janko commited on
Commit
7771474
1 Parent(s): ddf283e

Update spaCy pipeline

Browse files
.gitattributes CHANGED
@@ -32,3 +32,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ frequency_lemmatizer/table.json filter=lfs diff=lfs merge=lfs -text
36
+ grc_odycy_joint_trf-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
37
+ morphologizer/model filter=lfs diff=lfs merge=lfs -text
38
+ parser/model filter=lfs diff=lfs merge=lfs -text
39
+ tagger/model filter=lfs diff=lfs merge=lfs -text
40
+ trainable_lemmatizer/model filter=lfs diff=lfs merge=lfs -text
41
+ trainable_lemmatizer/trees filter=lfs diff=lfs merge=lfs -text
42
+ transformer/model filter=lfs diff=lfs merge=lfs -text
README.md ADDED
The diff for this file is too large to render. See raw diff
 
config.cfg ADDED
@@ -0,0 +1,228 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [paths]
2
+ train = "corpus/joint/train.spacy"
3
+ test = "corpus/test.spacy"
4
+ dev = "corpus/joint/dev.spacy"
5
+ vectors = null
6
+ init_tok2vec = null
7
+
8
+ [system]
9
+ gpu_allocator = "pytorch"
10
+ seed = 0
11
+
12
+ [nlp]
13
+ lang = "grc"
14
+ pipeline = ["transformer","tagger","morphologizer","parser","trainable_lemmatizer","frequency_lemmatizer"]
15
+ batch_size = 1024
16
+ disabled = []
17
+ before_creation = null
18
+ after_creation = null
19
+ after_pipeline_creation = null
20
+ tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
21
+
22
+ [components]
23
+
24
+ [components.frequency_lemmatizer]
25
+ factory = "frequency_lemmatizer"
26
+ fallback_priority = "lookup"
27
+ overwrite = true
28
+
29
+ [components.morphologizer]
30
+ factory = "morphologizer"
31
+ extend = false
32
+ overwrite = true
33
+ scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
34
+
35
+ [components.morphologizer.model]
36
+ @architectures = "spacy.Tagger.v2"
37
+ nO = null
38
+ normalize = false
39
+
40
+ [components.morphologizer.model.tok2vec]
41
+ @architectures = "spacy-transformers.TransformerListener.v1"
42
+ grad_factor = 1.0
43
+ pooling = {"@layers":"reduce_mean.v1"}
44
+ upstream = "*"
45
+
46
+ [components.parser]
47
+ factory = "parser"
48
+ learn_tokens = false
49
+ min_action_freq = 30
50
+ moves = null
51
+ scorer = {"@scorers":"spacy.parser_scorer.v1"}
52
+ update_with_oracle_cut_size = 100
53
+
54
+ [components.parser.model]
55
+ @architectures = "spacy.TransitionBasedParser.v2"
56
+ state_type = "parser"
57
+ extra_state_tokens = false
58
+ hidden_width = 128
59
+ maxout_pieces = 3
60
+ use_upper = true
61
+ nO = null
62
+
63
+ [components.parser.model.tok2vec]
64
+ @architectures = "spacy-transformers.TransformerListener.v1"
65
+ grad_factor = 1.0
66
+ pooling = {"@layers":"reduce_mean.v1"}
67
+ upstream = "*"
68
+
69
+ [components.tagger]
70
+ factory = "tagger"
71
+ neg_prefix = "!"
72
+ overwrite = false
73
+ scorer = {"@scorers":"spacy.tagger_scorer.v1"}
74
+
75
+ [components.tagger.model]
76
+ @architectures = "spacy.Tagger.v2"
77
+ nO = null
78
+ normalize = false
79
+
80
+ [components.tagger.model.tok2vec]
81
+ @architectures = "spacy-transformers.TransformerListener.v1"
82
+ grad_factor = 1.0
83
+ pooling = {"@layers":"reduce_mean.v1"}
84
+ upstream = "*"
85
+
86
+ [components.trainable_lemmatizer]
87
+ factory = "trainable_lemmatizer"
88
+ backoff = "orth"
89
+ min_tree_freq = 1
90
+ overwrite = false
91
+ scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
92
+ top_k = 3
93
+
94
+ [components.trainable_lemmatizer.model]
95
+ @architectures = "spacy.Tagger.v2"
96
+ nO = null
97
+ normalize = false
98
+
99
+ [components.trainable_lemmatizer.model.tok2vec]
100
+ @architectures = "spacy-transformers.TransformerListener.v1"
101
+ grad_factor = 1.0
102
+ pooling = {"@layers":"reduce_mean.v1"}
103
+ upstream = "*"
104
+
105
+ [components.transformer]
106
+ factory = "transformer"
107
+ max_batch_items = 4096
108
+ set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
109
+
110
+ [components.transformer.model]
111
+ @architectures = "spacy-transformers.TransformerModel.v3"
112
+ name = "pranaydeeps/Ancient-Greek-BERT"
113
+ mixed_precision = false
114
+
115
+ [components.transformer.model.get_spans]
116
+ @span_getters = "spacy-transformers.strided_spans.v1"
117
+ window = 128
118
+ stride = 96
119
+
120
+ [components.transformer.model.grad_scaler_config]
121
+
122
+ [components.transformer.model.tokenizer_config]
123
+ use_fast = true
124
+
125
+ [components.transformer.model.transformer_config]
126
+
127
+ [corpora]
128
+
129
+ [corpora.dev]
130
+ @readers = "spacy.Corpus.v1"
131
+ path = ${paths.dev}
132
+ max_length = 0
133
+ gold_preproc = false
134
+ limit = 0
135
+ augmenter = null
136
+
137
+ [corpora.train]
138
+ @readers = "spacy.Corpus.v1"
139
+ path = ${paths.train}
140
+ max_length = 0
141
+ gold_preproc = false
142
+ limit = 0
143
+ augmenter = null
144
+
145
+ [training]
146
+ accumulate_gradient = 3
147
+ dev_corpus = "corpora.dev"
148
+ train_corpus = "corpora.train"
149
+ seed = ${system.seed}
150
+ gpu_allocator = ${system.gpu_allocator}
151
+ dropout = 0.1
152
+ patience = 1600
153
+ max_epochs = 0
154
+ max_steps = 20000
155
+ eval_frequency = 200
156
+ frozen_components = []
157
+ annotating_components = []
158
+ before_to_disk = null
159
+ before_update = null
160
+
161
+ [training.batcher]
162
+ @batchers = "spacy.batch_by_padded.v1"
163
+ discard_oversize = true
164
+ size = 2000
165
+ buffer = 256
166
+ get_length = null
167
+
168
+ [training.logger]
169
+ @loggers = "spacy.WandbLogger.v3"
170
+ project_name = "homerCy"
171
+ remove_config_values = []
172
+ model_log_interval = null
173
+ log_dataset_dir = null
174
+ entity = null
175
+ run_name = null
176
+
177
+ [training.optimizer]
178
+ @optimizers = "Adam.v1"
179
+ beta1 = 0.9
180
+ beta2 = 0.999
181
+ L2_is_weight_decay = true
182
+ L2 = 0.01
183
+ grad_clip = 1.0
184
+ use_averages = true
185
+ eps = 0.00000001
186
+
187
+ [training.optimizer.learn_rate]
188
+ @schedules = "warmup_linear.v1"
189
+ warmup_steps = 250
190
+ total_steps = 20000
191
+ initial_rate = 0.00005
192
+
193
+ [training.score_weights]
194
+ tag_acc = 0.21
195
+ pos_acc = 0.1
196
+ morph_acc = 0.1
197
+ morph_per_feat = null
198
+ dep_uas = 0.1
199
+ dep_las = 0.1
200
+ dep_las_per_type = null
201
+ sents_p = null
202
+ sents_r = null
203
+ sents_f = 0.0
204
+ lemma_acc = 0.4
205
+
206
+ [pretraining]
207
+
208
+ [initialize]
209
+ vectors = ${paths.vectors}
210
+ init_tok2vec = ${paths.init_tok2vec}
211
+ vocab_data = null
212
+ lookups = null
213
+ before_init = null
214
+ after_init = null
215
+
216
+ [initialize.components]
