adrianeboyd commited on
Commit
6cd4e04
1 Parent(s): ab2ca28

Update spaCy pipeline

Browse files
README.md CHANGED
@@ -14,62 +14,62 @@ model-index:
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
- value: 0.838028169
18
  - name: NER Recall
19
  type: recall
20
- value: 0.8342893563
21
  - name: NER F Score
22
  type: f_score
23
- value: 0.8361545832
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
- value: 0.9824705811
31
  - task:
32
  name: POS
33
  type: token-classification
34
  metrics:
35
  - name: POS (UPOS) Accuracy
36
  type: accuracy
37
- value: 0.9767367565
38
  - task:
39
  name: MORPH
40
  type: token-classification
41
  metrics:
42
  - name: Morph (UFeats) Accuracy
43
  type: accuracy
44
- value: 0.8970513509
45
  - task:
46
  name: LEMMA
47
  type: token-classification
48
  metrics:
49
  - name: Lemma Accuracy
50
  type: accuracy
51
- value: 0.9366919628
52
  - task:
53
  name: UNLABELED_DEPENDENCIES
54
  type: token-classification
55
  metrics:
56
  - name: Unlabeled Attachment Score (UAS)
57
  type: f_score
58
- value: 0.8919060234
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
- value: 0.8162603893
66
  - task:
67
  name: SENTS
68
  type: token-classification
69
  metrics:
70
  - name: Sentences F-Score
71
  type: f_score
72
- value: 0.9624604251
73
  ---
74
  ### Details: https://spacy.io/models/pl#pl_core_news_md
75
 
@@ -78,8 +78,8 @@ Polish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, l
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `pl_core_news_md` |
81
- | **Version** | `3.4.0` |
82
- | **spaCy** | `>=3.4.0,<3.5.0` |
83
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `lemmatizer`, `tagger`, `attribute_ruler`, `ner` |
84
  | **Components** | `tok2vec`, `morphologizer`, `parser`, `lemmatizer`, `tagger`, `senter`, `attribute_ruler`, `ner` |
85
  | **Vectors** | 500000 keys, 20000 unique vectors (300 dimensions) |
@@ -106,22 +106,22 @@ Polish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, l
106
 
107
  | Type | Score |
108
  | --- | --- |
109
- | `TOKEN_ACC` | 99.99 |
110
  | `TOKEN_P` | 99.63 |
111
  | `TOKEN_R` | 99.83 |
112
  | `TOKEN_F` | 99.73 |
113
- | `POS_ACC` | 97.67 |
114
- | `MORPH_ACC` | 89.71 |
115
- | `MORPH_MICRO_P` | 94.96 |
116
- | `MORPH_MICRO_R` | 94.78 |
117
- | `MORPH_MICRO_F` | 94.87 |
118
- | `SENTS_P` | 96.42 |
119
- | `SENTS_R` | 96.07 |
120
- | `SENTS_F` | 96.25 |
121
- | `DEP_UAS` | 89.19 |
122
- | `DEP_LAS` | 81.63 |
123
- | `LEMMA_ACC` | 93.67 |
124
- | `TAG_ACC` | 98.25 |
125
- | `ENTS_P` | 83.80 |
126
- | `ENTS_R` | 83.43 |
127
- | `ENTS_F` | 83.62 |
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
+ value: 0.828425096
18
  - name: NER Recall
19
  type: recall
20
+ value: 0.8247291268
21
  - name: NER F Score
22
  type: f_score
23
+ value: 0.8265729799
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
+ value: 0.9816474605
31
  - task:
32
  name: POS
33
  type: token-classification
34
  metrics:
35
  - name: POS (UPOS) Accuracy
36
  type: accuracy
37
+ value: 0.9763909862
38
  - task:
39
  name: MORPH
40
  type: token-classification
41
  metrics:
42
  - name: Morph (UFeats) Accuracy
43
  type: accuracy
44
+ value: 0.8950409384
45
  - task:
46
  name: LEMMA
47
  type: token-classification
48
  metrics:
49
  - name: Lemma Accuracy
50
  type: accuracy
51
+ value: 0.9361695953
52
  - task:
53
  name: UNLABELED_DEPENDENCIES
54
  type: token-classification
55
  metrics:
56
  - name: Unlabeled Attachment Score (UAS)
57
  type: f_score
58
+ value: 0.8889276191
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
+ value: 0.8139397108
66
  - task:
67
  name: SENTS
68
  type: token-classification
69
  metrics:
70
  - name: Sentences F-Score
71
  type: f_score
72
+ value: 0.9633152174
73
  ---
74
  ### Details: https://spacy.io/models/pl#pl_core_news_md
75
 
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `pl_core_news_md` |
81
+ | **Version** | `3.5.0` |
82
+ | **spaCy** | `>=3.5.0,<3.6.0` |
83
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `lemmatizer`, `tagger`, `attribute_ruler`, `ner` |
84
  | **Components** | `tok2vec`, `morphologizer`, `parser`, `lemmatizer`, `tagger`, `senter`, `attribute_ruler`, `ner` |
85
  | **Vectors** | 500000 keys, 20000 unique vectors (300 dimensions) |
106
 
107
  | Type | Score |
108
  | --- | --- |
109
+ | `TOKEN_ACC` | 99.98 |
110
  | `TOKEN_P` | 99.63 |
111
  | `TOKEN_R` | 99.83 |
112
  | `TOKEN_F` | 99.73 |
113
+ | `POS_ACC` | 97.64 |
114
+ | `MORPH_ACC` | 89.50 |
115
+ | `MORPH_MICRO_P` | 94.87 |
116
+ | `MORPH_MICRO_R` | 94.74 |
117
+ | `MORPH_MICRO_F` | 94.81 |
118
+ | `SENTS_P` | 96.64 |
119
+ | `SENTS_R` | 96.03 |
120
+ | `SENTS_F` | 96.33 |
121
+ | `DEP_UAS` | 88.89 |
122
+ | `DEP_LAS` | 81.39 |
123
+ | `LEMMA_ACC` | 93.62 |
124
+ | `TAG_ACC` | 98.16 |
125
+ | `ENTS_P` | 82.84 |
126
+ | `ENTS_R` | 82.47 |
127
+ | `ENTS_F` | 82.66 |
accuracy.json CHANGED
@@ -1,330 +1,315 @@
1
  {
2
- "token_acc": 0.9998840378,
3
  "token_p": 0.99628964,
4
  "token_r": 0.9982863284,
5
  "token_f": 0.9972869848,
6
- "pos_acc": 0.9767367565,
7
- "morph_acc": 0.8970513509,
8
- "morph_micro_p": 0.9495885429,
9
- "morph_micro_r": 0.9477701341,
10
- "morph_micro_f": 0.9486784671,
11
  "morph_per_feat": {
12
  "Case": {
13
- "p": 0.9198536961,
14
- "r": 0.9183215887,
15
- "f": 0.9190870039
16
  },
17
  "Gender": {
18
- "p": 0.9300510533,
19
- "r": 0.9287974684,
20
- "f": 0.9294238381
21
  },
22
  "Number": {
23
- "p": 0.9734880302,
24
- "r": 0.9714480302,
25
- "f": 0.9724669604
26
  },
27
  "AdpType": {
28
- "p": 0.9994662397,
29
- "r": 0.9981343284,
30
- "f": 0.99879984
31
  },
32
  "Variant": {
33
- "p": 0.992310509,
34
  "r": 0.9963235294,
35
- "f": 0.9943129701
36
  },
37
  "Animacy": {
38
- "p": 0.8792837662,
39
- "r": 0.8854788631,
40
- "f": 0.8823704409
41
  },
42
  "Degree": {
43
- "p": 0.9376770538,
44
- "r": 0.9549913445,
45
- "f": 0.9462550029
46
  },
47
  "Aspect": {
48
- "p": 0.9165894347,
49
- "r": 0.9080058759,
50
- "f": 0.9122774652
51
  },
52
  "Mood": {
53
- "p": 0.9805540757,
54
- "r": 0.9813383098,
55
- "f": 0.980946036
56
  },
57
  "Person": {
58
- "p": 0.9805890228,
59
- "r": 0.9835515274,
60
- "f": 0.9820680409
61
  },
62
  "Tense": {
63
- "p": 0.9658141962,
64
- "r": 0.967834728,
65
- "f": 0.9668234065
66
  },
67
  "VerbForm": {
68
- "p": 0.9666061706,
69
- "r": 0.9582583663,
70
- "f": 0.962414167
71
  },
72
  "Voice": {
73
- "p": 0.9786666667,
74
- "r": 0.9671599432,
75
- "f": 0.9728792822
76
  },
77
  "PunctType": {
78
- "p": 0.9986067572,
79
  "r": 0.9975643702,
80
- "f": 0.9980852916
81
  },
82
  "NumForm": {
83
- "p": 0.9775967413,
84
- "r": 0.9736308316,
85
- "f": 0.9756097561
86
  },
87
  "PrepCase": {
88
- "p": 0.9805352798,
89
- "r": 0.9664268585,
90
- "f": 0.9734299517
91
  },
92
  "PronType": {
93
- "p": 0.96973962,
94
- "r": 0.9622905028,
95
- "f": 0.966000701
96
  },
97
  "Reflex": {
98
- "p": 0.9986282579,
99
  "r": 1.0,
100
- "f": 0.9993136582
101
  },
102
  "NumType": {
103
- "p": 0.9285714286,
104
- "r": 0.8624078624,
105
- "f": 0.8942675159
106
  },
107
  "Polarity": {
108
- "p": 0.9098067287,
109
- "r": 0.8741403026,
110
- "f": 0.8916169765
111
  },
112
  "Hyph": {
113
- "p": 0.9705882353,
114
- "r": 1.0,
115
- "f": 0.9850746269
116
  },
117
  "VerbType": {
118
- "p": 0.9166666667,
119
- "r": 0.9285714286,
120
- "f": 0.9225806452
121
  },
122
  "ConjType": {
123
- "p": 0.9463087248,
124
- "r": 0.9337748344,
125
- "f": 0.94
126
  },
127
  "Clitic": {
128
- "p": 0.9481132075,
129
  "r": 0.9901477833,
130
- "f": 0.9686746988
131
  },
132
  "Poss": {
133
- "p": 0.9941860465,
134
- "r": 1.0,
135
- "f": 0.9970845481
136
  },
137
  "Number[psor]": {
138
  "p": 1.0,
139
- "r": 1.0,
140
- "f": 1.0
141
  },
142
  "PartType": {
143
- "p": 0.9242424242,
144
- "r": 0.9104477612,
145
- "f": 0.9172932331
146
  },
147
  "Abbr": {
148
- "p": 0.9278846154,
149
  "r": 0.9460784314,
150
- "f": 0.9368932039
151
  },
152
  "Pun": {
153
- "p": 0.9147727273,
154
- "r": 0.9360465116,
155
- "f": 0.9252873563
 
