elisno commited on
Commit
325da04
1 Parent(s): 67b8a78

Update spaCy pipeline

Browse files
.gitattributes CHANGED
@@ -25,3 +25,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ *.whl filter=lfs diff=lfs merge=lfs -text
29
+ *.npz filter=lfs diff=lfs merge=lfs -text
30
+ *strings.json filter=lfs diff=lfs merge=lfs -text
31
+ vectors filter=lfs diff=lfs merge=lfs -text
32
+ model filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - spacy
4
+ - token-classification
5
+ language:
6
+ - is
7
+ model-index:
8
+ - name: is_core_web_trf
9
+ results:
10
+ - task:
11
+ name: NER
12
+ type: token-classification
13
+ metrics:
14
+ - name: NER Precision
15
+ type: precision
16
+ value: 0.9193318395
17
+ - name: NER Recall
18
+ type: recall
19
+ value: 0.9217728758
20
+ - name: NER F Score
21
+ type: f_score
22
+ value: 0.9205507394
23
+ ---
24
+ | Feature | Description |
25
+ | --- | --- |
26
+ | **Name** | `is_core_web_trf` |
27
+ | **Version** | `0.0.0` |
28
+ | **spaCy** | `>=3.1.1,<3.2.0` |
29
+ | **Default Pipeline** | `transformer`, `ner`, `tagger`, `parser` |
30
+ | **Components** | `transformer`, `ner`, `tagger`, `parser` |
31
+ | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
32
+ | **Sources** | n/a |
33
+ | **License** | n/a |
34
+ | **Author** | [n/a]() |
35
+
36
+ ### Label Scheme
37
+
38
+ <details>
39
+
40
+ <summary>View label scheme (591 labels for 3 components)</summary>
41
+
42
+ | Component | Labels |
43
+ | --- | --- |
44
+ | **`ner`** | `Date`, `Location`, `Miscellaneous`, `Money`, `Organization`, `Percent`, `Person`, `Time` |
45
+ | **`tagger`** | `aa`, `aae`, `aam`, `af`, `afe`, `afm`, `au`, `c`, `cn`, `ct`, `e`, `fahee`, `fahen`, `faheo`, `faheþ`, `fahfe`, `fahfn`, `fahfo`, `fahfþ`, `fakee`, `faken`, `fakeo`, `fakeþ`, `fakfe`, `fakfn`, `fakfo`, `fakfþ`, `favee`, `faven`, `faveo`, `faveþ`, `favfe`, `favfn`, `favfo`, `favfþ`, `fbhee`, `fbhen`, `fbheo`, `fbheþ`, `fbhfe`, `fbhfn`, `fbhfo`, `fbhfþ`, `fbkee`, `fbken`, `fbkeo`, `fbkeþ`, `fbkfe`, `fbkfn`, `fbkfo`, `fbkfþ`, `fbvee`, `fbven`, `fbveo`, `fbveþ`, `fbvfe`, `fbvfn`, `fbvfo`, `fbvfþ`, `fehee`, `fehen`, `feheo`, `feheþ`, `fehfe`, `fehfn`, `fehfo`, `fehfþ`, `fekee`, `feken`, `fekeo`, `fekeþ`, `fekfe`, `fekfn`, `fekfo`, `fekfþ`, `fevee`, `feven`, `feveo`, `feveþ`, `fevfe`, `fevfn`, `fevfo`, `fevfþ`, `fohee`, `fohen`, `foheo`, `foheþ`, `fohfe`, `fohfn`, `fohfo`, `fohfþ`, `fokee`, `foken`, `fokeo`, `fokeþ`, `fokfe`, `fokfn`, `fokfo`, `fokfþ`, `fovee`, `foven`, `foveo`, `foveþ`, `fovfe`, `fovfn`, `fovfo`, `fovfþ`, `fp1ee`, `fp1en`, `fp1eo`, `fp1eþ`, `fp1fe`, `fp1fn`, `fp1fo`, `fp1fþ`, `fp2ee`, `fp2en`, `fp2eo`, `fp2eþ`, `fp2fe`, `fp2fn`, `fp2fo`, `fp2fþ`, `fphee`, `fphen`, `fpheo`, `fpheþ`, `fphfe`, `fphfn`, `fphfo`, `fphfþ`, `fpkee`, `fpken`, `fpkeo`, `fpkeþ`, `fpkfe`, `fpkfn`, `fpkfo`, `fpkfþ`, `fpvee`, `fpven`, `fpveo`, `fpveþ`, `fpvfe`, `fpvfn`, `fpvfo`, `fpvfþ`, `fshee`, `fshen`, `fsheo`, `fsheþ`, `fshfe`, `fshfn`, `fshfo`, `fshfþ`, `fskee`, `fsken`, `fskeo`, `fskeþ`, `fskfe`, `fskfn`, `fskfo`, `fskfþ`, `fsvee`, `fsven`, `fsveo`, `fsveþ`, `fsvfe`, `fsvfn`, `fsvfo`, `fsvfþ`, `ghee`, `ghen`, `gheo`, `gheþ`, `ghfe`, `ghfn`, `ghfo`, `ghfþ`, `gkee`, `gken`, `gkeo`, `gkeþ`, `gkfe`, `gkfn`, `gkfo`, `gkfþ`, `gvee`, `gven`, `gveo`, `gveþ`, `gvfe`, `gvfn`, `gvfo`, `gvfþ`, `ks`, `kt`, `lheeof`, `lheesf`, `lheeve`, `lheevf`, `lheevm`, `lhenof`, `lhense`, `lhensf`, `lhenve`, `lhenvf`, `lhenvm`, `lheoof`, `lheose`, `lheosf`, `lheosm`, `lheove`, `lheovf`, `lheovm`, `lheþof`, `lheþse`, `lheþsf`, `lheþve`, `lheþvf`, `lheþvm`, `lhfeof`, `lhfese`, `lhfesf`, `lhfeve`, `lhfevf`, `lhfevm`, `lhfnof`, `lhfnse`, `lhfnsf`, `lhfnve`, `lhfnvf`, `lhfnvm`, `lhfoof`, `lhfose`, `lhfosf`, `lhfove`, `lhfovf`, `lhfovm`, `lhfþof`, `lhfþse`, `lhfþsf`, `lhfþve`, `lhfþvf`, `lhfþvm`, `lkeeof`, `lkeesf`, `lkeeve`, `lkeevf`, `lkeevm`, `lkenof`, `lkense`, `lkensf`, `lkenve`, `lkenvf`, `lkenvm`, `lkeoof`, `lkeose`, `lkeosf`, `lkeove`, `lkeovf`, `lkeovm`, `lkeþof`, `lkeþse`, `lkeþsf`, `lkeþve`, `lkeþvf`, `lkeþvm`, `lkfeof`, `lkfese`, `lkfesf`, `lkfeve`, `lkfevf`, `lkfevm`, `lkfnof`, `lkfnse`, `lkfnsf`, `lkfnve`, `lkfnvf`, `lkfnvm`, `lkfoof`, `lkfose`, `lkfosf`, `lkfove`, `lkfovf`, `lkfovm`, `lkfþof`, `lkfþse`, `lkfþsf`, `lkfþsm`, `lkfþve`, `lkfþvf`, `lkfþvm`, `lveeof`, `lveese`, `lveesf`, `lveeve`, `lveevf`, `lveevm`, `lvenof`, `lvense`, `lvensf`, `lvenve`, `lvenvf`, `lvenvm`, `lveoof`, `lveose`, `lveosf`, `lveove`, `lveovf`, `lveovm`, `lveþof`, `lveþse`, `lveþsf`, `lveþve`, `lveþvf`, `lveþvm`, `lvfeof`, `lvfese`, `lvfesf`, `lvfeve`, `lvfevf`, `lvfevm`, `lvfnof`, `lvfnse`, `lvfnsf`, `lvfnve`, `lvfnvf`, `lvfnvm`, `lvfoof`, `lvfose`, `lvfosf`, `lvfove`, `lvfovf`, `lvfovm`, `lvfþof`, `lvfþse`, `lvfþsf`, `lvfþsm`, `lvfþve`, `lvfþvf`, `lvfþvm`, `m`, `n----s`, `n-ee`, `n-ee-s`, `n-en`, `n-en-s`, `n-eng`, `n-eo`, `n-eo-s`, `n-eþ`, `n-eþ-s`, `n-fn`, `nhee`, `nhee-s`, `nheeg`, `nheegs`, `nhen`, `nhen-s`, `nheng`, `nhengs`, `nheo`, `nheo-s`, `nheog`, `nheogs`, `nheþ`, `nheþ-s`, `nheþg`, `nheþgs`, `nhfe`, `nhfe-s`, `nhfeg`, `nhfegs`, `nhfn`, `nhfn-s`, `nhfng`, `nhfngs`, `nhfo`, `nhfo-s`, `nhfog`, `nhfogs`, `nhfþ`, `nhfþ-s`, `nhfþg`, `nhfþgs`, `nkee`, `nkee-s`, `nkeeg`, `nkeegs`, `nken`, `nken-s`, `nkeng`, `nkengs`, `nkeo`, `nkeo-s`, `nkeog`, `nkeogs`, `nkeþ`, `nkeþ-s`, `nkeþg`, `nkeþgs`, `nkfe`, `nkfe-s`, `nkfeg`, `nkfegs`, `nkfn`, `nkfn-s`, `nkfng`, `nkfngs`, `nkfo`, `nkfo-s`, `nkfog`, `nkfogs`, `nkfþ`, `nkfþ-s`, `nkfþg`, `nkfþgs`, `nvee`, `nvee-s`, `nveeg`, `nveegs`, `nven`, `nven-s`, `nveng`, `nvengs`, `nveo`, `nveo-s`, `nveog`, `nveogs`, `nveþ`, `nveþ-s`, `nveþg`, `nveþgs`, `nvfe`, `nvfe-s`, `nvfeg`, `nvfegs`, `nvfn`, `nvfn-s`, `nvfng`, `nvfngs`, `nvfo`, `nvfo-s`, `nvfog`, `nvfogs`, `nvfþ`, `nvfþ-s`, `nvfþg`, `nvfþgs`, `pa`, `pg`, `pk`, `pl`, `sbg2en`, `sbg2fn`, `sbm2en`, `sbm2fn`, `sfg1en`, `sfg1eþ`, `sfg1fn`, `sfg1fþ`, `sfg2en`, `sfg2eþ`, `sfg2fn`, `sfg2fþ`, `sfg3en`, `sfg3eþ`, `sfg3fn`, `sfg3fþ`, `sfm1en`