+
}
|
parser/model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6eb5d9c1238236100820c932e3d0cf02eb194e33f02def65b46dfaac3497bd8
|
| 3 |
+
size 1200351
|
parser/moves
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
��moves��{"0":{"":127735},"1":{"":99477},"2":{"case":25327,"nsubj":18595,"mark":12179,"amod":10706,"det":10561,"advmod":9964,"cc":8377,"aux":6801,"cop":5512,"nmod":5437,"punct":2971,"obl":2939,"expl":2085,"nummod":1813,"nsubj:pass":1364,"aux:pass":862,"advcl":759,"obj":570,"compound":209,"discourse":89,"csubj":88,"compound:prt":82,"iobj":77,"xcomp":53,"acl||nsubj":51,"dep":0},"3":{"punct":25614,"obl":11546,"obj":10260,"nmod":10034,"conj":9330,"advmod":4272,"flat:name":4139,"nsubj":3716,"advcl":3239,"xcomp":3101,"acl:relcl":3068,"compound:prt":1935,"ccomp":1747,"acl":1253,"parataxis":1100,"csubj":693,"appos":625,"iobj":469,"expl":457,"flat:foreign":364,"amod":326,"acl:cleft":255,"cop":192,"det":179,"orphan":161,"advcl||advmod":161,"acl||nsubj":161,"case||obl":125,"obl||advmod":86,"nsubj:pass":81,"obl||amod":64,"obl||det":56,"appos||nsubj":38,"acl||nsubj:pass":34,"compound":33,"dep":0},"4":{"ROOT":15683}}�cfg��neg_key�
|
tagger/cfg
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"labels":[
|
| 3 |
+
"ADJ",
|
| 4 |
+
"ADP",
|
| 5 |
+
"ADV",
|
| 6 |
+
"AUX",
|
| 7 |
+
"CCONJ",
|
| 8 |
+
"DET",
|
| 9 |
+
"INTJ",
|
| 10 |
+
"NOUN",
|
| 11 |
+
"NUM",
|
| 12 |
+
"PART",
|
| 13 |
+
"PRON",
|
| 14 |
+
"PROPN",
|
| 15 |
+
"PUNCT",
|
| 16 |
+
"SCONJ",
|
| 17 |
+
"SYM",
|
| 18 |
+
"VERB",
|
| 19 |
+
"X"
|
| 20 |
+
]
|
| 21 |
+
}
|
tagger/model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0840ef807b3396b25639eb0b4cfe7d64abfc938b11fe9cef6afd6647df5384e1
|
| 3 |
+
size 52880
|
tokenizer
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
��prefix_search�{^§|^%|^=|^—|^–|^\+(?![0-9])|^…|^……|^,|^:|^;|^\!|^\?|^¿|^؟|^¡|^\(|^\)|^\[|^\]|^\{|^\}|^<|^>|^_|^\*|^&|^。|^?|^!|^,|^、|^;|^:|^~|^·|^।|^،|^۔|^؛|^٪|^\.\.+|^…|^\'|^"|^”|^“|^`|^‘|^´|^’|^‚|^,|^„|^»|^«|^「|^」|^『|^』|^(|^)|^〔|^〕|^【|^】|^《|^》|^〈|^〉|^\$|^£|^€|^¥|^฿|^US\$|^C\$|^A\$|^₽|^﷼|^₴|^₠|^₡|^₢|^₣|^₤|^₥|^₦|^₧|^₨|^₩|^₪|^₫|^€|^₭|^₮|^₯|^₰|^₱|^₲|^₳|^₴|^₵|^₶|^₷|^₸|^₹|^₺|^₻|^₼|^₽|^₾|^₿|^[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]�suffix_search�2…$|……$|,$|:$|;$|\!$|\?$|¿$|؟$|¡$|\($|\)$|\[$|\]$|\{$|\}$|<$|>$|_$|#$|\*$|&$|。$|?$|!$|,$|、$|;$|:$|~$|·$|।$|،$|۔$|؛$|٪$|\.\.+$|…$|"$|”$|“$|`$|‘$|´$|’$|‚$|,$|„$|»$|«$|「$|」$|『$|』$|($|)$|〔$|〕$|【$|】$|《$|》$|〈$|〉$|[\u00A6\u00A9\u00AE\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]$|—$|–$|(?