 
 
 
 
156
  },
157
  "PunctSide": {
158
  "p": 1.0,
159
  "r": 0.9708333333,
160
  "f": 0.9852008457
161
  },
162
- "Foreign": {
163
- "p": 0.8333333333,
164
- "r": 0.8333333333,
165
- "f": 0.8333333333
166
- },
167
  "Emphatic": {
168
  "p": 1.0,
169
- "r": 0.5,
170
- "f": 0.6666666667
171
  },
172
  "Polite": {
173
- "p": 0.0,
174
- "r": 0.0,
175
- "f": 0.0
176
  }
177
  },
178
- "sents_p": 0.9642048029,
179
- "sents_r": 0.9607223476,
180
- "sents_f": 0.9624604251,
181
- "dep_uas": 0.8919060234,
182
- "dep_las": 0.8162603893,
183
  "dep_las_per_type": {
184
  "nsubj": {
185
- "p": 0.8413159168,
186
- "r": 0.8608910891,
187
- "f": 0.8509909469
188
  },
189
  "case": {
190
- "p": 0.9678386481,
191
- "r": 0.9736769948,
192
- "f": 0.9707490432
193
  },
194
  "amod": {
195
- "p": 0.898976413,
196
- "r": 0.9062359803,
197
- "f": 0.9025915996
198
  },
199
  "nmod": {
200
- "p": 0.5716911765,
201
- "r": 0.5787841191,
202
- "f": 0.575215783
203
  },
204
  "cc": {
205
- "p": 0.875,
206
- "r": 0.8860759494,
207
- "f": 0.8805031447
208
  },
209
  "conj": {
210
- "p": 0.6639135959,
211
- "r": 0.6785714286,
212
- "f": 0.671162492
213
  },
214
  "root": {
215
- "p": 0.940697148,
216
- "r": 0.9381489842,
217
- "f": 0.9394213382
218
  },
219
  "obl": {
220
- "p": 0.7021960364,
221
- "r": 0.7171772429,
222
- "f": 0.7096075778
223
  },
224
  "obl:arg": {
225
- "p": 0.6683738796,
226
- "r": 0.6133960047,
227
- "f": 0.6397058824
228
  },
229
  "nummod": {
230
- "p": 0.8551724138,
231
- "r": 0.8857142857,
232
- "f": 0.8701754386
233
  },
234
  "obj": {
235
- "p": 0.819453274,
236
- "r": 0.8435863874,
237
- "f": 0.8313447275
238
  },
239
  "advcl": {
240
- "p": 0.6850828729,
241
- "r": 0.7167630058,
242
- "f": 0.7005649718
243
  },
244
  "iobj": {
245
- "p": 0.7516447368,
246
- "r": 0.7107309487,
247
- "f": 0.7306155076
248
  },
249
  "det:numgov": {
250
- "p": 0.9607843137,
251
- "r": 0.8448275862,
252
- "f": 0.8990825688
253
  },
254
  "acl": {
255
- "p": 0.7543859649,
256
- "r": 0.6991869919,
257
- "f": 0.7257383966
258
  },
259
  "fixed": {
260
- "p": 0.8632478632,
261
- "r": 0.7890625,
262
- "f": 0.8244897959
263
  },
264
  "nummod:gov": {
265
- "p": 0.8504672897,
266
- "r": 0.8425925926,
267
- "f": 0.8465116279
268
  },
269
  "obl:agent": {
270
- "p": 0.8983050847,
271
- "r": 0.868852459,
272
- "f": 0.8833333333
273
  },
274
  "expl:pv": {
275
- "p": 0.9784411277,
276
- "r": 0.9833333333,
277
- "f": 0.9808811305
278
  },
279
  "nmod:arg": {
280
- "p": 0.6095965104,
281
- "r": 0.6417910448,
282
- "f": 0.6252796421
283
  },
284
  "advmod": {
285
- "p": 0.8409490334,
286
- "r": 0.8544642857,
287
- "f": 0.8476527901
288
  },
289
  "acl:relcl": {
290
- "p": 0.7127659574,
291
- "r": 0.6931034483,
292
- "f": 0.7027972028
293
  },
294
  "advmod:emph": {
295
- "p": 0.7040169133,
296
- "r": 0.6908713693,
297
- "f": 0.697382199
298
- },
299
- "parataxis:insert": {
300
- "p": 0.5786163522,
301
- "r": 0.4532019704,
302
- "f": 0.5082872928
303
- },
304
- "dep": {
305
- "p": 0.0,
306
- "r": 0.0,
307
- "f": 0.0
308
  },
309
  "mark": {
310
- "p": 0.8811881188,
311
- "r": 0.8836879433,
312
- "f": 0.8824362606
313
  },
314
  "ccomp:obj": {
315
- "p": 0.6578947368,
316
- "r": 0.5555555556,
317
- "f": 0.6024096386
318
  },
319
  "appos": {
320
- "p": 0.6778846154,
321
- "r": 0.589958159,
322
- "f": 0.6308724832
323
- },
324
- "advcl:relcl": {
325
- "p": 0.0,
326
- "r": 0.0,
327
- "f": 0.0
328
  },
329
  "xcomp": {
330
  "p": 0.9267734554,
@@ -337,89 +322,89 @@
337
  "f": 0.9668508287
338
  },
339
  "det": {
340
- "p": 0.9004854369,
341
- "r": 0.8896882494,
342
- "f": 0.8950542823
343
  },
344
  "cop": {
345
- "p": 0.8839590444,
346
- "r": 0.875,
347
- "f": 0.8794567063
348
  },
349
  "nsubj:pass": {
350
- "p": 0.8055555556,
351
- "r": 0.7981651376,
352
- "f": 0.801843318
353
  },
354
  "aux:pass": {
355
- "p": 0.9319727891,
356
- "r": 0.9513888889,
357
- "f": 0.941580756
358
  },
359
  "aux:imp": {
360
  "p": 1.0,
361
- "r": 0.8888888889,
362
- "f": 0.9411764706
363
  },
364
  "advcl:cmpr": {
365
- "p": 0.2857142857,
366
- "r": 0.25,
367
- "f": 0.2666666667
368
  },
369
  "obl:cmpr": {
370
- "p": 0.6764705882,
371
- "r": 0.5168539326,
372
- "f": 0.5859872611
373
  },
374
  "ccomp": {
375
- "p": 0.6338028169,
376
- "r": 0.6308411215,
377
- "f": 0.6323185012
378
  },
379
  "nmod:poss": {
380
- "p": 0.5,
381
  "r": 0.1666666667,
382
- "f": 0.25
 
 
 
 
 
383
  },
384
  "det:poss": {
385
- "p": 0.9879518072,
386
- "r": 0.9534883721,
387
- "f": 0.9704142012
388
  },
389
  "aux": {
390
- "p": 0.8888888889,
391
- "r": 0.880733945,
392
- "f": 0.8847926267
393
  },
394
  "cc:preconj": {
395
- "p": 0.6363636364,
396
  "r": 0.5384615385,
397
- "f": 0.5833333333
398
  },
399
  "flat": {
400
- "p": 0.8383838384,
401
- "r": 0.8645833333,
402
- "f": 0.8512820513
403
  },
404
  "xcomp:pred": {
405
- "p": 0.7105263158,
406
- "r": 0.6585365854,
407
- "f": 0.6835443038
408
  },
409
  "parataxis:obj": {
410
- "p": 0.7718446602,
411
- "r": 0.8238341969,
412
- "f": 0.7969924812
413
  },
414
  "vocative": {
415
- "p": 0.6666666667,
416
- "r": 0.5714285714,
417
- "f": 0.6153846154
418
- },
419
- "discourse:intj": {
420
- "p": 0.1428571429,
421
- "r": 0.1111111111,
422
- "f": 0.125
423
  },
424
  "aux:cnd": {
425
  "p": 0.8571428571,
@@ -427,29 +412,34 @@
427
  "f": 0.8
428
  },
429
  "advmod:arg": {
430
- "p": 0.5,
431
  "r": 0.1111111111,
432
- "f": 0.1818181818
433
  },
434
  "csubj": {
435
- "p": 0.7647058824,
436
- "r": 0.5909090909,
437
- "f": 0.6666666667
438
  },
439
  "amod:flat": {
440
- "p": 0.8125,
441
- "r": 0.8253968254,
442
- "f": 0.8188976378
443
  },
444
  "nmod:flat": {
445
- "p": 0.8028169014,
446
- "r": 0.7125,
447
- "f": 0.7549668874
 
 
 
 
 