, `sfm1eþ`, `sfm1fn`, `sfm1fþ`, `sfm2en`, `sfm2eþ`, `sfm2fn`, `sfm2fþ`, `sfm3en`, `sfm3eþ`, `sfm3fn`, `sfm3fþ`, `slg`, `sng`, `snm`, `svg1en`, `svg1eþ`, `svg1fn`, `svg1fþ`, `svg2en`, `svg2eþ`, `svg2fn`, `svg2fþ`, `svg3en`, `svg3eþ`, `svg3fn`, `svg3fþ`, `svm1en`, `svm1eþ`, `svm1fn`, `svm1fþ`, `svm2en`, `svm2eþ`, `svm2fn`, `svm3en`, `svm3eþ`, `svm3fn`, `svm3fþ`, `sþghen`, `sþgheo`, `sþghfn`, `sþghfo`, `sþgken`, `sþgkeo`, `sþgkfn`, `sþgkfo`, `sþgven`, `sþgveo`, `sþgvfn`, `sþgvfo`, `sþgvfþ`, `sþmhen`, `sþmheo`, `sþmken`, `sþmven`, `ta`, `tfhee`, `tfhen`, `tfheo`, `tfheþ`, `tfhfe`, `tfhfn`, `tfhfo`, `tfhfþ`, `tfkee`, `tfken`, `tfkeo`, `tfkeþ`, `tfkfe`, `tfkfn`, `tfkfo`, `tfkfþ`, `tfvee`, `tfven`, `tfveo`, `tfveþ`, `tfvfe`, `tfvfn`, `tfvfo`, `tfvfþ`, `to`, `tp`, `v`, `x` |
46
+ | **`parser`** | `ROOT`, `acl`, `acl:relcl`, `advcl`, `advmod`, `amod`, `appos`, `aux`, `case`, `cc`, `ccomp`, `compound:prt`, `conj`, `cop`, `dep`, `det`, `fixed`, `flat:name`, `mark`, `nmod`, `nmod:poss`, `nsubj`, `nummod`, `obj`, `obl`, `obl:arg`, `parataxis`, `punct`, `xcomp` |
47
+
48
+ </details>
49
+
50
+ ### Accuracy
51
+
52
+ | Type | Score |
53
+ | --- | --- |
54
+ | `ENTS_F` | 92.06 |
55
+ | `ENTS_P` | 91.93 |
56
+ | `ENTS_R` | 92.18 |
57
+ | `TRANSFORMER_LOSS` | 248325.98 |
58
+ | `NER_LOSS` | 120059.07 |
config.cfg ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [paths]
2
+ train = "corpus/MIM-GOLD-NER/train.spacy"
3
+ dev = "corpus/MIM-GOLD-NER/dev.spacy"
4
+ vectors = null
5
+ init_tok2vec = null
6
+
7
+ [system]
8
+ gpu_allocator = "pytorch"
9
+ seed = 0
10
+
11
+ [nlp]
12
+ lang = "is"
13
+ pipeline = ["transformer","ner","tagger","parser"]
14
+ batch_size = 128
15
+ disabled = []
16
+ before_creation = null
17
+ after_creation = null
18
+ after_pipeline_creation = null
19
+ tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
20
+
21
+ [components]
22
+
23
+ [components.ner]
24
+ factory = "ner"
25
+ incorrect_spans_key = null
26
+ moves = null
27
+ update_with_oracle_cut_size = 100
28
+
29
+ [components.ner.model]
30
+ @architectures = "spacy.TransitionBasedParser.v2"
31
+ state_type = "ner"
32
+ extra_state_tokens = false
33
+ hidden_width = 64
34
+ maxout_pieces = 2
35
+ use_upper = false
36
+ nO = null
37
+
38
+ [components.ner.model.tok2vec]
39
+ @architectures = "spacy-transformers.TransformerListener.v1"
40
+ grad_factor = 1.0
41
+ pooling = {"@layers":"reduce_mean.v1"}
42
+ upstream = "*"
43
+
44
+ [components.parser]
45
+ factory = "parser"
46
+ learn_tokens = false
47
+ min_action_freq = 30
48
+ moves = null
49
+ update_with_oracle_cut_size = 100
50
+
51
+ [components.parser.model]
52
+ @architectures = "spacy.TransitionBasedParser.v2"
53
+ state_type = "parser"
54
+ extra_state_tokens = false
55
+ hidden_width = 128
56
+ maxout_pieces = 3
57
+ use_upper = false
58
+ nO = null
59
+
60
+ [components.parser.model.tok2vec]
61
+ @architectures = "spacy-transformers.TransformerListener.v1"
62
+ grad_factor = 1.0
63