<=[0-9])\+$|(?<=°[FfCcKk])\.$|(?<=[0-9])(?:\$|£|€|¥|฿|US\$|C\$|A\$|₽|﷼|₴|₠|₡|₢|₣|₤|₥|₦|₧|₨|₩|₪|₫|€|₭|₮|₯|₰|₱|₲|₳|₴|₵|₶|₷|₸|₹|₺|₻|₼|₽|₾|₿)$|(?<=[0-9])(?:km|km²|km³|m|m²|m³|dm|dm²|dm³|cm|cm²|cm³|mm|mm²|mm³|ha|µm|nm|yd|in|ft|kg|g|mg|µg|t|lb|oz|m/s|km/h|kmh|mph|hPa|Pa|mbar|mb|MB|kb|KB|gb|GB|tb|TB|T|G|M|K|%|км|км²|км³|м|м²|м³|дм|дм²|дм³|см|см²|см³|мм|мм²|мм³|нм|кг|г|мг|м/с|км/ч|кПа|Па|мбар|Кб|КБ|кб|Мб|МБ|мб|Гб|ГБ|гб|Тб|ТБ|тбكم|كم²|كم³|م|م²|م³|سم|سم²|سم³|مم|مم²|مم³|كم|غرام|جرام|جم|كغ|ملغ|كوب|اكواب)$|(?<=[a-z\uFF41-\uFF5A\u00DF-\u00F6\u00F8-\u00FF\u0101\u0103\u0105\u0107\u0109\u010B\u010D\u010F\u0111\u0113\u0115\u0117\u0119\u011B\u011D\u011F\u0121\u0123\u0125\u0127\u0129\u012B\u012D\u012F\u0131\u0133\u0135\u0137\u0138\u013A\u013C\u013E\u0140\u0142\u0144\u0146\u0148\u0149\u014B\u014D\u014F\u0151\u0153\u0155\u0157\u0159\u015B\u015D\u015F\u0161\u0163\u0165\u0167\u0169\u016B\u016D\u016F\u0171\u0173\u0175\u0177\u017A\u017C\u017E\u017F\u0180\u0183\u0185\u0188\u018C\u018D\u0192\u0195\u0199-\u019B\u019E\u01A1\u01A3\u01A5\u01A8\u01AA\u01AB\u01AD\u01B0\u01B4\u01B6\u01B9\u01BA\u01BD-\u01BF\u01C6\u01C9\u01CC\u01CE\u01D0\u01D2\u01D4\u01D6\u01D8\u01DA\u01DC\u01DD\u01DF\u01E1\u01E3\u01E5\u01E7\u01E9\u01EB\u01ED\u01EF\u01F0\u01F3\u01F5\u01F9\u01FB\u01FD\u01FF\u0201\u0203\u0205\u0207\u0209\u020B\u020D\u020F\u0211\u0213\u0215\u0217\u0219\u021B\u021D\u021F\u0221\u0223\u0225\u0227\u0229\u022B\u022D\u022F\u0231\u0233-\u0239\u023C\u023F\u0240\u0242\u0247\u0249\u024B\u024D\u024F\u2C61\u2C65\u2C66\u2C68\u2C6A\u2C6C\u2C71\u2C73\u2C74\u2C76-\u2C7B\uA723\uA725\uA727\uA729\uA72B\uA72D\uA72F-\uA731\uA733\uA735\uA737\uA739\uA73B\uA73D\uA73F\uA741\uA743\uA745\uA747\uA749\uA74B\uA74D\uA74F\uA751\uA753\uA755\uA757\uA759\uA75B\uA75D\uA75F\uA761\uA763\uA765\uA767\uA769\uA76B\uA76D\uA76F\uA771-\uA778\uA77A\uA77C\uA77F\uA781\uA783\uA785\uA787\uA78C\uA78E\uA791\uA793-\uA795\uA797\uA799\uA79B\uA79D\uA79F\uA7A1\uA7A3\uA7A5\uA7A7\uA7A9\uA7AF\uA7B5\uA7B7\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E01\u1E03\u1E05\u1E07\u1E09\u1E0B\u1E0D\u1E0F\u1E11\u1E13\u1E15\u1E17\u1E19\u1E1B\u1E1D\u1E1F\u1E21\u1E23\u1E25\u1E27\u1E29\u1E2B\u1E2D\u1E2F\u1E31\u1E33\u1E35\u1E37\u1E39\u1E3B\u1E3D\u1E3F\u1E41\u1E43\u1E45\u1E47\u1E49\u1E4B\u1E4D\u1E4F\u1E51\u1E53\u1E55\u1E57\u1E59\u1E5B\u1E5D\u1E5F\u1E61\u1E63\u1E65\u1E67\u1E69\u1E6B\u1E6D\u1E6F\u1E71\u1E73\u1E75\u1E77\u1E79\u1E7B\u1E7D\u1E7F\u1E81\u1E83\u1E85