217
+
218
+ [initialize.components.frequency_lemmatizer]
219
+
220
+ [initialize.components.frequency_lemmatizer.lookup]
221
+ @readers = "srsly.read_json.v1"
222
+ path = "assets/lemmas/lemma_lookup.json"
223
+
224
+ [initialize.components.frequency_lemmatizer.table]
225
+ @readers = "srsly.read_json.v1"
226
+ path = "assets/lemmas/lemma_table.json"
227
+
228
+ [initialize.tokenizer]
frequency_lemmatizer/config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"overwrite": true, "fallback_priority": "lookup"}
frequency_lemmatizer/lookup.json ADDED
The diff for this file is too large to render. See raw diff
 
frequency_lemmatizer/table.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b4678164e1be8f5de58fea33c1a25f57c348012986f69762dc6fde547f955ad
3
+ size 26885581
grc_odycy_joint_trf-any-py3-none-any.whl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e72e0180d0f56c1ace27f38f3c147c04190263fecc8d31d030662dfcc0f83164
3
+ size 497308444
lemmatizer.py ADDED
@@ -0,0 +1,271 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import os
2
+ import json
3
+ from pathlib import Path
4
+ from typing import Dict, List, Literal, Optional, Union, Iterable
5
+ from typing_extensions import TypedDict, NotRequired
6
+
7
+ from spacy.language import Language
8
+ from spacy.pipeline import Pipe
9
+ from spacy.pipeline.lemmatizer import lemmatizer_score
10
+ from spacy.util import ensure_path
11
+ from spacy.tokens import Doc, Token
12
+
13
+ MATCH_ORDER = [
14
+ "upos",
15
+ "Tense",
16
+ "VerbForm",
17
+ "Voice",
18
+ "Case",
19
+ "Gender",
20
+ "Number",
21
+ "Degree",
22
+ "Mood",
23
+ "Person",
24
+ "Aspect",
25
+ "Definite",
26
+ "PronType",
27
+ "Polarity",
28
+ "Poss",
29
+ "Reflex",
30
+ ]
31
+
32
+
33
+ class TableEntry(TypedDict):
34
+ form: str
35
+ lemma: str
36
+ upos: str
37
+ frequency: int
38
+ Tense: NotRequired[str]
39
+ VerbForm: NotRequired[str]
40
+ Voice: NotRequired[str]
41
+ Case: NotRequired[str]
42
+ Gender: NotRequired[str]
43
+ Number: NotRequired[str]
44
+ Degree: NotRequired[str]
45
+ Mood: NotRequired[str]
46
+ Person: NotRequired[str]
47
+ Aspect: NotRequired[str]
48
+ Definite: NotRequired[str]
49
+ PronType: NotRequired[str]
50
+ Polarity: NotRequired[str]
51
+ Poss: NotRequired[str]
52
+ Reflex: NotRequired[str]
53
+
54
+
55
+ FrequencyTable = Dict[str, List[TableEntry]]
56
+
57
+ LookupTable = Dict[str, str]
58
+
59
+
60
+ @Language.factory(
61
+ "frequency_lemmatizer",
62
+ assigns=["token.lemma"],
63
+ default_config={
64
+ "overwrite": True,
65
+ "fallback_priority": "lookup",
66
+ },
67
+ default_score_weights={"lemma_acc": 1.0},
68
+ )
69
+ def make_lemmatizer(
70
+ nlp: Language,
71
+ name: str,
72
+ overwrite: bool,
73
+ fallback_priority: Literal["lemma", "lookup"],
74
+ ):
75
+ return FrequencyLemmatizer(
76
+ nlp=nlp,
77
+ name=name,
78
+ overwrite=overwrite,
79
+ fallback_priority=fallback_priority,
80
+ ) # type: ignore
81
+
82
+
83
+ def max_freq_lemma(entries: List[TableEntry]) -> str:
84
+ """Returns lemma with highest frequency from the given entries."""
85
+ max_index = 0
86
+ n_entries = len(entries)
87
+ for index in range(1, n_entries):
88
+ if entries[index]["frequency"] > entries[max_index]["frequency"]:
89
+ max_index = index
90
+ return entries[max_index]["lemma"]
91
+
92
+
93
+ def match_lemma(
94
+ token_entry: TableEntry, table: FrequencyTable
95
+ ) -> Optional[str]:
96
+ """Returns a lemma for a token if it
97
+ can be found in the frequency table.
98
+ """
99
+ # Tries to find the entries associated with the token in the table
100
+ match = table.get(token_entry["form"], [])
101
+ if not match:
102
+ return None
103
+ # We go through all the properties to be matched
104
+ for match_property in MATCH_ORDER:
105
+ match_new = [
106
+ entry
107
+ for entry in match
108
+ if entry.get(match_property, "")
109
+ == token_entry.get(match_property, "")
110
+ ]
111
+ if not match_new:
112
+ return max_freq_lemma(entries=match)
113
+ match = match_new
114
+ return max_freq_lemma(entries=match)
115
+
116
+
117
+ def read_json(path: str) -> Dict:
118
+ with open(path) as file:
119
+ res = json.load(file)
120
+ return res
121
+
122
+
123
+ def write_json(object: Dict, path: str) -> None:
124
+ with open(path, "w") as file:
125
+ json.dump(object, file)
126
+
127
+
128
+ class FrequencyLemmatizer(Pipe):
129
+ """
130
+ Part-of-speech and morphology, and frequency
131
+ sensitive rule-based lemmatizer.
132
+
133
+ Parameters
134
+ ----------
135
+ overwrite: bool, default True
136
+ Specifies whether the frequency lemmatizer should overwrite
137
+ already assigned lemmas.
138
+ fallback_priority: 'lemma' or 'lookup', default 'lookup'
139
+ Specifies which fallback should have higher priority
140
+ if the lemma is not found in
141
+ the primary table.
142
+ """
143
+
144
+ def __init__(
145
+ self,
146
+ nlp: Language,
147
+ name: str = "freq_lemmatizer",
148
+ *,
149
+ overwrite: bool = True,
150
+ fallback_priority: Literal["lemma", "lookup"] = "lookup",
151
+ ):
152
+ self.name = name
153
+ self.overwrite = overwrite
154
+ self.scorer = lemmatizer_score
155
+ self.fallback_priority = fallback_priority
156
+
157
+ def initialize(
158
+ self,
159
+ get_examples=None,
160
+ *,
161
+ nlp=None,
162
+ table: Optional[FrequencyTable] = None,
163
+ lookup: Optional[LookupTable] = None,
164
+ ) -> None:
165
+ """Initializes the frequency lemmatizer from given lemma table and lookup.
166
+
167
+ Parameters
168
+ ----------
169
+ table: iterable of entries or None, default None
170
+ Iterable of all entries in the lemma table
171
+ with pos tags morph features and frequencies.
172
+ lookup: dict of str to str or None, default None
173
+ Backoff lookup table for simple token-lemma lookup.
174
+ """
175
+ if table is None:
176
+ self.table = None
177
+ else:
178
+ self.table = table
179
+ self.lookup = lookup
180
+
181
+ def backoff(self, token: Token) -> str:
182
+ """Gets backoff token based on priority."""
183
+ orth = token.orth_.lower()
184
+ lookup = self.lookup
185
+ in_lookup = (lookup is not None) and (orth in lookup)
186
+ priority = self.fallback_priority
187
+ has_lemma = (token.lemma != 0) and (token.lemma_ != token.orth_)
188
+ if in_lookup:
189
+ if priority == "lookup":
190
+ return lookup[orth] # type: ignore
191
+ else:
192
+ if has_lemma:
193
+ return token.lemma_
194
+ else:
195
+ return token.orth_
196
+ else:
197
+ if has_lemma:
198
+ return token.lemma_
199
+ else:
200
+ return token.orth_
201
+
202
+ def lemmatize(self, token: Token) -> str:
203
+ """Lemmatizes token."""