+ pooling = {"@layers":"reduce_mean.v1"}
64
+ upstream = "*"
65
+
66
+ [components.tagger]
67
+ factory = "tagger"
68
+
69
+ [components.tagger.model]
70
+ @architectures = "spacy.Tagger.v1"
71
+ nO = null
72
+
73
+ [components.tagger.model.tok2vec]
74
+ @architectures = "spacy.Tok2Vec.v1"
75
+
76
+ [components.tagger.model.tok2vec.embed]
77
+ @architectures = "spacy.MultiHashEmbed.v1"
78
+ width = 128
79
+ attrs = ["NORM","PREFIX","SUFFIX","LOWER"]
80
+ rows = [5000,2500,2500,2500]
81
+ include_static_vectors = true
82
+
83
+ [components.tagger.model.tok2vec.encode]
84
+ @architectures = "spacy.MaxoutWindowEncoder.v1"
85
+ width = 128
86
+ depth = 4
87
+ window_size = 1
88
+ maxout_pieces = 3
89
+
90
+ [components.transformer]
91
+ factory = "transformer"
92
+ max_batch_items = 4096
93
+ set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
94
+
95
+ [components.transformer.model]
96
+ @architectures = "spacy-transformers.TransformerModel.v1"
97
+ name = "mideind/IceBERT"
98
+
99
+ [components.transformer.model.get_spans]
100
+ @span_getters = "spacy-transformers.strided_spans.v1"
101
+ window = 128
102
+ stride = 96
103
+
104
+ [components.transformer.model.tokenizer_config]
105
+ use_fast = true
106
+
107
+ [corpora]
108
+
109
+ [corpora.dev]
110
+ @readers = "spacy.Corpus.v1"
111
+ path = ${paths.dev}
112
+ max_length = 512
113
+ gold_preproc = false
114
+ limit = 0
115
+ augmenter = null
116
+
117
+ [corpora.train]
118
+ @readers = "spacy.Corpus.v1"
119
+ path = ${paths.train}
120
+ max_length = 512
121
+ gold_preproc = false
122
+ limit = 0
123
+ augmenter = null
124
+
125
+ [training]
126
+ accumulate_gradient = 3
127
+ dev_corpus = "corpora.dev"
128
+ train_corpus = "corpora.train"
129
+ seed = ${system.seed}
130
+ gpu_allocator = ${system.gpu_allocator}
131
+ dropout = 0.1
132
+ patience = 1600
133
+ max_epochs = 0
134
+ max_steps = 20000
135
+ eval_frequency = 200
136
+ frozen_components = []
137
+ annotating_components = []
138
+ before_to_disk = null
139
+
140
+ [training.batcher]
141
+ @batchers = "spacy.batch_by_padded.v1"
142
+ discard_oversize = true
143
+ size = 2000
144
+ buffer = 256
145
+ get_length = null
146
+
147
+ [training.logger]
148
+ @loggers = "spacy.ConsoleLogger.v1"
149
+ progress_bar = false
150
+
151
+ [training.optimizer]
152
+ @optimizers = "Adam.v1"
153
+ beta1 = 0.9
154
+ beta2 = 0.999
155
+ L2_is_weight_decay = true
156
+ L2 = 0.01
157
+ grad_clip = 1.0
158
+ use_averages = false
159
+ eps = 0.00000001
160
+
161
+ [training.optimizer.learn_rate]
162
+ @schedules = "warmup_linear.v1"
163
+ warmup_steps = 250
164
+ total_steps = 20000
165
+ initial_rate = 0.00005
166
+
167
+ [training.score_weights]
168
+ ents_f = 0.33
169
+ ents_p = 0.0
170
+ ents_r = 0.0
171
+ ents_per_type = null
172
+ tag_acc = 0.33
173
+ dep_uas = 0.17
174
+ dep_las = 0.17
175
+ dep_las_per_type = null
176
+ sents_p = null
177
+ sents_r = null
178
+ sents_f = 0.0
179
+
180
+ [pretraining]
181
+
182
+ [initialize]
183