\u1E87\u1E89\u1E8B\u1E8D\u1E8F\u1E91\u1E93\u1E95-\u1E9D\u1E9F\u1EA1\u1EA3\u1EA5\u1EA7\u1EA9\u1EAB\u1EAD\u1EAF\u1EB1\u1EB3\u1EB5\u1EB7\u1EB9\u1EBB\u1EBD\u1EBF\u1EC1\u1EC3\u1EC5\u1EC7\u1EC9\u1ECB\u1ECD\u1ECF\u1ED1\u1ED3\u1ED5\u1ED7\u1ED9\u1EDB\u1EDD\u1EDF\u1EE1\u1EE3\u1EE5\u1EE7\u1EE9\u1EEB\u1EED\u1EEF\u1EF1\u1EF3\u1EF5\u1EF7\u1EF9\u1EFB\u1EFD\u1EFFёа-яәөүҗңһα-ωάέίόώήύа-щюяіїєґѓѕјљњќѐѝ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F%²\-\+…|……|,|:|;|\!|\?|¿|؟|¡|\(|\)|\[|\]|\{|\}|<|>|_|#|\*|&|。|?|!|,|、|;|:|~|·|।|،|۔|؛|٪(?:\"”“`‘´’‚,„»«「」『』()〔〕【】《》〈〉)])\.$|(?<=[A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F][A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])\.$|(?<=[^sSxXzZ])'$�infix_finditer�O�\.\.+|…|[\u00A6\u00A9\u00AE\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]|(?<=[a-z\uFF41-\uFF5A\u00DF-\u00F6\u00F8-\u00FF\u0101\u0103\u0105\u0107\u0109\u010B\u010D\u010F\u0111\u0113\u0115\u0117\u0119\u011B\u011D\u011F\u0121\u0123\u0125\u0127\u0129\u012B\u012D\u012F\u0131\u0133\u0135\u0137\u0138\u013A\u013C\u013E\u0140\u0142\u0144\u0146\u0148\u0149\u014B\u014D\u014F\u0151\u0153\u0155\u0157\u0159\u015B\u015D\u015F\u0161\u0163\u0165\u0167\u0169\u016B\u016D\u016F\u0171\u0173\u0175\u0177\u017A\u017C\u017E\u017F\u0180\u0183\u0185\u0188\u018C\u018D\u0192\u0195\u0199-\u019B\u019E\u01A1\u01A3\u01A5\u01A8\u01AA\u01AB\u01AD\u01B0\u01B4\u01B6\u01B9\u01BA\u01BD-\u01BF\u01C6\u01C9\u01CC\u01CE\u01D0\u01D2\u01D4\u01D6\u01D8\u01DA\u01DC\u01DD\u01DF\u01E1\u01E3\u01E5\u01E7\u01E9\u01EB\u01ED\u01EF\u01F0\u01F3\u01F5\u01F9\u01FB\u01FD\u01FF\u0201\u0203\u0205\u0207\u0209\u020B\u020D\u020F\u0211\u0213\u0215\u0217\u0219\u021B\u021D\u021F\u0221\u0223\u0225\u0227\u0229\u022B\u022D\u022F\u0231\u0233-\u0239\u023C\u023F\u0240\u0242\u0247\u0249\u024B\u024D\u024F\u2C61\u2C65\u2C66\u2C68\u2C6A\u2C6C\u2C71\u2C73\u2C74\u2C76-\u2C7B\uA723\uA725\uA727\uA729\uA72B\uA72D\uA72F-\uA731\uA733\uA735\uA737\uA739\uA73B\uA73D\uA73F\uA741\uA743\uA745\uA747\uA749\uA74B\uA74D\uA74F\uA751\uA753\uA755\uA757\uA759\uA75B\uA75D\uA75F\uA761\uA763\uA765\uA767\uA769\uA76B\uA76D\uA76F\uA771-\uA778\uA77A\uA77C\uA77F\uA781\uA783\uA785\uA787\uA78C\uA78E\uA791\uA793-\uA795\uA797\uA799\uA79B\uA79D\uA79F\uA7A1\uA7A3\uA7A5\uA7A7\uA7A9\uA7AF\uA7B5\uA7B7\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E01\u1E03\u1E05\u1E07\u1E09\u1E0B\u1E0D\u1E0F\u1E11\u1E13\u1E15\u1E17\u1E19\u1E1B\u1E1D\u1E1F\u1E21\u1E23\u1E25\u1E27\u1E29\u1E2B\u1E2D\u1E2F\u1E31\u1E33\u1E35\u1E37\u