204
+ backoff = self.backoff(token)
205
+ orth = token.orth_.lower()
206
+ # If the table is empty we early return
207
+ if self.table is None:
208
+ return backoff
209
+ # I only add frequency for type compatibility
210
+ token_entry: TableEntry = TableEntry(
211
+ form=orth, upos=token.pos_, frequency=-1, **token.morph.to_dict()
212
+ )
213
+ lemma = match_lemma(token_entry=token_entry, table=self.table)
214
+ if lemma is None:
215
+ return backoff
216
+ else:
217
+ return lemma
218
+
219
+ def __call__(self, doc: Doc) -> Doc:
220
+ """Apply the lemmatization to a document."""
221
+ error_handler = self.get_error_handler()
222
+ try:
223
+ for token in doc:
224
+ if self.overwrite or token.lemma == 0:
225
+ token.lemma_ = self.lemmatize(token)
226
+ return doc
227
+ except Exception as e:
228
+ error_handler(self.name, self, [doc], e)
229
+
230
+ def to_disk(
231
+ self, path: Union[str, Path], *, exclude: Iterable[str] = tuple()
232
+ ):
233
+ """Save frequency lemmatizer data to a directory."""
234
+ path = ensure_path(path)
235
+ Path(path).mkdir(parents=True, exist_ok=True)
236
+ config = dict(
237
+ overwrite=self.overwrite, fallback_priority=self.fallback_priority
238
+ )
239
+ with open(os.path.join(path, "config.json"), "w") as config_file:
240
+ json.dump(config, config_file)
241
+ if self.table is not None:
242
+ table_path = os.path.join(path, "table.json")
243
+ write_json(self.table, path=table_path)
244
+ if self.lookup is not None:
245
+ lookup_path = os.path.join(path, "lookup.json")
246
+ write_json(self.lookup, path=lookup_path)
247
+
248
+ def from_disk(
249
+ self, path: Union[str, Path], *, exclude: Iterable[str] = tuple()
250
+ ) -> "FrequencyLemmatizer":
251
+ """Load component from disk."""
252
+ path = ensure_path(path)
253
+ config = read_json(os.path.join(path, "config.json"))
254
+ self.overwrite = config.get("overwrite", self.overwrite)
255
+ self.fallback_priority = config.get(
256
+ "fallback_priority", self.fallback_priority
257
+ )
258
+ try:
259
+ table: Optional[FrequencyTable] = read_json(
260
+ os.path.join(path, "table.json")
261
+ )
262
+ except FileNotFoundError:
263
+ table = None
264
+ try:
265
+ lookup: Optional[LookupTable] = read_json(
266
+ os.path.join(path, "lookup.json")
267
+ )
268
+ except FileNotFoundError:
269
+ lookup = None
270
+ self.initialize(table=table, lookup=lookup)
271
+ return self
meta.json ADDED
The diff for this file is too large to render. See raw diff
 
morphologizer/cfg ADDED
The diff for this file is too large to render. See raw diff
 
morphologizer/model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eeff40f67250aacdbb0c93c0815becad2b1e400f71d06063e672a9994807576
3
+ size 4408561
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:e292087fce74cce8ddabe32dcf0e55ff588fcc5caa2b6e460c81aaf79a59ef58
3
+ size 2075321
parser/moves ADDED
@@ -0,0 +1 @@
 
 
1
+ ��moves� 3{"0":{"":181951},"1":{"":138489},"2":{"det":30514,"advmod":25856,"case":19705,"nsubj":14893,"obj":13046,"obl":9420,"advcl":8875,"nmod":8747,"discourse":8140,"punct":6644,"cc":5133,"mark":4895,"iobj":2542,"xcomp":2221,"cop":1869,"amod":1626,"vocative":1404,"det||nsubj":1381,"nmod||obj":1144,"nmod||nsubj":1039,"nsubj:pass":966,"case||obl":853,"nummod":639,"mark||advcl":633,"obj||advcl":615,"det||obj":507,"obl||advcl":389,"nsubj||ccomp":335,"acl":330,"obj||xcomp":307,"nmod||obl":298,"advmod||advcl":287,"nsubj||advcl":274,"xcomp||nsubj":272,"ccomp":268,"dislocated":261,"orphan":206,"cc||advcl":160,"conj||advcl":158,"det||obl":149,"amod||obj":149,"advmod||advmod":148,"det||nsubj:pass":140,"xcomp||obj":135,"nmod||nmod":135,"obl||xcomp":133,"det||nmod":133,"advmod||xcomp":128,"amod||nsubj":127,"obl:agent":126,"xcomp||advcl":107,"parataxis":106,"obj||ccomp":102,"det||iobj":100,"nmod||xcomp":94,"advmod||ccomp":89,"csubj":82,"iobj||xcomp":81,"iobj||advcl":79,"det||advmod":76,"advmod||nsubj":76,"advmod||obj":74,"obl||ccomp":72,"cc||nsubj":66,"conj||nsubj":60,"nmod||iobj":57,"advmod||nmod":55,"appos||nsubj":53,"advmod||obl":47,"conj||obj":46,"ccomp||advcl":46,"acl||nsubj":45,"amod||obl":42,"cc||obj":41,"obj||csubj":40,"det||xcomp":40,"iobj||ccomp":38,"nsubj||csubj":35,"advcl||ccomp":35,"nsubj:pass||advcl":34,"acl||obj":33,"xcomp||xcomp":32,"nsubj||nsubj":32,"nmod||det":32,"obl||obj":30,"dep":0},"3":{"conj":15241,"cc":14143,"punct":13626,"nmod":11545,"obj":11482,"obl":11254,"advcl":7395,"nsubj":6834,"advmod":6645,"xcomp":4281,"det":4188,"iobj":4162,"ccomp":2904,"cop":2189,"discourse":2107,"acl":1999,"appos":1772,"amod":1681,"nmod||obj":826,"nsubj:pass":710,"advmod||conj":678,"case":573,"nsubj||conj":568,"obj||conj":564