+ vectors = ${paths.vectors}
184
+ init_tok2vec = ${paths.init_tok2vec}
185
+ vocab_data = null
186
+ lookups = null
187
+ before_init = null
188
+ after_init = null
189
+
190
+ [initialize.components]
191
+
192
+ [initialize.tokenizer]
is_core_web_trf-any-py3-none-any.whl ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba588ce94773e4749c944d4420b7600bbd56e21e0f3e7f7931561de07657b4cc
3
+ size 471601718
meta.json ADDED
@@ -0,0 +1,690 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "lang":"is",
3
+ "name":"core_web_trf",
4
+ "version":"0.0.0",
5
+ "description":"",
6
+ "author":"",
7
+ "email":"",
8
+ "url":"",
9
+ "license":"",
10
+ "spacy_version":">=3.1.1,<3.2.0",
11
+ "spacy_git_version":"ffaead8fe",
12
+ "vectors":{
13
+ "width":0,
14
+ "vectors":0,
15
+ "keys":0,
16
+ "name":null
17
+ },
18
+ "labels":{
19
+ "transformer":[
20
+
21
+ ],
22
+ "ner":[
23
+ "Date",
24
+ "Location",
25
+ "Miscellaneous",
26
+ "Money",
27
+ "Organization",
28
+ "Percent",
29
+ "Person",
30
+ "Time"
31
+ ],
32
+ "tagger":[
33
+ "aa",
34
+ "aae",
35
+ "aam",
36
+ "af",
37
+ "afe",
38
+ "afm",
39
+ "au",
40
+ "c",
41
+ "cn",
42
+ "ct",
43
+ "e",
44
+ "fahee",
45
+ "fahen",
46
+ "faheo",
47
+ "fahe\u00fe",
48
+ "fahfe",
49
+ "fahfn",
50
+ "fahfo",
51
+ "fahf\u00fe",
52
+ "fakee",
53
+ "faken",
54
+ "fakeo",
55
+ "fake\u00fe",
56
+ "fakfe",
57
+ "fakfn",
58
+ "fakfo",
59
+ "fakf\u00fe",
60
+ "favee",
61
+ "faven",
62
+ "faveo",
63
+ "fave\u00fe",
64
+ "favfe",
65
+ "favfn",
66
+ "favfo",
67
+ "favf\u00fe",
68
+ "fbhee",
69
+ "fbhen",
70
+ "fbheo",
71
+ "fbhe\u00fe",
72
+ "fbhfe",
73
+ "fbhfn",
74
+ "fbhfo",
75
+ "fbhf\u00fe",
76
+ "fbkee",
77
+ "fbken",
78
+ "fbkeo",
79
+ "fbke\u00fe",
80
+ "fbkfe",
81
+ "fbkfn",
82
+ "fbkfo",
83
+ "fbkf\u00fe",
84
+ "fbvee",
85
+ "fbven",
86
+ "fbveo",
87
+ "fbve\u00fe",
88
+ "fbvfe",
89
+ "fbvfn",
90
+ "fbvfo",
91
+ "fbvf\u00fe",
92
+ "fehee",
93
+ "fehen",
94
+ "feheo",
95
+ "fehe\u00fe",
96
+ "fehfe",
97
+ "fehfn",
98
+ "fehfo",
99
+ "fehf\u00fe",
100
+ "fekee",
101
+ "feken",
102
+ "fekeo",
103
+ "feke\u00fe",
104
+ "fekfe",
105
+ "fekfn",
106
+ "fekfo",
107
+ "fekf\u00fe",
108
+ "fevee",
109
+ "feven",
110
+ "feveo",
111
+ "feve\u00fe",
112
+ "fevfe",
113
+ "fevfn",
114
+ "fevfo",
115
+ "fevf\u00fe",
116
+ "fohee",
117
+ "fohen",
118
+ "foheo",
119
+ "fohe\u00fe",
120
+ "fohfe",
121
+ "fohfn",
122
+ "fohfo",
123
+ "fohf\u00fe",
124
+ "fokee",
125
+ "foken",
126
+ "fokeo",
127
+ "foke\u00fe",
128
+ "fokfe",
129
+ "fokfn",
130
+ "fokfo",
131
+ "fokf\u00fe",
132
+ "fovee",
133
+ "foven",
134
+ "foveo",
135
+ "fove\u00fe",
136
+ "fovfe",
137
+ "fovfn",
138
+ "fovfo",
139
+ "fovf\u00fe",
140
+ "fp1ee",
141
+ "fp1en",
142
+ "fp1eo",
143
+ "fp1e\u00fe",
144
+ "fp1fe",
145
+ "fp1fn",
146
+ "fp1fo",
147
+ "fp1f\u00fe",
148
+ "fp2ee",
149
+ "fp2en",
150
+ "fp2eo",
151
+ "fp2e\u00fe",
152
+ "fp2fe",
153
+ "fp2fn",
154
+ "fp2fo",
155
+ "fp2f\u00fe",
156
+ "fphee",
157
+ "fphen",
158
+ "fpheo",
159