1E39\u1E3B\u1E3D\u1E3F\u1E41\u1E43\u1E45\u1E47\u1E49\u1E4B\u1E4D\u1E4F\u1E51\u1E53\u1E55\u1E57\u1E59\u1E5B\u1E5D\u1E5F\u1E61\u1E63\u1E65\u1E67\u1E69\u1E6B\u1E6D\u1E6F\u1E71\u1E73\u1E75\u1E77\u1E79\u1E7B\u1E7D\u1E7F\u1E81\u1E83\u1E85\u1E87\u1E89\u1E8B\u1E8D\u1E8F\u1E91\u1E93\u1E95-\u1E9D\u1E9F\u1EA1\u1EA3\u1EA5\u1EA7\u1EA9\u1EAB\u1EAD\u1EAF\u1EB1\u1EB3\u1EB5\u1EB7\u1EB9\u1EBB\u1EBD\u1EBF\u1EC1\u1EC3\u1EC5\u1EC7\u1EC9\u1ECB\u1ECD\u1ECF\u1ED1\u1ED3\u1ED5\u1ED7\u1ED9\u1EDB\u1EDD\u1EDF\u1EE1\u1EE3\u1EE5\u1EE7\u1EE9\u1EEB\u1EED\u1EEF\u1EF1\u1EF3\u1EF5\u1EF7\u1EF9\u1EFB\u1EFD\u1EFFёа-яәөүҗңһα-ωάέίόώήύа-щюяіїєґѓѕјљњќѐѝ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])\.(?=[A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])[,!?](?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])[:<>=/](?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F]),(?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])([\"”“`‘´’‚,„»«「」『』()〔〕【】《》〈〉\)\]\(\[])(?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])--(?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])�token_match��url_match�
|
| 2 |
+
��A�
|
| 3 |
+
� ��A� �'��A�'�''��A�''�(*_*)��A�(*_*)�(-8��A�(-8�(-:��A�(-:�(-;��A�(-;�(-_-)��A�(-_-)�(._.)��A�(._.)�(:��A�(:�(;��A�(;�(=��A�(=�(>_<)��A�(>_<)�(^_^)��A�(^_^)�(o:��A�(o:�(¬_¬)��A�(¬_¬)�(ಠ_ಠ)��A�(ಠ_ಠ)�(╯°□°)╯︵┻━┻��A�(╯°□°)╯︵┻━┻�)-:��A�)-:�):��A�):�-_-��A�-_-�-__-��A�-__-�._.��A�._.�0.0��A�0.0�0.o��A�0.o�0_0��A�0_0�0_o��A�0_o�8)��A�8)�8-)��A�8-)�8-D��A�8-D�8D��A�8D�:'(��A�:'(�:')��A�:')�:'-(��A�:'-(�:'-)��A�:'-)�:(��A�:(�:((��A�:((�:(((��A�:(((�:()��A�:()�:)��A�:)�:))��A�:))�:)))��A�:)))�:*��A�:*�:-(��A�:-(�:-((��A�:-((�:-(((��A�:-(((�:-)��A�:-)�:-))��A�:-))�:-)))��A�:-)))�:-*��A�:-*�:-/��A�:-/�:-0��A�:-0�:-3��A�:-3�:->��A�:->�:-D��A�:-D�:-O��A�:-O�:-P��A�:-P�:-X��A�:-X�:-]��A�:-]�:-o��A�:-o�:-p��A�:-p�:-x��A�:-x�:-|��A�:-|�:-}��A�:-}�:/��A�:/�:0��A�:0�:1��A�:1�:3��A�:3�:>��A�:>�:D��A�:D�:O��A�:O�:P��A�:P�:X��A�:X�:]��A�:]�:o��A�:o�:o)��A�:o)�:p��A�:p�:x��A�:x�:|��A�:|�:}��A�:}�:’(��A�:’(�:’)��A�:’)�:’-(��A�:’-(�:’-)��A�:’-)�;)��A�;)�;-)��A�;-)�;-D��A�;-D�;D��A�;D�;_;��A�;_;�<.<��A�<.<�</3��A�</3�<3��A�<3�<33��A�<33�<333��A�<333�<space>��A�<space>�=(��A�=(�=)��A�=)�=/��A�=/�=3��A�=3�=D��A�=D�=[��A�=[�=]��A�=]�=|��A�=|�>.<��A�>.<�>.>��A�>.>�>:(��A�>:(�>:o��A�>:o�><(((*>��A�><(((*>�@_@��A�@_@�Ap.��A�Ap.�Aq.��A�Aq.�C++��A�C++�Ca.��A�Ca.�Chr.��A�Chr.�Co.��A�Co.�Dr.��A�Dr.�F.eks.��A�F.eks.�Fr.p.��A�Fr.p.�Frp.��A�Frp.�Grl.��A�Grl.