,"vocative":527,"nmod||nsubj":510,"orphan":452,"acl||obj":422,"conj||obj":329,"obl||conj":300,"acl||nsubj":287,"nummod":282,"obl:agent":273,"nmod||conj":268,"cc||obj":258,"flat:name":248,"csubj":223,"conj||nsubj":218,"case||conj":213,"xcomp||obj":205,"parataxis":201,"advcl||conj":196,"cc||nsubj":186,"nmod||obl":178,"appos||nsubj":178,"amod||obj":174,"case||obl":170,"appos||obj":165,"xcomp||nsubj":148,"fixed":148,"nmod||nmod":146,"det||nsubj":137,"xcomp||conj":132,"amod||nsubj":131,"conj||obl":130,"cc||obl":120,"csubj:pass":118,"det||obj":117,"obl||xcomp":103,"conj||xcomp":95,"acl||obl":85,"obj||xcomp":81,"conj||nmod":79,"iobj||conj":73,"cc||xcomp":71,"cc||nmod":71,"acl||nmod":71,"advmod||obj":69,"nmod||xcomp":64,"dislocated":59,"appos||obl":58,"advcl||advmod":53,"nsubj||ccomp":52,"det||conj":52,"obj||advcl":51,"advmod||xcomp":49,"iobj||xcomp":45,"nmod||iobj":44,"conj||iobj":44,"advmod||advmod":44,"cop||xcomp":42,"advcl||xcomp":42,"cc||iobj":41,"acl||iobj":36,"cop||ccomp":34,"advmod||nsubj":34,"conj||advcl":33,"obl||advcl":32,"ccomp||conj":32,"obj||ccomp":31,"conj||amod":31,"cop||obj":30,"dep":0},"4":{"ROOT":26490}}�cfg��neg_key�
tagger/cfg ADDED
@@ -0,0 +1,839 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "labels":[
3
+ "---------",
4
+ "--p---fa-",
5
+ "--s---ma-",
6
+ "-3paia---",
7
+ "-3paim---",
8
+ "-3siia---",
9
+ "A-",
10
+ "C-",
11
+ "Df",
12
+ "Dq",
13
+ "Du",
14
+ "F-",
15
+ "G-",
16
+ "I-",
17
+ "Ma",
18
+ "Mo",
19
+ "Nb",
20
+ "Ne",
21
+ "Pc",
22
+ "Pd",
23
+ "Pi",
24
+ "Pk",
25
+ "Pp",
26
+ "Pr",
27
+ "Ps",
28
+ "Px",
29
+ "R-",
30
+ "S-",
31
+ "V-",
32
+ "a--------",
33
+ "a-------s",
34
+ "a-d---fa-",
35
+ "a-d---fd-",
36
+ "a-d---fg-",
37
+ "a-d---fn-",
38
+ "a-d---ma-",
39
+ "a-d---md-",
40
+ "a-d---mg-",
41
+ "a-d---mn-",
42
+ "a-d---mnc",
43
+ "a-d---mv-",
44
+ "a-d---na-",
45
+ "a-d---ng-",
46
+ "a-d---nn-",
47
+ "a-p----dc",
48
+ "a-p---fa-",
49
+ "a-p---fac",
50
+ "a-p---fas",
51
+ "a-p---fd-",
52
+ "a-p---fdc",
53
+ "a-p---fds",
54
+ "a-p---fg-",
55
+ "a-p---fgc",
56
+ "a-p---fn-",
57
+ "a-p---fnc",
58
+ "a-p---fns",
59
+ "a-p---fv-",
60
+ "a-p---m--",
61
+ "a-p---m-c",
62
+ "a-p---ma-",
63
+ "a-p---mac",
64
+ "a-p---mas",
65
+ "a-p---md-",
66
+ "a-p---mdc",
67
+ "a-p---mds",
68
+ "a-p---mg-",
69
+ "a-p---mgc",
70
+ "a-p---mgs",
71
+ "a-p---mn-",
72
+ "a-p---mnc",
73
+ "a-p---mns",
74
+ "a-p---mv-",
75
+ "a-p---mvs",
76
+ "a-p---na-",
77
+ "a-p---nac",
78
+ "a-p---nas",
79
+ "a-p---nd-",
80
+ "a-p---ndc",
81
+ "a-p---nds",
82
+ "a-p---ng-",
83
+ "a-p---ngs",
84
+ "a-p---nn-",
85
+ "a-p---nnc",
86
+ "a-p---nns",
87
+ "a-p---nv-",
88
+ "a-s----d-",
89
+ "a-s----dc",
90
+ "a-s----g-",
91
+ "a-s----gc",
92
+ "a-s---fa-",
93
+ "a-s---fac",
94
+ "a-s---fas",
95
+ "a-s---fd-",
96
+ "a-s---fds",
97
+ "a-s---fg-",
98
+ "a-s---fgc",
99
+ "a-s---fgs",
100
+ "a-s---fn-",
101
+ "a-s---fnc",
102
+ "a-s---fns",
103
+ "a-s---fv-",
104
+ "a-s---m--",
105
+ "a-s---ma-",
106
+ "a-s---mac",
107
+ "a-s---mas",
108
+ "a-s---md-",
109
+ "a-s---mdc",
110
+ "a-s---mds",
111
+ "a-s---mg-",
112
+ "a-s---mgc",
113
+ "a-s---mgs",
114
+ "a-s---mn-",
115
+ "a-s---mnc",
116
+ "a-s---mns",
117
+ "a-s---mv-",
118
+ "a-s---mvc",
119
+ "a-s---mvs",
120
+ "a-s---na-",
121
+ "a-s---nac",
122
+ "a-s---nas",
123
+ "a-s---nd-",
124
+ "a-s---ndc",
125
+ "a-s---nds",
126
+ "a-s---ng-",
127
+ "a-s---nn-",
128
+ "a-s---nnc",
129
+ "a-s---nns",
130
+ "a-s---nv-",
131
+ "a-s---nvs",
132
+ "c--------",
133
+ "d--------",
134
+ "d-------c",
135
+ "d-------s",
136
+ "g--------",
137
+ "i--------",
138
+ "l--------",
139
+ "l-d---fa-",
140
+ "l-d---fg-",
141
+ "l-d---mg-",
142
+ "l-d---mn-",
143
+ "l-d---na-",
144
+ "l-d---nn-",
145
+ "l-p---fa-",
146
+ "l-p---fd-",
147
+ "l-p---fg-",
148
+ "l-p---fn-",
149
+ "l-p---ma-",
150
+ "l-p---md-",
151
+ "l-p---mg-",
152
+ "l-p---mn-",
153
+ "l-p---na-",
154
+ "l-p---nd-",
155
+ "l-p---ng-",
156
+ "l-p---nn-",
157
+ "l-s---fa-",
158
+ "l-s---fd-",
159
+ "l-s---fg-",
160
+ "l-s---fn-",
161
+ "l-s---ma-",
162
+ "l-s---md-",
163
+ "l-s---mg-",
164
+ "l-s---mn-",
165
+ "l-s---na-",
166
+ "l-s---nd-",
167
+ "l-s---ng-",
168
+ "l-s---nn-",
169
+ "m--------",
170
+ "m-p---m--",
171
+ "m-p---md-",
172
+ "m-p---nn-",
173
+ "n-----fg-",
174
+ "n-----na-",
175
+ "n-----nn-",
176
+ "n-d----a-",
177
+ "n-d---fa-",
178
+ "n-d---fd-",
179
+ "n-d---fg-",
180
+ "n-d---fn-",
181
+ "n-d---ma-",
182
+ "n-d---md-",
183
+ "n-d---mg-",
184
+ "n-d---mn-",
185
+ "n-d---mv-",
186
+ "n-d---na-",
187
+ "n-d---nn-",
188
+ "n-p----d-",
189
+ "n-p----g-",
190
+ "n-p---fa-",
191
+ "n-p---fd-",
192
+ "n-p---fg-",
193
+ "n-p---fn-",
194
+ "n-p---fv-",