+ "fphe\u00fe",
160
+ "fphfe",
161
+ "fphfn",
162
+ "fphfo",
163
+ "fphf\u00fe",
164
+ "fpkee",
165
+ "fpken",
166
+ "fpkeo",
167
+ "fpke\u00fe",
168
+ "fpkfe",
169
+ "fpkfn",
170
+ "fpkfo",
171
+ "fpkf\u00fe",
172
+ "fpvee",
173
+ "fpven",
174
+ "fpveo",
175
+ "fpve\u00fe",
176
+ "fpvfe",
177
+ "fpvfn",
178
+ "fpvfo",
179
+ "fpvf\u00fe",
180
+ "fshee",
181
+ "fshen",
182
+ "fsheo",
183
+ "fshe\u00fe",
184
+ "fshfe",
185
+ "fshfn",
186
+ "fshfo",
187
+ "fshf\u00fe",
188
+ "fskee",
189
+ "fsken",
190
+ "fskeo",
191
+ "fske\u00fe",
192
+ "fskfe",
193
+ "fskfn",
194
+ "fskfo",
195
+ "fskf\u00fe",
196
+ "fsvee",
197
+ "fsven",
198
+ "fsveo",
199
+ "fsve\u00fe",
200
+ "fsvfe",
201
+ "fsvfn",
202
+ "fsvfo",
203
+ "fsvf\u00fe",
204
+ "ghee",
205
+ "ghen",
206
+ "gheo",
207
+ "ghe\u00fe",
208
+ "ghfe",
209
+ "ghfn",
210
+ "ghfo",
211
+ "ghf\u00fe",
212
+ "gkee",
213
+ "gken",
214
+ "gkeo",
215
+ "gke\u00fe",
216
+ "gkfe",
217
+ "gkfn",
218
+ "gkfo",
219
+ "gkf\u00fe",
220
+ "gvee",
221
+ "gven",
222
+ "gveo",
223
+ "gve\u00fe",
224
+ "gvfe",
225
+ "gvfn",
226
+ "gvfo",
227
+ "gvf\u00fe",
228
+ "ks",
229
+ "kt",
230
+ "lheeof",
231
+ "lheesf",
232
+ "lheeve",
233
+ "lheevf",
234
+ "lheevm",
235
+ "lhenof",
236
+ "lhense",
237
+ "lhensf",
238
+ "lhenve",
239
+ "lhenvf",
240
+ "lhenvm",
241
+ "lheoof",
242
+ "lheose",
243
+ "lheosf",
244
+ "lheosm",
245
+ "lheove",
246
+ "lheovf",
247
+ "lheovm",
248
+ "lhe\u00feof",
249
+ "lhe\u00fese",
250
+ "lhe\u00fesf",
251
+ "lhe\u00feve",
252
+ "lhe\u00fevf",
253
+ "lhe\u00fevm",
254
+ "lhfeof",
255
+ "lhfese",
256
+ "lhfesf",
257
+ "lhfeve",
258
+ "lhfevf",
259
+ "lhfevm",
260
+ "lhfnof",
261
+ "lhfnse",
262
+ "lhfnsf",
263
+ "lhfnve",
264
+ "lhfnvf",
265
+ "lhfnvm",
266
+ "lhfoof",
267
+ "lhfose",
268
+ "lhfosf",
269
+ "lhfove",
270
+ "lhfovf",
271
+ "lhfovm",
272
+ "lhf\u00feof",
273
+ "lhf\u00fese",
274
+ "lhf\u00fesf",
275
+ "lhf\u00feve",
276
+ "lhf\u00fevf",
277
+ "lhf\u00fevm",
278
+ "lkeeof",
279
+ "lkeesf",
280
+ "lkeeve",
281
+ "lkeevf",
282
+ "lkeevm",
283
+ "lkenof",
284
+ "lkense",
285
+ "lkensf",
286
+ "lkenve",
287
+ "lkenvf",
288
+ "lkenvm",
289
+ "lkeoof",
290
+ "lkeose",
291
+ "lkeosf",
292
+ "lkeove",
293
+ "lkeovf",
294
+ "lkeovm",
295
+ "lke\u00feof",
296
+ "lke\u00fese",
297
+ "lke\u00fesf",
298
+ "lke\u00feve",
299
+ "lke\u00fevf",
300
+ "lke\u00fevm",
301
+ "lkfeof",
302
+ "lkfese",
303
+ "lkfesf",
304
+ "lkfeve",
305
+ "lkfevf",
306
+ "lkfevm",
307
+ "lkfnof",
308
+ "lkfnse",
309
+ "lkfnsf",
310
+ "lkfnve",
311
+ "lkfnvf",
312
+ "lkfnvm",
313
+ "lkfoof",
314
+ "lkfose",
315
+ "lkfosf",
316
+ "lkfove",
317
+ "lkfovf",
318
+ "lkfovm",
319
+ "lkf\u00feof",
320
+ "lkf\u00fese",
321
+ "lkf\u00fesf",
322
+ "lkf\u00fesm",
323
+ "lkf\u00feve",
324
+ "lkf\u00fevf",
325
+ "lkf\u00fevm",
326
+ "lveeof",
327
+ "lveese",
328
+ "lveesf",
329
+ "lveeve",
330
+ "lveevf",
331
+ "lveevm",
332
+ "lvenof",
333
+ "lvense",
334
+ "lvensf",
335
+ "lvenve",
336
+ "lvenvf",
337
+ "lvenvm",
338