448
  },
449
  "det:nummod": {
450
- "p": 0.9166666667,
451
  "r": 1.0,
452
- "f": 0.9565217391
453
  },
454
  "nmod:pred": {
455
  "p": 0.0,
@@ -457,14 +447,14 @@
457
  "f": 0.0
458
  },
459
  "ccomp:cleft": {
460
- "p": 0.75,
461
- "r": 0.8823529412,
462
- "f": 0.8108108108
463
  },
464
  "list": {
465
- "p": 0.7878787879,
466
- "r": 0.6666666667,
467
- "f": 0.7222222222
468
  },
469
  "xcomp:subj": {
470
  "p": 0.0,
@@ -476,53 +466,63 @@
476
  "r": 0.0,
477
  "f": 0.0
478
  },
 
 
 
 
 
479
  "xcomp:cleft": {
480
  "p": 1.0,
481
  "r": 1.0,
482
  "f": 1.0
483
  },
 
 
 
 
 
484
  "obl:orphan": {
485
  "p": 0.0,
486
  "r": 0.0,
487
  "f": 0.0
488
  }
489
  },
490
- "lemma_acc": 0.9366919628,
491
- "tag_acc": 0.9824705811,
492
- "ents_p": 0.838028169,
493
- "ents_r": 0.8342893563,
494
- "ents_f": 0.8361545832,
495
  "ents_per_type": {
496
  "placeName": {
497
- "p": 0.8177676538,
498
- "r": 0.8387850467,
499
- "f": 0.8281430219
500
  },
501
  "orgName": {
502
- "p": 0.7845659164,
503
- "r": 0.7820512821,
504
- "f": 0.7833065811
505
  },
506
  "date": {
507
- "p": 0.932038835,
508
- "r": 0.8888888889,
509
- "f": 0.9099526066
510
  },
511
  "persName": {
512
- "p": 0.8847457627,
513
- "r": 0.883248731,
514
- "f": 0.883996613
515
  },
516
  "time": {
517
- "p": 0.8846153846,
518
  "r": 0.92,
519
- "f": 0.9019607843
520
  },
521
  "geogName": {
522
- "p": 0.6989247312,
523
- "r": 0.619047619,
524
- "f": 0.6565656566
525
  }
526
  },
527
- "speed": 7690.9472477757
528
  }
1
  {
2
+ "token_acc": 0.9997681025,
3
  "token_p": 0.99628964,
4
  "token_r": 0.9982863284,
5
  "token_f": 0.9972869848,
6
+ "pos_acc": 0.9763909862,
7
+ "morph_acc": 0.8950409384,
8
+ "morph_micro_p": 0.9487407865,
9
+ "morph_micro_r": 0.9473889605,
10
+ "morph_micro_f": 0.9480643916,
11
  "morph_per_feat": {
12
  "Case": {
13
+ "p": 0.9173400026,
14
+ "r": 0.9163997438,
15
+ "f": 0.9168696321
16
  },
17
  "Gender": {
18
+ "p": 0.9293213678,
19
+ "r": 0.9285044538,
20
+ "f": 0.9289127312
21
  },
22
  "Number": {
23
+ "p": 0.974864879,
24
+ "r": 0.9732816429,
25
+ "f": 0.9740726176
26
  },
27
  "AdpType": {
28
+ "p": 0.9994665244,
29
+ "r": 0.9986673774,
30
+ "f": 0.9990667911
31
  },
32
  "Variant": {
33
+ "p": 0.9955914769,
34
  "r": 0.9963235294,
35
+ "f": 0.9959573686
36
  },
37
  "Animacy": {
38
+ "p": 0.8787806903,
39
+ "r": 0.8847623597,
40
+ "f": 0.8817613805
41
  },
42
  "Degree": {
43
+ "p": 0.9340534395,
44
+ "r": 0.9480669359,
45
+ "f": 0.9410080183
46
  },
47
  "Aspect": {
48
+ "p": 0.9085039661,
49
+ "r": 0.9043334557,
50
+ "f": 0.9064139137
51
  },
52
  "Mood": {
53
+ "p": 0.9826666667,
54
+ "r": 0.9824046921,
55
+ "f": 0.9825356619
56
  },
57
  "Person": {
58
+ "p": 0.9815063887,
59
+ "r": 0.9798590131,
60
+ "f": 0.9806820091
61
  },
62
  "Tense": {
63
+ "p": 0.9662833246,
64
+ "r": 0.9667887029,
65
+ "f": 0.9665359477
66
  },
67
  "VerbForm": {
68
+ "p": 0.9647441692,
69
+ "r": 0.9600575747,
70
+ "f": 0.9623951664
71
  },
72
  "Voice": {
73
+ "p": 0.9767299449,
74
+ "r": 0.9699979728,
75
+ "f": 0.973352319
76
  },
77
  "PunctType": {
78
+ "p": 0.9982590529,
79
  "r": 0.9975643702,
80
+ "f": 0.9979115907
81
  },
82
  "NumForm": {
83
+ "p": 0.9756592292,
84
+ "r": 0.9756592292,
85
+ "f": 0.9756592292
86
  },
87
  "PrepCase": {
88
+ "p": 0.9876847291,
89
+ "r": 0.9616306954,
90
+ "f": 0.9744835966
91
  },
92
  "PronType": {
93
+ "p": 0.9709631728,
94
+ "r": 0.9574022346,
95
+ "f": 0.9641350211
96
  },
97
  "Reflex": {
98
+ "p": 0.9918256131,
99
  "r": 1.0,
100
+ "f": 0.9958960328
101
  },
102
  "NumType": {
103
+ "p": 0.9104859335,
104
+ "r": 0.8746928747,
105
+ "f": 0.8922305764
106
  },
107
  "Polarity": {
108
+ "p": 0.9047954866,
109
+ "r": 0.8823933975,
110
+ "f": 0.893454039
111
  },
112
  "Hyph": {
113
+ "p": 1.0,
114
+ "r": 0.9696969697,
115
+ "f": 0.9846153846
116
  },
117
  "VerbType": {
118
+ "p": 0.9342105263,
119
+ "r": 0.9220779221,
120
+ "f": 0.9281045752
121
  },
122
  "ConjType": {
123
+ "p": 0.9411764706,
124
+ "r": 0.9536423841,
125
+ "f": 0.9473684211
126
  },
127
  "Clitic": {
128
+ "p": 0.9663461538,
129
  "r": 0.9901477833,
130
+ "f": 0.9781021898
131
  },
132
  "Poss": {
133
+ "p": 0.9883040936,
134
+ "r": 0.9883040936,
135
+ "f": 0.9883040936
136
  },
137
  "Number[psor]": {
138
  "p": 1.0,
139
+ "r": 0.9411764706,
140
+ "f": 0.9696969697
141
  },
142
  "PartType": {
143
+ "p": 0.9375,
144
+ "r": 0.8955223881,
145
+ "f": 0.9160305344
146
  },
147
  "Abbr": {
148
+ "p": 0.9323671498,
149
  "r": 0.9460784314,
150
+ "f": 0.9391727494
151
  },
152
  "Pun": {
153
+ "p": 0.9356725146,
154
+ "r": 0.9302325581,
155
+ "f": 0.9329446064
156
+ },
157
+ "Foreign": {
158
+ "p": 0.6,
159
+ "r": 0.5,
160
+ "f": 0.5454545455
161
  },
162
  "PunctSide": {
163
  "p": 1.0,
164
  "r": 0.9708333333,
165
  "f": 0.9852008457
166
  },
 
 
 
 
 
167
  "Emphatic": {
168
  "p": 1.0,
169
+ "r": 0.6666666667,
170
+ "f": 0.8
171
  },
172
  "Polite": {
173
+ "p": 0.5,
174
+ "r": 1.0,
175
+ "f": 0.6666666667
176
  }
177
  },
178
+ "sents_p": 0.9663789187,
179
+ "sents_r": 0.9602708804,
180
+ "sents_f": 0.9633152174,
181
+ "dep_uas": 0.8889276191,
182
+ "dep_las": 0.8139397108,
183
  "dep_las_per_type": {
184
  "nsubj": {
185
+ "p": 0.8498542274,
186
+ "r": 0.8658415842,
187
+ "f": 0.8577734183
188
  },
189
  "case": {
190
+ "p": 0.9675660943,
191
+ "r": 0.9734027968,
192
+ "f": 0.9704756698
193
  },
194
  "amod": {
195
+ "p": 0.892732049,
196
+ "r": 0.9147599821,
197
+ "f": 0.9036117882
198
  },
199
  "nmod": {
200
+ "p": 0.5712515489,
201
+ "r": 0.5719602978,
202
+ "f": 0.5716057037
203
  },
204
  "cc": {
205
+ "p": 0.8711538462,
206
+ "r": 0.88218111,
207
+ "f": 0.8766328012
208
  },
209
  "conj": {
210
+ "p": 0.6463878327,
211
+ "r": 0.6623376623,
212
+ "f": 0.6542655548
213
  },
214
  "root": {
215
+ "p": 0.9396277803,
216
+ "r": 0.934537246,
217
+ "f": 0.9370755998
218
  },
219
  "obl": {
220
+ "p": 0.7137445887,
221
+ "r": 0.7215536105,
222
+ "f": 0.7176278564
223
  },
224
  "obl:arg": {
225
+ "p": 0.6746835443,
226
+ "r": 0.6263219741,
227
+ "f": 0.6496039001
228
  },
229
  "nummod": {
230
+ "p": 0.8601398601,
231
+ "r": 0.8785714286,
232
+ "f": 0.8692579505
233
  },
234
  "obj": {
235
+ "p": 0.8260869565,
236
+ "r": 0.8455497382,
237
+ "f": 0.8357050453
238
  },
239
  "advcl": {
240
+ "p": 0.6818181818,
241
+ "r": 0.6936416185,
242
+ "f": 0.6876790831
243
  },
244
  "iobj": {
245
+ "p": 0.7407407407,
246
+ "r": 0.7153965785,
247
+ "f": 0.7278481013
248
  },
249
  "det:numgov": {
250
+ "p": 0.962962963,
251
+ "r": 0.8965517241,
252
+ "f": 0.9285714286
253
  },
254
  "acl": {
255
+ "p": 0.7359307359,
256
+ "r": 0.6910569106,
257
+ "f": 0.71278826
258
  },
259
  "fixed": {
260
+ "p": 0.8280802292,
261
+ "r": 0.7526041667,
262
+ "f": 0.7885402456
263
  },
264
  "nummod:gov": {
265
+ "p": 0.8301886792,
266
+ "r": 0.8148148148,
267
+ "f": 0.8224299065
268
  },
269
  "obl:agent": {
270
+ "p": 0.8947368421,
271
+ "r": 0.8360655738,
272
+ "f": 0.8644067797
273
  },
274
  "expl:pv": {
275
+ "p": 0.9717138103,
276
+ "r": 0.9733333333,
277
+ "f": 0.9725228976
278
  },
279
  "nmod:arg": {
280
+ "p": 0.6119733925,
281
+ "r": 0.6337543054,
282
+ "f": 0.6226734349
283
  },
284
  "advmod": {
285
+ "p": 0.8255915863,
286
+ "r": 0.8410714286,
287
+ "f": 0.8332596196
288
  },
289
  "acl:relcl": {
290
+ "p": 0.7093425606,
291
+ "r": 0.7068965517,
292
+ "f": 0.7081174439
293
  },
294
  "advmod:emph": {
295
+ "p": 0.7136842105,
296
+ "r": 0.7033195021,
297
+ "f": 0.7084639498
 