�Kr.��A�Kr.�Kr.F.��A�Kr.F.�Kr.F.s��A�Kr.F.s�Mr.��A�Mr.�Mrs.��A�Mrs.�O.O��A�O.O�O.o��A�O.o�O_O��A�O_O�O_o��A�O_o�Pb.��A�Pb.�Pr.��A�Pr.�Sp.��A�Sp.�St.��A�St.�V.V��A�V.V�V_V��A�V_V�XD��A�XD�XDD��A�XDD�[-:��A�[-:�[:��A�[:�[=��A�[=�\")��A�\")�\n��A�\n�\t��A�\t�]=��A�]=�^_^��A�^_^�^__^��A�^__^�^___^��A�^___^�a.��A�a.�a.m.��A�a.m.�ad.��A�ad.�adm.dir.��A�adm.dir.�andelsnr��A�andelsnr�apr.��A�apr.C�april�aug.��A�aug.C�august�b.��A�b.�b.c.��A�b.c.�bl.a.��A�bl.a.�bla.��A�bla.�bm.��A�bm.�bnr.��A�bnr.�bto.��A�bto.�c.��A�c.�c.c.��A�c.c.�ca.��A�ca.�cand.mag.��A�cand.mag.�co.��A�co.�d.��A�d.�d.d.��A�d.d.�d.m.��A�d.m.�d.y.��A�d.y.�dept.��A�dept.�des.��A�des.C�desember�dr.��A�dr.�dr.med.��A�dr.med.�dr.philos.��A�dr.philos.�dr.psychol.��A�dr.psychol.�dvs.��A�dvs.�e.��A�e.�e.Kr.��A�e.Kr.�e.l.��A�e.l.�eg.��A�eg.�ekskl.��A�ekskl.�el.��A�el.�et.��A�et.�etc.��A�etc.�etg.��A�etg.�ev.��A�ev.�evt.��A�evt.�f.��A�f.�f.Kr.��A�f.Kr.�f.eks.��A�f.eks.�f.o.m.��A�f.o.m.�feb.��A�feb.C�februar�fhv.��A�fhv.�fk.��A�fk.�foreg.��A�foreg.�fork.��A�fork.�fv.��A�fv.�fvt.��A�fvt.�g.��A�g.�gl.��A�gl.�gno.��A�gno.�gnr.��A�gnr.�grl.��A�grl.�gt.��A�gt.�h.��A�h.�h.r.adv.��A�h.r.adv.�hhv.��A�hhv.�hoh.��A�hoh.�hr.��A�hr.�i.��A�i.�ifb.��A�ifb.�ifm.��A�ifm.�iht.��A�iht.�inkl.��A�inkl.�istf.��A�istf.�j.��A�j.�jan.��A�jan.C�januar�jf.��A�jf.�jr.��A�jr.�jul.��A�jul.C�juli�jun.��A�jun.�juris.��A�juris.�k.��A�k.�kfr.��A�kfr.�kgl.��A�kgl.�kgl.res.��A�kgl.res.�kl.��A�kl.�komm.��A�komm.�kr.��A�kr.�kst.��A�kst.�l.��A�l.�lat.��A�lat.�lø.��A�lø.�m.��A�m.�m.a.o.��A�m.a.o.�m.fl.��A�m.fl.�m.m.��A�m.m.�m.v.��A�m.v.�ma.��A�ma.�mag.art.��A�mag.art.�mar.��A�mar.C�mars�md.��A�md.�mfl.��A�mfl.�mht.��A�mht.�mill.��A�mill.�min.��A�min.�mnd.��A�mnd.�moh.��A�moh.�mrd.��A�mrd.�muh.��A�muh.�mv.��A�mv.�mva.��A�mva.�n.��A�n.�n.å.��A�n.å.�ndf.��A�ndf.�no.��A�no.�nov.��A�nov.�nr.��A�nr.�nto.��A�nto.�nyno.��A�nyno.�o.��A�o.�o.0��A�o.0�o.O��A�o.O�o.a.��A�o.a.�o.l.��A�o.l.�o.o��A�o.o�o_0��A�o_0�o_O��A�o_O�o_o��A�o_o�off.��A�off.�ofl.��A�ofl.�okt.��A�okt.�on.��A�on.�op.��A�op.�org.��A�org.�osv.��A�osv.�ovf.��A�ovf.�p.��A�p.�p.a.��A�p.a.�p.g.a.��A�p.g.a.�p.m.��A�p.m.�p.t.��A�p.t.�pga.��A�pga.�ph.d.��A�ph.d.�pkt.��A�pkt.�pr.��A�pr.�pst.��A�pst.�pt.��A�pt.�q.��A�q.�r.��A�r.�red.anm.��A�red.anm.�ref.��A�ref.�res.��A�res.�res.kap.��A�res.kap.�resp.��A�resp.�rv.��A�rv.�s.��A�s.�s.d.��A�s.d.�s.k.��A�s.k.�s.u.��A�s.u.�s.å.��A�s.å.�sen.��A�sen.�sep.��A�sep.�siviling.��A�siviling.�sms.��A�sms.�snr.��A�snr.�spm.��A�spm.