195
+ "n-p---ma-",
196
+ "n-p---md-",
197
+ "n-p---mg-",
198
+ "n-p---mn-",
199
+ "n-p---mv-",
200
+ "n-p---na-",
201
+ "n-p---nd-",
202
+ "n-p---ng-",
203
+ "n-p---nn-",
204
+ "n-p---nv-",
205
+ "n-s----d-",
206
+ "n-s----g-",
207
+ "n-s----n-",
208
+ "n-s----v-",
209
+ "n-s---fa-",
210
+ "n-s---fd-",
211
+ "n-s---fg-",
212
+ "n-s---fn-",
213
+ "n-s---fv-",
214
+ "n-s---m--",
215
+ "n-s---ma-",
216
+ "n-s---md-",
217
+ "n-s---mg-",
218
+ "n-s---mn-",
219
+ "n-s---mv-",
220
+ "n-s---na-",
221
+ "n-s---nd-",
222
+ "n-s---ng-",
223
+ "n-s---nn-",
224
+ "n-s---nv-",
225
+ "p--------",
226
+ "p-d----d-",
227
+ "p-d----n-",
228
+ "p-d---fa-",
229
+ "p-d---fd-",
230
+ "p-d---fg-",
231
+ "p-d---fn-",
232
+ "p-d---ma-",
233
+ "p-d---md-",
234
+ "p-d---mg-",
235
+ "p-d---mn-",
236
+ "p-d---mv-",
237
+ "p-p----a-",
238
+ "p-p----d-",
239
+ "p-p----g-",
240
+ "p-p----n-",
241
+ "p-p---fa-",
242
+ "p-p---fd-",
243
+ "p-p---fg-",
244
+ "p-p---fn-",
245
+ "p-p---ma-",
246
+ "p-p---md-",
247
+ "p-p---mg-",
248
+ "p-p---mn-",
249
+ "p-p---na-",
250
+ "p-p---nd-",
251
+ "p-p---ng-",
252
+ "p-p---nn-",
253
+ "p-s----a-",
254
+ "p-s----d-",
255
+ "p-s----g-",
256
+ "p-s----n-",
257
+ "p-s---fa-",
258
+ "p-s---fd-",
259
+ "p-s---fg-",
260
+ "p-s---fn-",
261
+ "p-s---ma-",
262
+ "p-s---md-",
263
+ "p-s---mg-",
264
+ "p-s---mn-",
265
+ "p-s---mv-",
266
+ "p-s---na-",
267
+ "p-s---nd-",
268
+ "p-s---ng-",
269
+ "p-s---nn-",
270
+ "p1p---fa-",
271
+ "p1p---ma-",
272
+ "p1p---md-",
273
+ "p1p---mg-",
274
+ "p1p---mn-",
275
+ "p1s---fa-",
276
+ "p1s---fd-",
277
+ "p1s---fg-",
278
+ "p1s---fn-",
279
+ "p1s---ma-",
280
+ "p1s---md-",
281
+ "p1s---mg-",
282
+ "p1s---mn-",
283
+ "p2p----a-",
284
+ "p2p----d-",
285
+ "p2p---ma-",
286
+ "p2p---mg-",
287
+ "p2p---mn-",
288
+ "p2s----a-",
289
+ "p2s----d-",
290
+ "p2s----g-",
291
+ "p2s----n-",
292
+ "p2s---ma-",
293
+ "p2s---md-",
294
+ "p2s---mg-",
295
+ "p3s---fa-",
296
+ "p3s---ma-",
297
+ "r--------",
298
+ "u--------",
299
+ "v---na---",
300
+ "v--amm---",
301
+ "v--an----",
302
+ "v--ana---",
303
+ "v--ane---",
304
+ "v--anm---",
305
+ "v--anp---",
306
+ "v--fna---",
307
+ "v--fne---",
308
+ "v--fnm---",
309
+ "v--fnp---",
310
+ "v--pna---",
311
+ "v--pnd---",
312
+ "v--pne---",
313
+ "v--pnp---",
314
+ "v--ppefa-",
315
+ "v--ppemn-",
316
+ "v--rn----",
317
+ "v--rna---",
318
+ "v--rne---",
319
+ "v--rnp---",
320
+ "v--tna---",
321
+ "v-dapafn-",
322
+ "v-dapama-",
323
+ "v-dapamg-",
324
+ "v-dapamn-",
325
+ "v-dapmfn-",
326
+ "v-dapmmn-",
327
+ "v-dappma-",
328
+ "v-dappmn-",
329
+ "v-dppafg-",
330
+ "v-dppama-",
331
+ "v-dppamn-",
332
+ "v-dppefn-",
333
+ "v-dppema-",
334
+ "v-dppemd-",
335
+ "v-dppemn-",
336
+ "v-dpppmn-",
337
+ "v-drpama-",
338
+ "v-drpamn-",
339
+ "v-drpefn-",
340
+ "v-drpemn-",
341
+ "v-p-pmma-",
342
+ "v-pap-mn-",
343
+ "v-papafa-",
344
+ "v-papafg-",
345
+ "v-papafn-",
346
+ "v-papama-",
347
+ "v-papamd-",
348
+ "v-papamg-",
349
+ "v-papamn-",
350
+ "v-papana-",
351
+ "v-papand-",
352
+ "v-papann-",
353
+ "v-papefn-",
354
+ "v-papema-",
355
+ "v-papemn-",
356
+ "v-papmfa-",
357
+ "v-papmfg-",
358
+ "v-papmfn-",
359
+ "v-papmma-",
360
+ "v-papmmd-",
361
+ "v-papmmg-",
362
+ "v-papmmn-",
363
+ "v-papmna-",
364
+ "v-papmng-",
365
+ "v-papmnn-",
366
+ "v-pappfd-",
367
+ "v-pappfg-",
368
+ "v-pappfn-",
369
+ "v-pappma-",
370
+ "v-pappmd-",
371
+ "v-pappmg-",
372
+ "v-pappmn-",
373
+ "v-pappna-",
374
+ "v-pappng-",
375
+ "v-pappnn-",
376
+ "v-pfpama-",
377
+ "v-pfpamg-",
378
+ "v-pfpamn-",
379
+ "v-pfpema-",
380
+ "v-pfpemn-",
381
+ "v-pfpmfa-",
382
+ "v-pfpmfn-",
383
+ "v-pfpmma-",
384
+ "v-pfpmmd-",
385
+ "v-pfpmmg-",
386
+ "v-pfpmmn-",
387
+ "v-pfpmnn-",
388
+ "v-pfppmn-",
389
+ "v-ppp-mn-",
390
+ "v-pppafa-",
391
+ "v-pppafd-",
392
+ "v-pppafg-",
393
+ "v-pppafn-",
394
+ "v-pppafv-",
395
+ "v-pppama-",
396
+ "v-pppamd-",
397
+ "v-pppamg-",
398
+ "v-pppamn-",
399
+ "v-pppamv-",
400
+ "v-pppana-",
401
+ "v-pppand-",
402
+ "v-pppang-",
403
+ "v-pppann-",
404
+ "v-pppefa-",
405
+ "v-pppefd-",
406
+ "v-pppefg-",
407
+ "v-pppefn-",
408
+ "v-pppefv-",
409
+ "v-pppema-",
410
+ "v-pppemd-",
411
+ "v-pppemg-",
412
+ "v-pppemn-",
413
+ "v-pppemv-",
414
+ "v-pppena-",
415
+ "v-pppend-",
416
+ "v-pppeng-",
417
+ "v-pppenn-",
418
+ "v-ppppma-",
419
+ "v-ppppmd-",
420
+ "v-ppppmn-",
421
+ "v-prp-mn-",
422
+ "v-prpafa-",
423
+ "v-prpafd-",
424
+ "v-prpafn-",
425
+ "v-prpama-",
426
+ "v-prpamd-",
427
+ "v-prpamg-",
428
+ "v-prpamn-",
429
+ "v-prpana-",
430
+ "v-prpang-",
431
+ "v-prpefa-",
432
+ "v-prpefd-",
433
+ "v-prpefg-",
434
+ "v-prpefn-",
435
+ "v-prpema-",
436
+ "v-prpemd-",
437
+ "v-prpemg-",
438