 
 
 
 
 
 
 
 
 
298
  },
299
  "mark": {
300
+ "p": 0.8723098996,
301
+ "r": 0.8624113475,
302
+ "f": 0.8673323823
303
  },
304
  "ccomp:obj": {
305
+ "p": 0.6413043478,
306
+ "r": 0.6555555556,
307
+ "f": 0.6483516484
308
  },
309
  "appos": {
310
+ "p": 0.6444444444,
311
+ "r": 0.6066945607,
312
+ "f": 0.625
 
 
 
 
 
313
  },
314
  "xcomp": {
315
  "p": 0.9267734554,
322
  "f": 0.9668508287
323
  },
324
  "det": {
325
+ "p": 0.9119804401,
326
+ "r": 0.8944844125,
327
+ "f": 0.9031476998
328
  },
329
  "cop": {
330
+ "p": 0.8888888889,
331
+ "r": 0.8648648649,
332
+ "f": 0.8767123288
333
  },
334
  "nsubj:pass": {
335
+ "p": 0.7522123894,
336
+ "r": 0.7798165138,
337
+ "f": 0.7657657658
338
  },
339
  "aux:pass": {
340
+ "p": 0.9127516779,
341
+ "r": 0.9444444444,
342
+ "f": 0.9283276451
343
  },
344
  "aux:imp": {
345
  "p": 1.0,
346
+ "r": 0.7777777778,
347
+ "f": 0.875
348
  },
349
  "advcl:cmpr": {
350
+ "p": 0.4285714286,
351
+ "r": 0.1875,
352
+ "f": 0.2608695652
353
  },
354
  "obl:cmpr": {
355
+ "p": 0.7083333333,
356
+ "r": 0.5730337079,
357
+ "f": 0.6335403727
358
  },
359
  "ccomp": {
360
+ "p": 0.6411483254,
361
+ "r": 0.6261682243,
362
+ "f": 0.63356974
363
  },
364
  "nmod:poss": {
365
+ "p": 1.0,
366
  "r": 0.1666666667,
367
+ "f": 0.2857142857
368
+ },
369
+ "parataxis:insert": {
370
+ "p": 0.5555555556,
371
+ "r": 0.4187192118,
372
+ "f": 0.4775280899
373
  },
374
  "det:poss": {
375
+ "p": 0.9880239521,
376
+ "r": 0.9593023256,
377
+ "f": 0.9734513274
378
  },
379
  "aux": {
380
+ "p": 0.8773584906,
381
+ "r": 0.8532110092,
382
+ "f": 0.8651162791
383
  },
384
  "cc:preconj": {
385
+ "p": 0.5833333333,
386
  "r": 0.5384615385,
387
+ "f": 0.56
388
  },
389
  "flat": {
390
+ "p": 0.8694158076,
391
+ "r": 0.8784722222,
392
+ "f": 0.8739205527
393
  },
394
  "xcomp:pred": {
395
+ "p": 0.696969697,
396
+ "r": 0.5609756098,
397
+ "f": 0.6216216216
398
  },
399
  "parataxis:obj": {
400
+ "p": 0.7175925926,
401
+ "r": 0.8031088083,
402
+ "f": 0.7579462103
403
  },
404
  "vocative": {
405
+ "p": 0.5185185185,
406
+ "r": 0.5,
407
+ "f": 0.5090909091
 
 
 
 
 
408
  },
409
  "aux:cnd": {
410
  "p": 0.8571428571,
412
  "f": 0.8
413
  },
414
  "advmod:arg": {
415
+ "p": 1.0,
416
  "r": 0.1111111111,
417
+ "f": 0.2
418
  },
419
  "csubj": {
420
+ "p": 0.7272727273,
421
+ "r": 0.3636363636,
422
+ "f": 0.4848484848
423
  },
424
  "amod:flat": {
425
+ "p": 0.8172043011,
426
+ "r": 0.8042328042,
427
+ "f": 0.8106666667
428
  },
429
  "nmod:flat": {
430
+ "p": 0.7179487179,
431
+ "r": 0.7,
432
+ "f": 0.7088607595
433
+ },
434
+ "dep": {
435
+ "p": 0.0,
436
+ "r": 0.0,
437
+ "f": 0.0
438
  },
439
  "det:nummod": {
440
+ "p": 1.0,
441
  "r": 1.0,
442
+ "f": 1.0
443
  },
444
  "nmod:pred": {
445
  "p": 0.0,
447
  "f": 0.0
448
  },
449
  "ccomp:cleft": {
450
+ "p": 0.8235294118,
451
+ "r": 0.8235294118,
452
+ "f": 0.8235294118
453
  },
454
  "list": {
455
+ "p": 0.8823529412,
456
+ "r": 0.7692307692,
457
+ "f": 0.8219178082
458
  },
459
  "xcomp:subj": {
460
  "p": 0.0,
466
  "r": 0.0,
467
  "f": 0.0
468
  },
469
+ "discourse:intj": {
470
+ "p": 0.125,
471
+ "r": 0.1111111111,
472
+ "f": 0.1176470588
473
+ },
474
  "xcomp:cleft": {
475
  "p": 1.0,
476
  "r": 1.0,
477
  "f": 1.0
478
  },
479
+ "advcl:relcl": {
480
+ "p": 0.5,
481
+ "r": 0.25,
482
+ "f": 0.3333333333
483
+ },
484
  "obl:orphan": {
485
  "p": 0.0,
486
  "r": 0.0,
487
  "f": 0.0
488
  }
489
  },
490
+ "lemma_acc": 0.9361695953,
491
+ "tag_acc": 0.9816474605,
492
+ "ents_p": 0.828425096,
493
+ "ents_r": 0.8247291268,
494
+ "ents_f": 0.8265729799,
495
  "ents_per_type": {
496
  "placeName": {
497
+ "p": 0.808411215,
498
+ "r": 0.808411215,
499
+ "f": 0.808411215
500
  },
501
  "orgName": {
502
+ "p": 0.7828947368,
503
+ "r": 0.7628205128,
504
+ "f": 0.7727272727
505
  },
506
  "date": {
507
+ "p": 0.9405940594,
508
+ "r": 0.8796296296,
509
+ "f": 0.9090909091
510
  },
511
  "persName": {
512
+ "p": 0.8708609272,
513
+ "r": 0.8900169205,
514
+ "f": 0.880334728
515
  },
516
  "time": {
517
+ "p": 0.8518518519,
518
  "r": 0.92,
519
+ "f": 0.8846153846
520
  },
521
  "geogName": {
522
+ "p": 0.6734693878,
523
+ "r": 0.6285714286,
524
+ "f": 0.6502463054
525
  }
526
  },
527
+ "speed": 7725.6968010248
528
  }
config.cfg CHANGED
@@ -81,8 +81,8 @@ nO = null
81
  [components.ner.model.tok2vec.embed]
82
  @architectures = "spacy.MultiHashEmbed.v2"
83
  width = 96
84
- attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
85
- rows = [5000,1000,2500,2500,50]
86
  include_static_vectors = true
87
 
88
  [components.ner.model.tok2vec.encode]
@@ -158,8 +158,8 @@ normalize = false
158
  [components.tagger.model.tok2vec.embed]
159
  @architectures = "spacy.MultiHashEmbed.v2"
160
  width = 96
161
- attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
162
- rows = [5000,1000,2500,2500,50]
163
  include_static_vectors = true
164
 
165
  [components.tagger.model.tok2vec.encode]
@@ -178,8 +178,8 @@ factory = "tok2vec"
178
  [components.tok2vec.model.embed]
179
  @architectures = "spacy.MultiHashEmbed.v2"
180
  width = ${components.tok2vec.model.encode:width}
181
- attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
182
- rows = [5000,1000,2500,2500,50]
183
  include_static_vectors = true
184
 
185
  [components.tok2vec.model.encode]
@@ -221,6 +221,7 @@ eval_frequency = 1000
221
  frozen_components = []
222
  before_to_disk = null
223
  annotating_components = []
 
224
 
225
  [training.batcher]
226
  @batchers = "spacy.batch_by_words.v1"
81
  [components.ner.model.tok2vec.embed]
82
  @architectures = "spacy.MultiHashEmbed.v2"
83
  width = 96
84
+ attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
85
+ rows = [5000,1000,2500,2500]
86
  include_static_vectors = true
87
 
88
  [components.ner.model.tok2vec.encode]
158
  [components.tagger.model.tok2vec.embed]
159
  @architectures = "spacy.MultiHashEmbed.v2"
160
  width = 96
161
+ attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY","IS_SPACE"]
162
+ rows = [5000,1000,2500,2500,50,50]
163
  include_static_vectors = true
164
 