�sr.��A�sr.�sst.��A�sst.�st.��A�st.�st.meld.��A�st.meld.�st.prp.��A�st.prp.�stip.��A�stip.�stk.��A�stk.�stud.��A�stud.�sv.��A�sv.�såk.��A�såk.�sø.��A�sø.�t.��A�t.�t.h.��A�t.h.�t.o.m.��A�t.o.m.�t.v.��A�t.v.�temp.��A�temp.�ti.��A�ti.�tils.��A�tils.�tilsv.��A�tilsv.�tl;dr��A�tl;dr�tlf.��A�tlf.�to.��A�to.�u.��A�u.�ult.��A�ult.�utg.��A�utg.�v.��A�v.�v.v��A�v.v�v_v��A�v_v�vedk.��A�vedk.�vedr.��A�vedr.�vg.��A�vg.�vgs.��A�vgs.�vha.��A�vha.�vit.ass.��A�vit.ass.�vn.��A�vn.�vol.��A�vol.�vs.��A�vs.�vsa.��A�vsa.�w.��A�w.�x.��A�x.�xD��A�xD�xDD��A�xDD�y.��A�y.�z.��A�z.� ��A� C� �§§��A�§§�©NTB��A�©NTB�¯\(ツ)/¯��A�¯\(ツ)/¯�ä.��A�ä.�årg.��A�årg.�årh.��A�årh.�ö.��A�ö.�ü.��A�ü.�ಠ_ಠ��A�ಠ_ಠ�ಠ︵ಠ��A�ಠ︵ಠ�—��A�—�’��A�’�’’��A�’’
|
transformer/cfg
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_batch_items":4096
|
| 3 |
+
}
|
transformer/model/config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "ltgoslo/norbert",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"gradient_checkpointing": false,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"pad_token_id": 0,
|
| 19 |
+
"position_embedding_type": "absolute",
|
| 20 |
+
"transformers_version": "4.9.1",
|
| 21 |
+
"type_vocab_size": 2,
|
| 22 |
+
"use_cache": true,
|
| 23 |
+
"vocab_size": 32922
|
| 24 |
+
}
|
transformer/model/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f880a01bde528523a62a90c25453a31cb5588d46c9cac86837922f5dd7d6049
|
| 3 |
+
size 445383089
|
transformer/model/special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
transformer/model/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
transformer/model/tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/home/radbrt/.cache/huggingface/transformers/347a652456195f970ad34f0e57ae6e3c37d136a77b7a2e972dbb56f5e0b7d27a.750293617705dd39d21eef1e163d80ca5b23e1a0ec507fff24a087c44632142c", "name_or_path": "ltgoslo/norbert", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
|
transformer/model/vocab.txt
ADDED
|
Binary file (261 kB). View file
|
|
|
vocab/key2row
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
�
|
vocab/lookups.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
|
| 3 |
+
size 1
|
vocab/strings.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:661bbbc6637c8d0d603945681d6af5a509b74443843cac2bd7151d7b47fd1ff4
|
| 3 |
+
size 784112
|
vocab/vectors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14772b683e726436d5948ad3fff2b43d036ef2ebbe3458aafed6004e05a40706
|
| 3 |
+
size 128
|