+ "v-prpemn-",
439
+ "v-prpena-",
440
+ "v-prpend-",
441
+ "v-prpeng-",
442
+ "v-prpenn-",
443
+ "v-prppfn-",
444
+ "v-prppmn-",
445
+ "v-sagamn-",
446
+ "v-saiamn-",
447
+ "v-samp---",
448
+ "v-sap-mg-",
449
+ "v-sap-mn-",
450
+ "v-sapafa-",
451
+ "v-sapafd-",
452
+ "v-sapafg-",
453
+ "v-sapafn-",
454
+ "v-sapama-",
455
+ "v-sapamd-",
456
+ "v-sapamg-",
457
+ "v-sapamn-",
458
+ "v-sapamv-",
459
+ "v-sapana-",
460
+ "v-sapang-",
461
+ "v-sapann-",
462
+ "v-sapanv-",
463
+ "v-sapema-",
464
+ "v-sapemn-",
465
+ "v-sapmfa-",
466
+ "v-sapmfd-",
467
+ "v-sapmfg-",
468
+ "v-sapmfn-",
469
+ "v-sapmma-",
470
+ "v-sapmmd-",
471
+ "v-sapmmg-",
472
+ "v-sapmmn-",
473
+ "v-sapmna-",
474
+ "v-sapmng-",
475
+ "v-sapmnn-",
476
+ "v-sappfa-",
477
+ "v-sappfd-",
478
+ "v-sappfg-",
479
+ "v-sappfn-",
480
+ "v-sappma-",
481
+ "v-sappmd-",
482
+ "v-sappmg-",
483
+ "v-sappmn-",
484
+ "v-sappna-",
485
+ "v-sappng-",
486
+ "v-sappnn-",
487
+ "v-sappnv-",
488
+ "v-sfpafa-",
489
+ "v-sfpafd-",
490
+ "v-sfpafn-",
491
+ "v-sfpama-",
492
+ "v-sfpamd-",
493
+ "v-sfpamg-",
494
+ "v-sfpamn-",
495
+ "v-sfpmfa-",
496
+ "v-sfpmfd-",
497
+ "v-sfpmfg-",
498
+ "v-sfpmfn-",
499
+ "v-sfpmma-",
500
+ "v-sfpmmg-",
501
+ "v-sfpmmn-",
502
+ "v-sfpmna-",
503
+ "v-sfppma-",
504
+ "v-spiamn-",
505
+ "v-spp-mn-",
506
+ "v-spp-nn-",
507
+ "v-sppa---",
508
+ "v-sppafa-",
509
+ "v-sppafd-",
510
+ "v-sppafg-",
511
+ "v-sppafn-",
512
+ "v-sppafv-",
513
+ "v-sppama-",
514
+ "v-sppamd-",
515
+ "v-sppamg-",
516
+ "v-sppamn-",
517
+ "v-sppamv-",
518
+ "v-sppana-",
519
+ "v-sppand-",
520
+ "v-sppang-",
521
+ "v-sppann-",
522
+ "v-sppanv-",
523
+ "v-sppefa-",
524
+ "v-sppefd-",
525
+ "v-sppefg-",
526
+ "v-sppefn-",
527
+ "v-sppema-",
528
+ "v-sppemd-",
529
+ "v-sppemg-",
530
+ "v-sppemn-",
531
+ "v-sppemv-",
532
+ "v-sppena-",
533
+ "v-sppend-",
534
+ "v-sppeng-",
535
+ "v-sppenn-",
536
+ "v-spppfa-",
537
+ "v-spppfd-",
538
+ "v-spppfg-",
539
+ "v-spppfn-",
540
+ "v-spppma-",
541
+ "v-spppmn-",
542
+ "v-srp-mn-",
543
+ "v-srpafa-",
544
+ "v-srpafd-",
545
+ "v-srpafg-",
546
+ "v-srpafn-",
547
+ "v-srpama-",
548
+ "v-srpamd-",
549
+ "v-srpamg-",
550
+ "v-srpamn-",
551
+ "v-srpamv-",
552
+ "v-srpana-",
553
+ "v-srpand-",
554
+ "v-srpang-",
555
+ "v-srpann-",
556
+ "v-srpefa-",
557
+ "v-srpefd-",
558
+ "v-srpefg-",
559
+ "v-srpefn-",
560
+ "v-srpema-",
561
+ "v-srpemd-",
562
+ "v-srpemg-",
563
+ "v-srpemn-",
564
+ "v-srpemv-",
565
+ "v-srpena-",
566
+ "v-srpend-",
567
+ "v-srpeng-",
568
+ "v-srpenn-",
569
+ "v-srppfn-",
570
+ "v-srppma-",
571
+ "v-srppmn-",
572
+ "v-srppmv-",
573
+ "v1paia---",
574
+ "v1paim---",
575
+ "v1paip---",
576
+ "v1paoa---",
577
+ "v1paom---",
578
+ "v1paop---",
579
+ "v1pasa---",
580
+ "v1pase---",
581
+ "v1pasm---",
582
+ "v1pasp---",
583
+ "v1pfia---",
584
+ "v1pfim---",
585
+ "v1pfom---",
586
+ "v1piia---",
587
+ "v1piie---",
588
+ "v1plia---",
589
+ "v1plie---",
590
+ "v1ppia---",
591
+ "v1ppie---",
592
+ "v1ppip---",
593
+ "v1ppoa---",
594
+ "v1ppoe---",
595
+ "v1ppsa---",
596
+ "v1ppse---",
597
+ "v1pria---",
598
+ "v1prie---",
599
+ "v1prsa---",
600
+ "v1prse---",
601
+ "v1ptie---",
602
+ "v1s-sa---",
603
+ "v1sa-a---",
604
+ "v1saia---",
605
+ "v1saie---",
606
+ "v1saim---",
607
+ "v1saip---",
608
+ "v1sao----",
609
+ "v1saoa---",
610
+ "v1saoe---",
611
+ "v1saom---",
612
+ "v1saop---",
613
+ "v1sasa---",
614
+ "v1sase---",
615
+ "v1sasm---",
616
+ "v1sasp---",
617
+ "v1sfi----",
618
+ "v1sfia---",
619
+ "v1sfie---",
620
+ "v1sfim---",
621
+ "v1sfip---",
622
+ "v1siia---",
623
+ "v1siie---",
624
+ "v1slia---",
625
+ "v1slie---",
626
+ "v1slim---",
627
+ "v1spia---",
628
+ "v1spie---",
629
+ "v1spoa---",
630
+ "v1spoe---",
631
+ "v1spsa---",
632
+ "v1spse---",
633
+ "v1sria---",
634
+ "v1srie---",
635
+ "v1sroa---",
636
+ "v1sroe---",
637
+ "v1srsa---",
638
+ "v1stie---",
639
+ "v1stim---",
640
+ "v2daia---",
641
+ "v2dama---",
642
+ "v2dasa---",
643
+ "v2dase---",
644
+ "v2dfia---",
645
+ "v2dfim---",
646
+ "v2diia---",
647
+ "v2diie---",
648
+ "v2dpia---",
649
+ "v2dpma---",
650
+ "v2dpme---",
651
+ "v2dria---",
652
+ "v2drma---",
653
+ "v2paia---",
654
+ "v2paim---",
655
+ "v2paip---",
656
+ "v2pama---",
657
+ "v2pame---",
658
+ "v2pamm---",
659
+ "v2paoa---",
660
+ "v2paom---",
661
+ "v2paop---",
662
+ "v2pasa---",
663
+ "v2pase---",
664
+ "v2pasm---",
665
+ "v2pasp---",
666
+ "v2pfia---",
667
+ "v2pfim---",
668
+ "v2piia---",
669
+ "v2piie---",
670
+ "v2ppia---",
671
+ "v2ppie---",
672
+ "v2ppma---",
673
+ "v2ppme---",
674
+ "v2ppoa---",
675
+ "v2ppoe---",
676
+ "v2ppsa---",
677
+ "v2pria---",
678
+ "v2prie---",
679
+ "v2prma---",
680
+ "v2prmp---",
681
+ "v2proa---",