165
  [components.tagger.model.tok2vec.encode]
178
  [components.tok2vec.model.embed]
179
  @architectures = "spacy.MultiHashEmbed.v2"
180
  width = ${components.tok2vec.model.encode:width}
181
+ attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY","IS_SPACE"]
182
+ rows = [5000,1000,2500,2500,50,50]
183
  include_static_vectors = true
184
 
185
  [components.tok2vec.model.encode]
221
  frozen_components = []
222
  before_to_disk = null
223
  annotating_components = []
224
+ before_update = null
225
 
226
  [training.batcher]
227
  @batchers = "spacy.batch_by_words.v1"
lemmatizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bc2e779245d860b599ba3d7b1f0315fb75a51d34697df51f6092c8cf435e2bf
3
  size 829986
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:016b7466aef71df699b92680ef1969ec1636a9032456acdc751107e11398921d
3
  size 829986
meta.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "lang":"pl",
3
  "name":"core_news_md",
4
- "version":"3.4.0",
5
  "description":"Polish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, lemmatizer (trainable_lemmatizer), tagger, senter, ner.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"GNU GPL 3.0",
10
- "spacy_version":">=3.4.0,<3.5.0",
11
- "spacy_git_version":"dd038b536",
12
  "vectors":{
13
  "width":300,
14
  "vectors":20000,
@@ -1780,332 +1780,317 @@
1780
  "senter"
1781
  ],
1782
  "performance":{
1783
- "token_acc":0.9998840378,
1784
  "token_p":0.99628964,
1785
  "token_r":0.9982863284,
1786
  "token_f":0.9972869848,
1787
- "pos_acc":0.9767367565,
1788
- "morph_acc":0.8970513509,
1789
- "morph_micro_p":0.9495885429,
1790
- "morph_micro_r":0.9477701341,
1791
- "morph_micro_f":0.9486784671,
1792
  "morph_per_feat":{
1793
  "Case":{
1794
- "p":0.9198536961,
1795
- "r":0.9183215887,
1796
- "f":0.9190870039
1797
  },
1798
  "Gender":{
1799
- "p":0.9300510533,
1800
- "r":0.9287974684,
1801
- "f":0.9294238381
1802
  },
1803
  "Number":{
1804
- "p":0.9734880302,
1805
- "r":0.9714480302,
1806
- "f":0.9724669604
1807
  },
1808
  "AdpType":{
1809
- "p":0.9994662397,
1810
- "r":0.9981343284,
1811
- "f":0.99879984
1812
  },
1813
  "Variant":{
1814
- "p":0.992310509,
1815
  "r":0.9963235294,
1816
- "f":0.9943129701
1817
  },
1818
  "Animacy":{
1819
- "p":0.8792837662,
1820
- "r":0.8854788631,
1821
- "f":0.8823704409
1822
  },
1823
  "Degree":{
1824
- "p":0.9376770538,
1825
- "r":0.9549913445,
1826
- "f":0.9462550029
1827
  },
1828
  "Aspect":{
1829
- "p":0.9165894347,
1830
- "r":0.9080058759,
1831
- "f":0.9122774652
1832
  },
1833
  "Mood":{
1834
- "p":0.9805540757,
1835
- "r":0.9813383098,
1836
- "f":0.980946036
1837
  },
1838
  "Person":{
1839
- "p":0.9805890228,
1840
- "r":0.9835515274,
1841
- "f":0.9820680409
1842
  },
1843
  "Tense":{
1844
- "p":0.9658141962,
1845
- "r":0.967834728,
1846
- "f":0.9668234065
1847
  },
1848
  "VerbForm":{
1849
- "p":0.9666061706,
1850
- "r":0.9582583663,
1851
- "f":0.962414167
1852
  },
1853
  "Voice":{
1854
- "p":0.9786666667,
1855
- "r":0.9671599432,
1856
- "f":0.9728792822
1857
  },
1858
  "PunctType":{
1859
- "p":0.9986067572,
1860
  "r":0.9975643702,
1861
- "f":0.9980852916
1862
  },
1863
  "NumForm":{
1864
- "p":0.9775967413,
1865
- "r":0.9736308316,
1866
- "f":0.9756097561
1867
  },
1868
  "PrepCase":{
1869
- "p":0.9805352798,
1870
- "r":0.9664268585,
1871
- "f":0.9734299517
1872
  },
1873
  "PronType":{
1874
- "p":0.96973962,
1875
- "r":0.9622905028,
1876
- "f":0.966000701
1877
  },
1878
  "Reflex":{
1879
- "p":0.9986282579,
1880
  "r":1.0,
1881
- "f":0.9993136582
1882
  },
1883
  "NumType":{
1884
- "p":0.9285714286,
1885
- "r":0.8624078624,
1886
- "f":0.8942675159
1887
  },
1888
  "Polarity":{
1889
- "p":0.9098067287,
1890
- "r":0.8741403026,
1891
- "f":0.8916169765
1892
  },
1893
  "Hyph":{
1894
- "p":0.9705882353,
1895
- "r":1.0,
1896
- "f":0.9850746269
1897
  },
1898
  "VerbType":{
1899
- "p":0.9166666667,
1900
- "r":0.9285714286,
1901
- "f":0.9225806452
1902
  },
1903
  "ConjType":{
1904
- "p":0.9463087248,
1905
- "r":0.9337748344,
1906
- "f":0.94
1907
  },
1908
  "Clitic":{
1909
- "p":0.9481132075,
1910
  "r":0.9901477833,
1911
- "f":0.9686746988
1912
  },
1913
  "Poss":{
1914
- "p":0.9941860465,
1915
- "r":1.0,
1916
- "f":0.9970845481
1917
  },
1918
  "Number[psor]":{
1919
  "p":1.0,
1920
- "r":1.0,
1921
- "f":1.0
1922
  },
1923
  "PartType":{
1924
- "p":0.9242424242,
1925
- "r":0.9104477612,
1926
- "f":0.9172932331
1927
  },
1928
  "Abbr":{
1929
- "p":0.9278846154,
1930
  "r":0.9460784314,
1931
- "f":0.9368932039
1932
  },
1933
  "Pun":{
1934
- "p":0.9147727273,
1935
- "r":0.9360465116,
1936
- "f":0.9252873563
 
 
 
 
 
1937
  },
1938
  "PunctSide":{
1939
  "p":1.0,
1940
  "r":0.9708333333,
1941
  "f":0.9852008457
1942
  },
1943
- "Foreign":{
1944
- "p":0.8333333333,
1945
- "r":0.8333333333,
1946
- "f":0.8333333333
1947
- },
1948
  "Emphatic":{
1949
  "p":1.0,
1950
- "r":0.5,
1951
- "f":0.6666666667
1952
  },
1953
  "Polite":{
1954
- "p":0.0,
1955
- "r":0.0,
1956
- "f":0.0
1957
  }
1958
  },
1959
- "sents_p":0.9642048029,
1960
- "sents_r":0.9607223476,
1961
- "sents_f":0.9624604251,
1962
- "dep_uas":0.8919060234,
1963
- "dep_las":0.8162603893,
1964
  "dep_las_per_type":{
1965
  "nsubj":{
1966
- "p":0.8413159168,
1967
- "r":0.8608910891,
1968
- "f":0.8509909469
1969
  },
1970
  "case":{
1971
- "p":0.9678386481,
1972
- "r":0.9736769948,
1973
- "f":0.9707490432
1974
  },
1975
  "amod":{
1976
- "p":0.898976413,
1977
- "r":0.9062359803,
1978
- "f":0.9025915996
1979
  },
1980
  "nmod":{
1981
- "p":0.5716911765,
1982
- "r":0.5787841191,
1983
- "f":0.575215783
1984
  },
1985
  "cc":{
1986
- "p":0.875,
1987
- "r":0.8860759494,
1988
- "f":0.8805031447
1989
  },
1990
  "conj":{
1991
- "p":0.6639135959,
1992
- "r":0.6785714286,
1993
- "f":0.671162492
1994
  },
1995
  "root":{
1996
- "p":0.940697148,
1997
- "r":0.9381489842,
1998
- "f":0.9394213382
1999
  },
2000
  "obl":{
2001
- "p":0.7021960364,
2002
- "r":0.7171772429,
2003
- "f":0.7096075778
2004
  },
2005
  "obl:arg":{
2006
- "p":0.6683738796,
2007
- "r":0.6133960047,
2008
- "f":0.6397058824
2009
  },
2010
  "nummod":{
2011
- "p":0.8551724138,
2012
- "r":0.8857142857,
2013
- "f":0.8701754386
2014
  },
2015
  "obj":{
2016
- "p":0.819453274,
2017
- "r":0.8435863874,
2018
- "f":0.8313447275
2019
  },
2020
  "advcl":{
2021
- "p":0.6850828729,
2022
- "r":0.7167630058,
2023
- "f":0.7005649718
2024
  },
2025
  "iobj":{
2026
- "p":0.7516447368,
2027
- "r":0.7107309487,
2028
- "f":0.7306155076
2029
  },
2030
  "det:numgov":{
2031
- "p":0.9607843137,
2032
- "r":0.8448275862,
2033
- "f":0.8990825688
2034
  },
2035
  "acl":{
2036
- "p":0.7543859649,
2037
- "r":0.6991869919,
2038
- "f":0.7257383966
2039
  },
2040
  "fixed":{
2041
- "p":0.8632478632,
2042
- "r":0.7890625,
2043
- "f":0.8244897959
2044
  },
2045
  "nummod:gov":{
2046
- "p":0.8504672897,
2047
- "r":0.8425925926,
2048
- "f":0.8465116279
2049
  },
2050
  "obl:agent":{
2051
- "p":0.8983050847,
2052
- "r":0.868852459,
2053
- "f":0.8833333333
2054
  },
2055
  "expl:pv":{
2056
- "p":0.9784411277,
2057
- "r":0.9833333333,
2058
- "f":0.9808811305
2059
  },
2060
  "nmod:arg":{
2061
- "p":0.6095965104,
2062
- "r":0.6417910448,
2063
- "f":0.6252796421
2064
  },
2065
  "advmod":{
2066
- "p":0.8409490334,
2067
- "r":0.8544642857,
2068
- "f":0.8476527901
2069
  },
2070
  "acl:relcl":{
2071
- "p":0.7127659574,
2072
- "r":0.6931034483,
2073
- "f":0.7027972028
2074
  },
2075
  "advmod:emph":{
2076
- "p":0.7040169133,
2077
- "r":0.6908713693,
2078
- "f":0.697382199
2079
- },
2080
- "parataxis:insert":{
2081
- "p":0.5786163522,
2082
- "r":0.4532019704,
2083
- "f":0.5082872928
2084
- },
2085
- "dep":{
2086
- "p":0.0,
2087
- "r":0.0,
2088
- "f":0.0
2089
  },
2090
  "mark":{
2091
- "p":0.8811881188,
2092
- "r":0.8836879433,
2093
- "f":0.8824362606
2094
  },
2095
  "ccomp:obj":{
2096
- "p":0.6578947368,
2097
- "r":0.5555555556,
2098
- "f":0.6024096386
2099
  },
2100
  "appos":{
2101
- "p":0.6778846154,
2102
- "r":0.589958159,
2103
- "f":0.6308724832
2104
- },
2105
- "advcl:relcl":{
2106
- "p":0.0,
2107
- "r":0.0,
2108
- "f":0.0
2109
  },
2110
  "xcomp":{
2111
  "p":0.9267734554,
@@ -2118,89 +2103,89 @@
2118
  "f":0.9668508287
2119
  },
2120
  "det":{
2121
- "p":0.9004854369,
2122
- "r":0.8896882494,
2123
- "f":0.8950542823
2124
  },
2125
  "cop":{
2126
- "p":0.8839590444,
2127
- "r":0.875,
2128
- "f":0.8794567063
2129
  },
2130
  "nsubj:pass":{
2131
- "p":0.8055555556,
2132
- "r":0.7981651376,
2133
- "f":0.801843318
2134
  },
2135
  "aux:pass":{
2136
- "p":0.9319727891,
2137
- "r":0.9513888889,
2138
- "f":0.941580756
2139
  },
2140
  "aux:imp":{
2141
  "p":1.0,
2142
- "r":0.8888888889,
2143
- "f":0.9411764706
2144
  },
2145
  "advcl:cmpr":{
2146
- "p":0.2857142857,
2147
- "r":0.25,
2148
- "f":0.2666666667
2149
  },
2150
  "obl:cmpr":{
2151
- "p":0.6764705882,
2152
- "r":0.5168539326,
2153
- "f":0.5859872611
2154
  },
2155
  "ccomp":{
2156
- "p":0.6338028169,
2157
- "r":0.6308411215,
2158
- "f":0.6323185012
2159
  },
2160
  "nmod:poss":{
2161
- "p":0.5,
2162
  "r":0.1666666667,
2163
- "f":0.25
 