+ "lveoof",
339
+ "lveose",
340
+ "lveosf",
341
+ "lveove",
342
+ "lveovf",
343
+ "lveovm",
344
+ "lve\u00feof",
345
+ "lve\u00fese",
346
+ "lve\u00fesf",
347
+ "lve\u00feve",
348
+ "lve\u00fevf",
349
+ "lve\u00fevm",
350
+ "lvfeof",
351
+ "lvfese",
352
+ "lvfesf",
353
+ "lvfeve",
354
+ "lvfevf",
355
+ "lvfevm",
356
+ "lvfnof",
357
+ "lvfnse",
358
+ "lvfnsf",
359
+ "lvfnve",
360
+ "lvfnvf",
361
+ "lvfnvm",
362
+ "lvfoof",
363
+ "lvfose",
364
+ "lvfosf",
365
+ "lvfove",
366
+ "lvfovf",
367
+ "lvfovm",
368
+ "lvf\u00feof",
369
+ "lvf\u00fese",
370
+ "lvf\u00fesf",
371
+ "lvf\u00fesm",
372
+ "lvf\u00feve",
373
+ "lvf\u00fevf",
374
+ "lvf\u00fevm",
375
+ "m",
376
+ "n----s",
377
+ "n-ee",
378
+ "n-ee-s",
379
+ "n-en",
380
+ "n-en-s",
381
+ "n-eng",
382
+ "n-eo",
383
+ "n-eo-s",
384
+ "n-e\u00fe",
385
+ "n-e\u00fe-s",
386
+ "n-fn",
387
+ "nhee",
388
+ "nhee-s",
389
+ "nheeg",
390
+ "nheegs",
391
+ "nhen",
392
+ "nhen-s",
393
+ "nheng",
394
+ "nhengs",
395
+ "nheo",
396
+ "nheo-s",
397
+ "nheog",
398
+ "nheogs",
399
+ "nhe\u00fe",
400
+ "nhe\u00fe-s",
401
+ "nhe\u00feg",
402
+ "nhe\u00fegs",
403
+ "nhfe",
404
+ "nhfe-s",
405
+ "nhfeg",
406
+ "nhfegs",
407
+ "nhfn",
408
+ "nhfn-s",
409
+ "nhfng",
410
+ "nhfngs",
411
+ "nhfo",
412
+ "nhfo-s",
413
+ "nhfog",
414
+ "nhfogs",
415
+ "nhf\u00fe",
416
+ "nhf\u00fe-s",
417
+ "nhf\u00feg",
418
+ "nhf\u00fegs",
419
+ "nkee",
420
+ "nkee-s",
421
+ "nkeeg",
422
+ "nkeegs",
423
+ "nken",
424
+ "nken-s",
425
+ "nkeng",
426
+ "nkengs",
427
+ "nkeo",
428
+ "nkeo-s",
429
+ "nkeog",
430
+ "nkeogs",
431
+ "nke\u00fe",
432
+ "nke\u00fe-s",
433
+ "nke\u00feg",
434
+ "nke\u00fegs",
435
+ "nkfe",
436
+ "nkfe-s",
437
+ "nkfeg",
438
+ "nkfegs",
439
+ "nkfn",
440
+ "nkfn-s",
441
+ "nkfng",
442
+ "nkfngs",
443
+ "nkfo",
444
+ "nkfo-s",
445
+ "nkfog",
446
+ "nkfogs",
447
+ "nkf\u00fe",
448
+ "nkf\u00fe-s",
449
+ "nkf\u00feg",
450
+ "nkf\u00fegs",
451
+ "nvee",
452
+ "nvee-s",
453
+ "nveeg",
454
+ "nveegs",
455
+ "nven",
456
+ "nven-s",
457
+ "nveng",
458
+ "nvengs",
459
+ "nveo",
460
+ "nveo-s",
461
+ "nveog",
462
+ "nveogs",
463
+ "nve\u00fe",
464
+ "nve\u00fe-s",
465
+ "nve\u00feg",
466
+ "nve\u00fegs",
467
+ "nvfe",
468
+ "nvfe-s",
469
+ "nvfeg",
470
+ "nvfegs",
471
+ "nvfn",
472
+ "nvfn-s",
473
+ "nvfng",
474
+ "nvfngs",
475
+ "nvfo",
476
+ "nvfo-s",
477
+ "nvfog",
478
+ "nvfogs",
479
+ "nvf\u00fe",
480
+ "nvf\u00fe-s",
481
+ "nvf\u00feg",
482
+ "nvf\u00fegs",
483
+ "pa",
484
+ "pg",
485
+ "pk",
486
+ "pl",
487
+ "sbg2en",
488
+ "sbg2fn",
489
+ "sbm2en",
490
+ "sbm2fn",
491
+ "sfg1en",
492
+ "sfg1e\u00fe",
493
+ "sfg1fn",
494
+ "sfg1f\u00fe",
495
+ "sfg2en",
496
+ "sfg2e\u00fe",
497
+ "sfg2fn",
498
+ "sfg2f\u00fe",
499
+ "sfg3en",
500
+ "sfg3e\u00fe",
501
+ "sfg3fn",
502
+ "sfg3f\u00fe",
503
+ "sfm1en",
504
+ "sfm1e\u00fe",
505
+ "sfm1fn",
506
+ "sfm1f\u00fe",
507
+ "sfm2en",
508
+ "sfm2e\u00fe",
509
+ "sfm2fn",
510
+ "sfm2f\u00fe",
511
+ "sfm3en",
512
+ "sfm3e\u00fe",
513
+ "sfm3fn",
514
+ "sfm3f\u00fe",