682
+ "v2prsa---",
683
+ "v2saia---",
684
+ "v2saie---",
685
+ "v2saim---",
686
+ "v2saip---",
687
+ "v2sam----",
688
+ "v2sama---",
689
+ "v2same---",
690
+ "v2samm---",
691
+ "v2samp---",
692
+ "v2saoa---",
693
+ "v2saoe---",
694
+ "v2saom---",
695
+ "v2saop---",
696
+ "v2sasa---",
697
+ "v2sase---",
698
+ "v2sasm---",
699
+ "v2sasp---",
700
+ "v2sfi----",
701
+ "v2sfia---",
702
+ "v2sfie---",
703
+ "v2sfim---",
704
+ "v2sfip---",
705
+ "v2siia---",
706
+ "v2siie---",
707
+ "v2siip---",
708
+ "v2slia---",
709
+ "v2slie---",
710
+ "v2slim---",
711
+ "v2spia---",
712
+ "v2spie---",
713
+ "v2spma---",
714
+ "v2spme---",
715
+ "v2spoa---",
716
+ "v2spoe---",
717
+ "v2spsa---",
718
+ "v2spse---",
719
+ "v2sria---",
720
+ "v2srie---",
721
+ "v2srma---",
722
+ "v2srme---",
723
+ "v2sroa---",
724
+ "v2srsa---",
725
+ "v2stie---",
726
+ "v3-roe---",
727
+ "v3daia---",
728
+ "v3daim---",
729
+ "v3daip---",
730
+ "v3daoa---",
731
+ "v3dfia---",
732
+ "v3dfim---",
733
+ "v3diia---",
734
+ "v3diie---",
735
+ "v3dlia---",
736
+ "v3dlie---",
737
+ "v3dlim---",
738
+ "v3dpia---",
739
+ "v3dpie---",
740
+ "v3dpma---",
741
+ "v3dpme---",
742
+ "v3dpsa---",
743
+ "v3dria---",
744
+ "v3pai----",
745
+ "v3paia---",
746
+ "v3paie---",
747
+ "v3paim---",
748
+ "v3paip---",
749
+ "v3pamm---",
750
+ "v3paoa---",
751
+ "v3paoe---",
752
+ "v3paom---",
753
+ "v3paop---",
754
+ "v3pasa---",
755
+ "v3pase---",
756
+ "v3pasm---",
757
+ "v3pasp---",
758
+ "v3pfia---",
759
+ "v3pfie---",
760
+ "v3pfim---",
761
+ "v3piia---",
762
+ "v3piie---",
763
+ "v3piip---",
764
+ "v3plia---",
765
+ "v3plie---",
766
+ "v3plim---",
767
+ "v3plip---",
768
+ "v3ppia---",
769
+ "v3ppie---",
770
+ "v3ppip---",
771
+ "v3ppma---",
772
+ "v3ppme---",
773
+ "v3ppoa---",
774
+ "v3ppoe---",
775
+ "v3ppsa---",
776
+ "v3ppse---",
777
+ "v3pria---",
778
+ "v3prie---",
779
+ "v3prip---",
780
+ "v3sai----",
781
+ "v3saia---",
782
+ "v3saie---",
783
+ "v3saim---",
784
+ "v3saip---",
785
+ "v3sama---",
786
+ "v3samm---",
787
+ "v3samp---",
788
+ "v3sana---",
789
+ "v3sao----",
790
+ "v3saoa---",
791
+ "v3saoe---",
792
+ "v3saom---",
793
+ "v3saop---",
794
+ "v3sas----",
795
+ "v3sasa---",
796
+ "v3sase---",
797
+ "v3sasm---",
798
+ "v3sasp---",
799
+ "v3sfi----",
800
+ "v3sfia---",
801
+ "v3sfie---",
802
+ "v3sfim---",
803
+ "v3sfip---",
804
+ "v3sfoa---",
805
+ "v3sii----",
806
+ "v3siia---",
807
+ "v3siie---",
808
+ "v3siip---",
809
+ "v3sli----",
810
+ "v3slia---",
811
+ "v3slie---",
812
+ "v3slim---",
813
+ "v3slip---",
814
+ "v3spia---",
815
+ "v3spie---",
816
+ "v3spip---",
817
+ "v3spma---",
818
+ "v3spme---",
819
+ "v3spoa---",
820
+ "v3spoe---",
821
+ "v3spop---",
822
+ "v3spsa---",
823
+ "v3spse---",
824
+ "v3sria---",
825
+ "v3srie---",
826
+ "v3srip---",
827
+ "v3srma---",
828
+ "v3sroa---",
829
+ "v3srsa---",
830
+ "v3stie---",
831
+ "v3stim---",
832
+ "v3stip---",
833
+ "x--------",
834
+ "x-p----d-",
835
+ "x-p---nn-"
836
+ ],
837
+ "neg_prefix":"!",
838
+ "overwrite":false
839
+ }
tagger/model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0a79e1afe28e4f918648ba940fd9ba2d4cc72dc0e051237590a2f73e90a2af1
3
+ size 2562961
tokenizer ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ ��prefix_search� {^†|^⸏|^…|^……|^,|^:|^;|^\!|^\?|^¿|^؟|^¡|^\(|^\)|^\[|^\]|^\{|^\}|^<|^>|^_|^#|^\*|^&|^。|^?|^!|^,|^、|^;|^:|^~|^·|^।|^،|^۔|^؛|^٪|^\.\.+|^…|^\'|^"|^”|^“|^`|^‘|^´|^’|^‚|^,|^„|^»|^«|^「|^」|^『|^』|^(|^)|^〔|^〕|^【|^】|^《|^》|^〈|^〉|^〈|^〉|^⟦|^⟧|^\$|^£|^€|^¥|^฿|^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\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]$|†$|⸎$|(?<=[\u1F00-\u1FFF\u0370-\u03FF])[\-\.⸏]$�infix_finditer�?!\.\.+|…|[\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]|(?<=[0-9])[+\-\*^](?=[0-9-])|(?<=[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\u3040-\u309F\u30A0-\u30FFー\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\u3040-\u309F\u30A0-\u30FFー\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\u3040-\u309F\u30A0-\u30FFー\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\u3040-\u309F\u30A0-\u30FFー\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\u3040-\u309F\u30A0-\u30FFー\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-\U0002FA1F0-9])(?:-|–|—|--|---|——|~)(?=[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\u3040-\u309F\u30A0-\u30FFー\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\u3040-\u309F\u30A0-\u30FFー\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-\U0002FA1F0-9])[:<>=/](?=[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\u3040-\u309F\u30A0-\u30FFー\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])|(?<=[\u1F00-\u1FFF\u0370-\u03FF])—�token_match��url_match�
3
+ ��A�
4
+ � ��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�@_@�C++��A�C++�O.O��A�O.O�O.o��A�O.o�O_O��A�O_O�O_o��A�O_o�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.�b.��A�b.�c.��A�c.�d.��A�d.�e.��A�e.�f.��A�f.�g.��A�g.�h.��A�h.�i.��A�i.�j.��A�j.�k.��A�k.�l.��A�l.�m.��A�m.�n.��A�n.�o.��A�o.�o.0��A�o.0�o.O��A�o.O�o.o��A�o.o�o_0��A�o_0�o_O��A�o_O�o_o��A�o_o�p.��A�p.�q.��A�q.�r.��A�r.�s.��A�s.�t.��A�t.�u.��A�u.�v.��A�v.�v.v��A�v.v�v_v��A�v_v�w.��A�w.�x.��A�x.�xD��A�xD�xDD��A�xDD�y.��A�y.�z.��A�z.� ��A� C� �¯\(ツ)/¯��A�¯\(ツ)/¯�°C.��A�°�A�C�A�.�°F.��A�°�A�F�A�.�°K.��A�°�A�K�A�.�°c.��A�°�A�c�A�.�°f.��A�°�A�f�A�.�°k.��A�°�A�k�A�.�ä.��A�ä.�ö.��A�ö.�ü.��A�ü.�Δ'��A�Δ'C�δέ�Δι'��A�Δι'C�διά�Δι’��A�Δι’C�διά�Δ’��A�Δ’C�δέ�Εφ'��A�Εφ'C�επί�Εφ’��A�Εφ’C�επί�Καθ'��A�Καθ'C�κατά�Καθ’��A�Καθ’C�κατά�Κατ'��A�Κατ'C�κατά�Κατ’��A�Κατ’C�κατά�Μ'��A�Μ'C�με�Μετ'��A�Μετ'C�μετά�Μετ’��A�Μετ’C�μετά�Μ’��A�Μ’C�με�Παρ'��A�Παρ'C�παρά�Παρ’��A�Παρ’C�παρά�Σ'��A�Σ'C�σε�Σ’��A�Σ’C�σε�Τ'��A�Τ'C�τε�Τ’��A�Τ’C�τε�αὑτός��A�αὑC�ὁ�A�τόςC�αὐτός�αὑτὸς��A�αὑC�ὁ�A�τὸςC�αὐτός�δ'��A�δ'C�δέ�δι'��A�δι'C�διά�διὰ��A�διὰC�διά�δι’��A�δι’C�διά�δὲ��A�δὲC�δέ�δ’��A�δ’C�δέ�εφ'��A�εφ'C�επί�εφ’��A�εφ’C�επί�θοἰμάτιον��A�θοC�τό�A�ἰμάτιον�θἡμέρᾳ��A�θC�τῇ�A�ἡμέρᾳ�καθ'��A�καθ'C�κατά�καθ’��A�καθ’C�κατά�κατ'��A�κατ'C�κατά�κατὰ��A�κατὰC�κατά�κατ’��A�κατ’C�κατά�καὐτός��A�κC�καί�A�αὐτός�καὐτὸς��A�κC�καί�A�αὐτὸςC�αὐτός�καὶ��A�καὶC�καί�κεἰ��A�κC�καί�A�εἰ�κεἰς��A�κC�καί�A�εἰς�κοὐ��A�κC�καί�A�οὐ�κἀγώ��A�κἀC�καί�A�γώC�ἐγώ�κἀγὼ��A�κἀC�καί�A�γὼC�ἐγώ�κἀν��A�κC�καί�A�ἀνC�ἐν�κἀς��A�κC�καί�A�ἀςC�ἐς�κᾆτα��A�κC�καί�A�ᾆταC�εἶτα�μ'��A�μ'C�με�μέ��A�μέC�με�μεθ'��A�μεθ'C�μετά�μεθ’��A�μεθ’C�μετά�μετ'��A�μετ'C�μετά�μετὰ��A�μετὰC�μετά�μετ’��A�μετ’C�μετά�μοὔστι��A�μοὔC�μοί�A�στιC�ἐστι�μοὖστι��A�μοὖC�μοί�A�στιC�ἐστι�μὲ��A�μὲC�με�μὲν��A�μὲνC�μέν�μὴν��A�μὴνC�μήν�μ’��A�μ’C�με�οὑμοί��A�οὑC�οἱ�A�μοίC�ἐμoί�οὑμοὶ��A�οὑC�οἱ�A�μοὶC�ἐμoί�οὑμός��A�οὑC�ὁ�A�μόςC�ἐμός�οὑμὸς��A�οὑC�ὁ�A�μὸςC�ἐμός�οὑν��A�οὑC�ὁ�A�νC�ἐν�παρ��A�παρC�παρά�παρ'��A�παρ'C�παρά�παρὰ��A�παρὰC�παρά�παρ’��A�παρ’C�παρά�προὔχοντα��A�προὔC�πρό�A�χονταC�ἔχοντα�προὔχων��A�προὔC�πρό�A�χωνC�ἔχων�σ'��A�σ'C�σε�σέ��A�σέC�σε�σοὐστί��A�σοὐC�σοί�A�στίC�ἐστί�σοὐστὶ��A�σοὐC�σοί�A�στὶC�ἐστί�σοὔστι��A�σοὔC�σοί�A�στιC�ἐστι�σὲ��A�σὲC�σε�σ’��A�σ’C�σε�τ'��A�τ'C�τε�τέ��A�τέC�τε�ταὐτοῦ��A�τC�τοῦ�A�αὐτοῦ�τοὔνομα��A�τοὔC�τό�A�νομαC�ὄνομα�τἀνδρί��A�τC�τῷ�A�ἀνδρί�τἀνδρός��A�τC�τοῦ�A�ἀνδρός�τἀνδρὶ��A�τC�τῷ�A�ἀνδρὶC�ἀνδρί�τἀνδρὸς��A�τC�τοῦ�A�ἀνδρὸςC�ἀνδρός�τἄλλα��A�τC�τὰ�A�ἄλλα�τἆλλα��A�τἆC�τὰ�A�λλαC�ἄλλα�τὠληθές��A�τὠC�τὸ�A�ληθέςC�ἀληθές�τὲ��A�τὲC�τε�τὴν��A�τὴνC�τήν�τὸν��A�τὸνC�τόν�τ’��A�τ’C�τε�χοἱ��A�χC�καί�A�οἱ�χἡ��A�χC�καί�A�ἡ�χἱκετεύετε��A�χC�καί�A�ἱκετεύετε�χὤπως��A�χC�καί�A�ὤπωςC�ὅπως�χὤταν��A�χC�καί�A�ὤτανC�ὅταν�χὤτε��A�χC�καί�A�ὤτεC�ὅτε�χὤτι��A�χC�καί�A�ὤτιC�ὅτι�ಠ_ಠ��A�ಠ_ಠ�ಠ︵ಠ��A�ಠ︵ಠ�ἀλλ'��A�ἀλλ'C�ἀλλά�ἀλλὰ��A�ἀλλὰC�ἀλλά�ἀλλ’��A�ἀλλ’C�ἀλλά�ἀπὸ��A�ἀπὸC�από�ἀφ'��A�ἀφ'C�από�ἀφ’��A�ἀφ’C�από�ἁγαθαί��A�ἁC�αἱ�A�γαθαίC�ἀγαθαί�ἁγαθαὶ��A�ἁC�αἱ�A�γαθαὶC�ἀγαθαί�ἁγώ��A�ἁC�ἃ�A�γώC�ἐγώ�ἁγὼ��A�ἁC�ἃ�A�γὼC�ἐγώ�ἁλήθεια��A�ἁC�ἡ�A�λήθειαC�ἀλήθεια�ἁνήρ��A�ἁC�ὁ�A�νήρC�ἀνήρ�ἁνὴρ��A�ἁC�ὁ�A�νὴρC�ἀνήρ�ἅνδρες��A�ἅC�οἱ�A�νδρεςC�ἄνδρες�ἅνθρωπος��A�ἅC�ὁ�A�νθρωποςC�ἄνθρωπος�ἐγᾦδα��A�ἐγC�ἐγώ�A�ᾦδαC�οἶδα�ἐγᾦμαι��A�ἐγC�ἐγώ�A�ᾦμαιC�οἶμαι�ἐπ'��A�ἐπ'C�επί�ἐπὶ��A�ἐπὶC�επί�ἐπ’��A�ἐπ’C�επί�Ἐπ'��A�Ἐπ'C�επί�Ἐπ’��A�Ἐπ’C�επί�ὑπ'��A�ὑπ'C�ὑπό�ὑπ’��A�ὑπ’C�ὑπό�ὑφ'��A�ὑφ'C�ὑπό�ὑφ’��A�ὑφ’C�ὑπό�Ὑπ'��A�Ὑπ'C�ὑπό�Ὑπ’��A�Ὑπ’C�ὑπό�ὥνεκα��A�ὥC�οὗ�A�νεκαC�ἕνεκα�ὦνδρες��A�ὦC�ὦ�A�νδρεςC�ἄνδρες�ὦνερ��A�ὦC�ὦ�A�νερC�ἄνερ�᾽ΑΠ'��A�᾽ΑΠ'C�από�᾽ΑΠ’��A�᾽ΑΠ’C�από�᾽Αλλ'��A�᾽Αλλ'C�ἀλλά�᾽Αλλ’��A�᾽Αλλ’C�ἀλλά�᾽Απ'��A�᾽Απ'C�από�᾽Απ’��A�᾽Απ’C�από�᾽Αφ��A�᾽ΑφC�από�—��A�—�’��A�’�’’��A�’’�faster_heuristics�
trainable_lemmatizer/cfg ADDED
The diff for this file is too large to render. See raw diff
 
trainable_lemmatizer/model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa940742b9dc6d624ec6f0be5c6b4dd75aaea5ad4704727d568b3408cd543ef
3
+ size 71957523
trainable_lemmatizer/trees ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aba7a4c89fb247baa6c661704f3822b6b184a224518142a2fce31835a504cea
3
+ size 2400258
transformer/cfg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "max_batch_items":4096
3
+ }
transformer/model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93121f678bdeaf358a029839af586fdcc837c37bde94b38acd80c7dff23022a6
3
+ size 453378980
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
The diff for this file is too large to render. See raw diff
 
vocab/vectors ADDED
Binary file (128 Bytes). View file
 
vocab/vectors.cfg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "mode":"default"
3
+ }