 
 
 
 
2164
  },
2165
  "det:poss":{
2166
- "p":0.9879518072,
2167
- "r":0.9534883721,
2168
- "f":0.9704142012
2169
  },
2170
  "aux":{
2171
- "p":0.8888888889,
2172
- "r":0.880733945,
2173
- "f":0.8847926267
2174
  },
2175
  "cc:preconj":{
2176
- "p":0.6363636364,
2177
  "r":0.5384615385,
2178
- "f":0.5833333333
2179
  },
2180
  "flat":{
2181
- "p":0.8383838384,
2182
- "r":0.8645833333,
2183
- "f":0.8512820513
2184
  },
2185
  "xcomp:pred":{
2186
- "p":0.7105263158,
2187
- "r":0.6585365854,
2188
- "f":0.6835443038
2189
  },
2190
  "parataxis:obj":{
2191
- "p":0.7718446602,
2192
- "r":0.8238341969,
2193
- "f":0.7969924812
2194
  },
2195
  "vocative":{
2196
- "p":0.6666666667,
2197
- "r":0.5714285714,
2198
- "f":0.6153846154
2199
- },
2200
- "discourse:intj":{
2201
- "p":0.1428571429,
2202
- "r":0.1111111111,
2203
- "f":0.125
2204
  },
2205
  "aux:cnd":{
2206
  "p":0.8571428571,
@@ -2208,29 +2193,34 @@
2208
  "f":0.8
2209
  },
2210
  "advmod:arg":{
2211
- "p":0.5,
2212
  "r":0.1111111111,
2213
- "f":0.1818181818
2214
  },
2215
  "csubj":{
2216
- "p":0.7647058824,
2217
- "r":0.5909090909,
2218
- "f":0.6666666667
2219
  },
2220
  "amod:flat":{
2221
- "p":0.8125,
2222
- "r":0.8253968254,
2223
- "f":0.8188976378
2224
  },
2225
  "nmod:flat":{
2226
- "p":0.8028169014,
2227
- "r":0.7125,
2228
- "f":0.7549668874
 
 
 
 
 
2229
  },
2230
  "det:nummod":{
2231
- "p":0.9166666667,
2232
  "r":1.0,
2233
- "f":0.9565217391
2234
  },
2235
  "nmod:pred":{
2236
  "p":0.0,
@@ -2238,14 +2228,14 @@
2238
  "f":0.0
2239
  },
2240
  "ccomp:cleft":{
2241
- "p":0.75,
2242
- "r":0.8823529412,
2243
- "f":0.8108108108
2244
  },
2245
  "list":{
2246
- "p":0.7878787879,
2247
- "r":0.6666666667,
2248
- "f":0.7222222222
2249
  },
2250
  "xcomp:subj":{
2251
  "p":0.0,
@@ -2257,55 +2247,65 @@
2257
  "r":0.0,
2258
  "f":0.0
2259
  },
 
 
 
 
 
2260
  "xcomp:cleft":{
2261
  "p":1.0,
2262
  "r":1.0,
2263
  "f":1.0
2264
  },
 
 
 
 
 
2265
  "obl:orphan":{
2266
  "p":0.0,
2267
  "r":0.0,
2268
  "f":0.0
2269
  }
2270
  },
2271
- "lemma_acc":0.9366919628,
2272
- "tag_acc":0.9824705811,
2273
- "ents_p":0.838028169,
2274
- "ents_r":0.8342893563,
2275
- "ents_f":0.8361545832,
2276
  "ents_per_type":{
2277
  "placeName":{
2278
- "p":0.8177676538,
2279
- "r":0.8387850467,
2280
- "f":0.8281430219
2281
  },
2282
  "orgName":{
2283
- "p":0.7845659164,
2284
- "r":0.7820512821,
2285
- "f":0.7833065811
2286
  },
2287
  "date":{
2288
- "p":0.932038835,
2289
- "r":0.8888888889,
2290
- "f":0.9099526066
2291
  },
2292
  "persName":{
2293
- "p":0.8847457627,
2294
- "r":0.883248731,
2295
- "f":0.883996613
2296
  },
2297
  "time":{
2298
- "p":0.8846153846,
2299
  "r":0.92,
2300
- "f":0.9019607843
2301
  },
2302
  "geogName":{
2303
- "p":0.6989247312,
2304
- "r":0.619047619,
2305
- "f":0.6565656566
2306
  }
2307
  },
2308
- "speed":7690.9472477757
2309
  },
2310
  "sources":[
2311
  {
1
  {
2
  "lang":"pl",
3
  "name":"core_news_md",
4
+ "version":"3.5.0",
5
  "description":"Polish pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, lemmatizer (trainable_lemmatizer), tagger, senter, ner.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"GNU GPL 3.0",
10
+ "spacy_version":">=3.5.0,<3.6.0",
11
+ "spacy_git_version":"9e0322de1",
12
  "vectors":{
13
  "width":300,
14
  "vectors":20000,
1780
  "senter"
1781
  ],
1782
  "performance":{
1783
+ "token_acc":0.9997681025,
1784
  "token_p":0.99628964,
1785
  "token_r":0.9982863284,
1786
  "token_f":0.9972869848,
1787
+ "pos_acc":0.9763909862,
1788
+ "morph_acc":0.8950409384,
1789
+ "morph_micro_p":0.9487407865,
1790
+ "morph_micro_r":0.9473889605,
1791
+ "morph_micro_f":0.9480643916,
1792
  "morph_per_feat":{
1793
  "Case":{
1794
+ "p":0.9173400026,
1795
+ "r":0.9163997438,
1796
+ "f":0.9168696321
1797
  },
1798
  "Gender":{
1799
+ "p":0.9293213678,
1800
+ "r":0.9285044538,
1801
+ "f":0.9289127312
1802
  },
1803
  "Number":{
1804
+ "p":0.974864879,
1805
+ "r":0.9732816429,
1806
+ "f":0.9740726176
1807
  },
1808
  "AdpType":{
1809
+ "p":0.9994665244,
1810
+ "r":0.9986673774,
1811
+ "f":0.9990667911
1812
  },
1813
  "Variant":{
1814
+ "p":0.9955914769,
1815
  "r":0.9963235294,
1816
+ "f":0.9959573686
1817
  },
1818
  "Animacy":{
1819
+ "p":0.8787806903,
1820
+ "r":0.8847623597,
1821
+ "f":0.8817613805
1822
  },
1823
  "Degree":{
1824
+ "p":0.9340534395,
1825
+ "r":0.9480669359,
1826
+ "f":0.9410080183
1827
  },
1828
  "Aspect":{
1829
+ "p":0.9085039661,
1830
+ "r":0.9043334557,
1831
+ "f":0.9064139137
1832
  },
1833
  "Mood":{
1834
+ "p":0.9826666667,
1835
+ "r":0.9824046921,
1836
+ "f":0.9825356619
1837
  },
1838
  "Person":{
1839
+ "p":0.9815063887,
1840
+ "r":0.9798590131,
1841
+ "f":0.9806820091
1842
  },
1843
  "Tense":{
1844
+ "p":0.9662833246,
1845
+ "r":0.9667887029,
1846
+ "f":0.9665359477
1847
  },
1848
  "VerbForm":{
1849
+ "p":0.9647441692,
1850
+ "r":0.9600575747,
1851
+ "f":0.9623951664
1852
  },
1853
  "Voice":{
1854
+ "p":0.9767299449,
1855
+ "r":0.9699979728,
1856
+ "f":0.973352319
1857
  },
1858
  "PunctType":{
1859
+ "p":0.9982590529,
1860
  "r":0.9975643702,
1861
+ "f":0.9979115907
1862
  },
1863
  "NumForm":{
1864
+ "p":0.9756592292,
1865
+ "r":0.9756592292,
1866
+ "f":0.9756592292
1867
  },
1868
  "PrepCase":{
1869
+ "p":0.9876847291,
1870
+ "r":0.9616306954,
1871
+ "f":0.9744835966
1872
  },
1873
  "PronType":{
1874
+ "p":0.9709631728,
1875
+ "r":0.9574022346,
1876
+ "f":0.9641350211
1877
  },
1878
  "Reflex":{
1879
+ "p":0.9918256131,
1880
  "r":1.0,
1881
+ "f":0.9958960328
1882
  },
1883
  "NumType":{
1884
+ "p":0.9104859335,
1885
+ "r":0.8746928747,
1886
+ "f":0.8922305764
1887
  },
1888
  "Polarity":{
1889
+ "p":0.9047954866,
1890
+ "r":0.8823933975,
1891
+ "f":0.893454039
1892
  },
1893
  "Hyph":{
1894
+ "p":1.0,
1895
+ "r":0.9696969697,
1896
+ "f":0.9846153846
1897
  },
1898
  "VerbType":{
1899
+ "p":0.9342105263,
1900
+ "r":0.9220779221,
1901
+ "f":0.9281045752
1902
  },
1903
  "ConjType":{
1904
+ "p":0.9411764706,
1905
+ "r":0.9536423841,
1906
+ "f":0.9473684211
1907
  },
1908
  "Clitic":{
1909
+ "p":0.9663461538,
1910
  "r":0.9901477833,
1911
+ "f":0.9781021898
1912
  },
1913
  "Poss":{
1914
+ "p":0.9883040936,
1915
+ "r":0.9883040936,
1916
+ "f":0.9883040936
1917
  },
1918
  "Number[psor]":{
1919
  "p":1.0,
1920
+ "r":0.9411764706,
1921
+ "f":0.9696969697
1922
  },
1923
  "PartType":{
1924
+ "p":0.9375,
1925
+ "r":0.8955223881,
1926
+ "f":0.9160305344
1927
  },
1928
  "Abbr":{
1929
+ "p":0.9323671498,
1930
  "r":0.9460784314,
1931
+ "f":0.9391727494
1932
  },
1933
  "Pun":{
1934
+ "p":0.9356725146,
1935
+ "r":0.9302325581,
1936
+ "f":0.9329446064
1937
+ },
1938
+ "Foreign":{
1939
+ "p":0.6,
1940
+ "r":0.5,
1941
+ "f":0.5454545455
1942
  },
1943
  "PunctSide":{
1944
  "p":1.0,
1945
  "r":0.9708333333,
1946
  "f":0.9852008457
1947
  },
 
 
 
 
 
1948
  "Emphatic":{
1949
  "p":1.0,
1950
+ "r":0.6666666667,
1951
+ "f":0.8
1952
  },
1953
  "Polite":{
1954
+ "p":0.5,
1955
+ "r":1.0,
1956
+ "f":0.6666666667
1957
  }
1958
  },
1959
+ "sents_p":0.9663789187,
1960
+ "sents_r":0.9602708804,
1961
+ "sents_f":0.9633152174,
1962
+ "dep_uas":0.8889276191,
1963
+ "dep_las":0.8139397108,
1964
  "dep_las_per_type":{
1965
  "nsubj":{
1966
+ "p":0.8498542274,
1967
+ "r":0.8658415842,
1968
+ "f":0.8577734183
1969
  },
1970
  "case":{
1971
+ "p":0.9675660943,
1972
+ "r":0.9734027968,
1973
+ "f":0.9704756698
1974
  },
1975
  "amod":{
1976
+ "p":0.892732049,
1977
+ "r":0.9147599821,
1978
+ "f":0.9036117882
1979
  },
1980
  "nmod":{
1981
+ "p":0.5712515489,
1982
+ "r":0.5719602978,
1983
+ "f":0.5716057037
1984
  },
1985
  "cc":{
1986
+ "p":0.8711538462,
1987
+ "r":0.88218111,
1988
+ "f":0.8766328012
1989
  },
1990
  "conj":{
1991
+ "p":0.6463878327,
1992
+ "r":0.6623376623,
1993
+ "f":0.6542655548
1994
  },
1995
  "root":{
1996
+ "p":0.9396277803,
1997
+ "r":0.934537246,
1998
+ "f":0.9370755998
1999
  },
2000
  "obl":{
2001
+ "p":0.7137445887,
2002
+ "r":0.7215536105,
2003
+ "f":0.7176278564
2004
  },
2005
  "obl:arg":{
2006
+ "p":0.6746835443,
2007
+ "r":0.6263219741,
2008
+ "f":0.6496039001
2009
  },
2010
  "nummod":{
2011
+ "p":0.8601398601,
2012
+ "r":0.8785714286,
2013
+ "f":0.8692579505
2014
  },
2015
  "obj":{
2016
+ "p":0.8260869565,
2017
+ "r":0.8455497382,
2018
+ "f":0.8357050453
2019
  },
2020
  "advcl":{
2021
+ "p":0.6818181818,
2022
+ "r":0.6936416185,
2023
+ "f":0.6876790831
2024
  },
2025
  "iobj":{
2026
+ "p":0.7407407407,
2027
+ "r":0.7153965785,
2028
+ "f":0.7278481013
2029
  },
2030
  "det:numgov":{
2031
+ "p":0.962962963,
2032
+ "r":0.8965517241,
2033
+ "f":0.9285714286
2034
  },
2035
  "acl":{
2036
+ "p":0.7359307359,
2037
+ "r":0.6910569106,
2038
+ "f":0.71278826
2039
  },
2040
  "fixed":{
2041
+ "p":0.8280802292,
2042
+ "r":0.7526041667,
2043
+ "f":0.7885402456
2044
  },
2045
  "nummod:gov":{
2046
+ "p":0.8301886792,
2047
+ "r":0.8148148148,
2048
+ "f":0.8224299065
2049
  },
2050
  "obl:agent":{
2051
+ "p":0.8947368421,
2052
+ "r":0.8360655738,
2053
+ "f":0.8644067797
2054
  },
2055
  "expl:pv":{
2056
+ "p":0.9717138103,
2057
+ "r":0.9733333333,
2058
+ "f":0.9725228976
2059
  },
2060
  "nmod:arg":{
2061
+ "p":0.6119733925,
2062
+ "r":0.6337543054,
2063
+ "f":0.6226734349
2064
  },
2065
  "advmod":{
2066
+ "p":0.8255915863,
2067
+ "r":0.8410714286,
2068
+ "f":0.8332596196
2069
  },
2070
  "acl:relcl":{
2071
+ "p":0.7093425606,
2072
+ "r":0.7068965517,
2073
+ "f":0.7081174439
2074
  },
2075
  "advmod:emph":{
2076
+ "p":0.7136842105,
2077
+ "r":0.7033195021,
2078
+ "f":0.7084639498
 
 
 
 
 
 
 
 
 
 
2079
  },
2080
  "mark":{
2081
+ "p":0.8723098996,
2082
+ "r":0.8624113475,
2083
+ "f":0.8673323823
2084
  },
2085
  "ccomp:obj":{
2086
+ "p":0.6413043478,
2087
+ "r":0.6555555556,
2088
+ "f":0.6483516484
2089
  },
2090
  "appos":{
2091
+ "p":0.6444444444,
2092
+ "r":0.6066945607,
2093
+ "f":0.625
 
 
 
 
 
2094
  },
2095
  "xcomp":{
2096
  "p":0.9267734554,
2103
  "f":0.9668508287
2104
  },
2105
  "det":{
2106
+ "p":0.9119804401,
2107
+ "r":0.8944844125,
2108
+ "f":0.9031476998
2109
  },
2110
  "cop":{
2111
+ "p":0.8888888889,
2112
+ "r":0.8648648649,
2113
+ "f":0.8767123288
2114
  },
2115
  "nsubj:pass":{
2116
+ "p":0.7522123894,
2117
+ "r":0.7798165138,
2118
+ "f":0.7657657658
2119
  },
2120
  "aux:pass":{
2121
+ "p":0.9127516779,
2122
+ "r":0.9444444444,
2123
+ "f":0.9283276451
2124
  },
2125
  "aux:imp":{
2126
  "p":1.0,
2127
+ "r":0.7777777778,
2128
+ "f":0.875
2129
  },
2130
  "advcl:cmpr":{
2131
+ "p":0.4285714286,
2132
+ "r":0.1875,
2133
+ "f":0.2608695652
2134
  },
2135
  "obl:cmpr":{
2136
+ "p":0.7083333333,
2137
+ "r":0.5730337079,
2138
+ "f":0.6335403727
2139
  },
2140
  "ccomp":{
2141
+ "p":0.6411483254,
2142
+ "r":0.6261682243,
2143
+ "f":0.63356974
2144
  },
2145
  "nmod:poss":{
2146
+ "p":1.0,
2147
  "r":0.1666666667,
2148
+ "f":0.2857142857
2149
+ },
2150
+ "parataxis:insert":{
2151
+ "p":0.5555555556,
2152
+ "r":0.4187192118,
2153
+ "f":0.4775280899
2154
  },
2155
  "det:poss":{
2156
+ "p":0.9880239521,
2157
+ "r":0.9593023256,
2158
+ "f":0.9734513274
2159
  },
2160
  "aux":{
2161
+ "p":0.8773584906,
2162
+ "r":0.8532110092,
2163
+ "f":0.8651162791
2164
  },
2165
  "cc:preconj":{
2166
+ "p":0.5833333333,
2167
  "r":0.5384615385,
2168
+ "f":0.56
2169
  },
2170
  "flat":{
2171
+ "p":0.8694158076,
2172
+ "r":0.8784722222,
2173
+ "f":0.8739205527
2174
  },
2175
  "xcomp:pred":{
2176
+ "p":0.696969697,
2177
+ "r":0.5609756098,
2178
+ "f":0.6216216216
2179
  },
2180
  "parataxis:obj":{
2181
+ "p":0.7175925926,
2182
+ "r":0.8031088083,
2183
+ "f":0.7579462103
2184
  },
2185
  "vocative":{
2186
+ "p":0.5185185185,
2187
+ "r":0.5,
2188
+ "f":0.5090909091
 
 
 
 
 
2189
  },
2190
  "aux:cnd":{
2191
  "p":0.8571428571,
2193
  "f":0.8
2194
  },
2195
  "advmod:arg":{
2196
+ "p":1.0,
2197
  "r":0.1111111111,
2198
+ "f":0.2
2199
  },
2200
  "csubj":{
2201
+ "p":0.7272727273,
2202
+ "r":0.3636363636,
2203
+ "f":0.4848484848
2204
  },
2205
  "amod:flat":{
2206
+ "p":0.8172043011,
2207
+ "r":0.8042328042,
2208
+ "f":0.8106666667
2209
  },
2210
  "nmod:flat":{
2211
+ "p":0.7179487179,
2212
+ "r":0.7,
2213
+ "f":0.7088607595
2214
+ },
2215
+ "dep":{
2216
+ "p":0.0,
2217
+ "r":0.0,
2218
+ "f":0.0
2219
  },
2220
  "det:nummod":{
2221
+ "p":1.0,
2222
  "r":1.0,
2223
+ "f":1.0
2224
  },
2225
  "nmod:pred":{
2226
  "p":0.0,
2228
  "f":0.0
2229
  },
2230
  "ccomp:cleft":{
2231
+ "p":0.8235294118,
2232
+ "r":0.8235294118,
2233
+ "f":0.8235294118
2234
  },
2235
  "list":{
2236
+ "p":0.8823529412,
2237
+ "r":0.7692307692,
2238
+ "f":0.8219178082
2239
  },
2240
  "xcomp:subj":{
2241
  "p":0.0,
2247
  "r":0.0,
2248
  "f":0.0
2249
  },
2250
+ "discourse:intj":{
2251
+ "p":0.125,
2252
+ "r":0.1111111111,
2253
+ "f":0.1176470588
2254
+ },
2255
  "xcomp:cleft":{
2256
  "p":1.0,
2257
  "r":1.0,
2258
  "f":1.0
2259
  },
2260
+ "advcl:relcl":{
2261
+ "p":0.5,
2262
+ "r":0.25,
2263
+ "f":0.3333333333
2264
+ },
2265
  "obl:orphan":{
2266
  "p":0.0,
2267
  "r":0.0,
2268
  "f":0.0
2269
  }
2270
  },
2271
+ "lemma_acc":0.9361695953,
2272
+ "tag_acc":0.9816474605,
2273
+ "ents_p":0.828425096,
2274
+ "ents_r":0.8247291268,
2275
+ "ents_f":0.8265729799,
2276
  "ents_per_type":{
2277
  "placeName":{
2278
+ "p":0.808411215,
2279
+ "r":0.808411215,
2280
+ "f":0.808411215
2281
  },
2282
  "orgName":{
2283
+ "p":0.7828947368,
2284
+ "r":0.7628205128,
2285
+ "f":0.7727272727
2286
  },
2287
  "date":{
2288
+ "p":0.9405940594,
2289
+ "r":0.8796296296,
2290
+ "f":0.9090909091
2291
  },
2292
  "persName":{
2293
+ "p":0.8708609272,
2294
+ "r":0.8900169205,
2295
+ "f":0.880334728
2296
  },
2297
  "time":{
2298
+ "p":0.8518518519,
2299
  "r":0.92,
2300
+ "f":0.8846153846
2301
  },
2302
  "geogName":{
2303
+ "p":0.6734693878,
2304
+ "r":0.6285714286,
2305
+ "f":0.6502463054
2306
  }
2307
  },
2308
+ "speed":7725.6968010248
2309
  },
2310
  "sources":[
2311
  {
morphologizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:519314542bea2cafc5e265ca806ce7a1312eb4653341637304513c2f250e9d9e
3
  size 630554
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:039134274d06c24307addcba5ed272504d8f4cf94e12c21d14f58baae433a2ca
3
  size 630554
ner/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c1a0815e0b51bbaf484c87af0dd8cd74333d317cd4150a12ebd406821106496
3
- size 6498672
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f88d85725fec63a4948ead00ed2d5ac136d8bfe4a4930dbc059a741b19673d3a
3
+ size 6368462
parser/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfb39e05f8212c0846691a96fa815fd5d3ec24d5195eef079a8f9c3f0184f7f2
3
  size 318869
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5703a13ce15d70ef417b72bdb3137d60e94830dc39818cdefd86ee50177cc9c5
3
  size 318869
pl_core_news_md-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c21261f21abf67278589a7cba1ab0cc306eb9ee19e42b2f4a2e23e94b40a2196
3
- size 49372312
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb6eead5f1831eb40f56a38d79ec448c26d97263ad8648a8ea8bf941c088385b
3
+ size 49491360
senter/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2357aa5daee06162ff690352fb7742594eb31e565c5c8b70227145ec7e0342c
3
  size 219953
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f5e9f4406b3f1127b94c9f22f1070468f81e6b5de5a9a71bde0c6050a76ae4c
3
  size 219953
tagger/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e87ca8d781f9488e71769a1ebf368a5e4792d190f54c1cb4ab3b88c6cb152284
3
- size 6380361
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec162a34ca831e67fbc6714cd9aa86bc17cdb332da6dbd2d940e223be6b15b67
3
+ size 6510574
tok2vec/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:979c28a57e678b900df386ff0900ae2b548f24adf68d5268bc10d410b0638dc1
3
- size 6365604
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2939d86ce9b6bc2a367f41266f8f5a984de7449d495bb92f9aa5944f5d7cbaf1
3
+ size 6495793
tokenizer CHANGED
@@ -1,3 +1,3 @@
1
- ��prefix_search� �^(długo|krótko|jedno|dwu|trzy|cztero)-|^§|^%|^=|^—|^–|^\+(?![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�&m''$|’’$|\.$|…$|…$|……$|,$|:$|;$|\!$|\?$|¿$|؟$|¡$|\($|\)$|\[$|\]$|\{$|\}$|<$|>$|_$|#$|\*$|&$|。$|?$|!$|,$|、$|;$|:$|~$|·$|।$|،$|۔$|؛$|٪$|\'$|"$|”$|“$|`$|‘$|´$|’$|‚$|,$|„$|»$|«$|「$|」$|『$|』$|($|)$|〔$|〕$|【$|】$|《$|》$|〈$|〉$|[\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]$|(?<=[0-9])\+$|(?<=°[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)$|(?<=[0-9a-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%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\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])\.$�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]|-|–|—|--|---|——|~|(?<=[0-9A-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])\.(?=[0-9A-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-\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-\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])�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�-__-�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�;-)�;-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�^___^�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�v.v��A�v.v�v_v��A�v_v�xD��A�xD�xDD��A�xDD� ��A� C� �¯\(ツ)/¯��A�¯\(ツ)/¯�ಠ_ಠ��A�ಠ_ಠ�ಠ︵ಠ��A�ಠ︵ಠ�—��A�—�faster_heuristics�
1
+ ��prefix_search� �^(długo|krótko|jedno|dwu|trzy|cztero)-|^§|^%|^=|^—|^–|^\+(?![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�&�''$|’’$|\.$|…$|…$|……$|,$|:$|;$|\!$|\?$|¿$|؟$|¡$|\($|\)$|\[$|\]$|\{$|\}$|<$|>$|_$|#$|\*$|&$|。$|?$|!$|,$|、$|;$|:$|~$|·$|।$|،$|۔$|؛$|٪$|\'$|"$|”$|“$|`$|‘$|´$|’$|‚$|,$|„$|»$|«$|「$|」$|『$|』$|($|)$|〔$|〕$|【$|】$|《$|》$|〈$|〉$|〈$|〉$|⟦$|⟧$|[\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]$|(?<=[0-9])\+$|(?<=°[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)$|(?<=[0-9a-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%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\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])\.$�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]|-|–|—|--|---|——|~|(?<=[0-9A-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])\.(?=[0-9A-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-\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-\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])�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�-__-�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�;-)�;-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�^___^�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�v.v��A�v.v�v_v��A�v_v�xD��A�xD�xDD��A�xDD� ��A� C� �¯\(ツ)/¯��A�¯\(ツ)/¯�ಠ_ಠ��A�ಠ_ಠ�ಠ︵ಠ��A�ಠ︵ಠ�—��A�—�faster_heuristics�
vocab/strings.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39f085f5ad0c5629d21f37f870aebb9ab25a388358133e1731d22aaf5fc22b8f
3
- size 11412502
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ffeb76dfcad63dcd6ccf737578b127645618fe0ca10d42b8126f26deeeb79d9
3
+ size 11407521