515
+ "slg",
516
+ "sng",
517
+ "snm",
518
+ "svg1en",
519
+ "svg1e\u00fe",
520
+ "svg1fn",
521
+ "svg1f\u00fe",
522
+ "svg2en",
523
+ "svg2e\u00fe",
524
+ "svg2fn",
525
+ "svg2f\u00fe",
526
+ "svg3en",
527
+ "svg3e\u00fe",
528
+ "svg3fn",
529
+ "svg3f\u00fe",
530
+ "svm1en",
531
+ "svm1e\u00fe",
532
+ "svm1fn",
533
+ "svm1f\u00fe",
534
+ "svm2en",
535
+ "svm2e\u00fe",
536
+ "svm2fn",
537
+ "svm3en",
538
+ "svm3e\u00fe",
539
+ "svm3fn",
540
+ "svm3f\u00fe",
541
+ "s\u00feghen",
542
+ "s\u00fegheo",
543
+ "s\u00feghfn",
544
+ "s\u00feghfo",
545
+ "s\u00fegken",
546
+ "s\u00fegkeo",
547
+ "s\u00fegkfn",
548
+ "s\u00fegkfo",
549
+ "s\u00fegven",
550
+ "s\u00fegveo",
551
+ "s\u00fegvfn",
552
+ "s\u00fegvfo",
553
+ "s\u00fegvf\u00fe",
554
+ "s\u00femhen",
555
+ "s\u00femheo",
556
+ "s\u00femken",
557
+ "s\u00femven",
558
+ "ta",
559
+ "tfhee",
560
+ "tfhen",
561
+ "tfheo",
562
+ "tfhe\u00fe",
563
+ "tfhfe",
564
+ "tfhfn",
565
+ "tfhfo",
566
+ "tfhf\u00fe",
567
+ "tfkee",
568
+ "tfken",
569
+ "tfkeo",
570
+ "tfke\u00fe",
571
+ "tfkfe",
572
+ "tfkfn",
573
+ "tfkfo",
574
+ "tfkf\u00fe",
575
+ "tfvee",
576
+ "tfven",
577
+ "tfveo",
578
+ "tfve\u00fe",
579
+ "tfvfe",
580
+ "tfvfn",
581
+ "tfvfo",
582
+ "tfvf\u00fe",
583
+ "to",
584
+ "tp",
585
+ "v",
586
+ "x"
587
+ ],
588
+ "parser":[
589
+ "ROOT",
590
+ "acl",
591
+ "acl:relcl",
592
+ "advcl",
593
+ "advmod",
594
+ "amod",
595
+ "appos",
596
+ "aux",
597
+ "case",
598
+ "cc",
599
+ "ccomp",
600
+ "compound:prt",
601
+ "conj",
602
+ "cop",
603
+ "dep",
604
+ "det",
605
+ "fixed",
606
+ "flat:name",
607
+ "mark",
608
+ "nmod",
609
+ "nmod:poss",
610
+ "nsubj",
611
+ "nummod",
612
+ "obj",
613
+ "obl",
614
+ "obl:arg",
615
+ "parataxis",
616
+ "punct",
617
+ "xcomp"
618
+ ]
619
+ },
620
+ "pipeline":[
621
+ "transformer",
622
+ "ner",
623
+ "tagger",
624
+ "parser"
625
+ ],
626
+ "components":[
627
+ "transformer",
628
+ "ner",
629
+ "tagger",
630
+ "parser"
631
+ ],
632
+ "disabled":[
633
+
634
+ ],
635
+ "_sourced_vectors_hashes":{
636
+
637
+ },
638
+ "performance":{
639
+ "ents_f":0.9205507394,
640
+ "ents_p":0.9193318395,
641
+ "ents_r":0.9217728758,
642
+ "ents_per_type":{
643
+ "Organization":{
644
+ "p":0.9057888763,
645
+ "r":0.875,
646
+ "f":0.8901282766
647
+ },
648
+ "Location":{
649
+ "p":0.9245495495,
650
+ "r":0.9436781609,
651
+ "f":0.9340159272
652
+ },
653
+ "Miscellaneous":{
654
+ "p":0.8373860182,
655
+ "r":0.8236173393,
656
+ "f":0.8304446119
657
+ },
658
+ "Person":{
659
+ "p":0.951946472,
660
+ "r":0.9607120933,
661
+ "f":0.9563091965
662
+ },
663
+ "Date":{
664
+ "p":0.9265232975,
665
+ "r":0.9503676471,
666
+ "f":0.9382940109
667
+ },
668
+ "Money":{
669
+ "p":0.8901098901,
670
+ "r":0.9418604651,
671
+ "f":0.9152542373
672
+ },
673
+ "Time":{
674
+ "p":0.9380530973,
675
+ "r":0.954954955,
676
+ "f":0.9464285714
677
+ },
678
+ "Percent":{
679
+ "p":0.9736842105,
680
+ "r":0.9866666667,
681
+ "f":0.9801324503
682
+ }
683
+ },
684
+ "transformer_loss":2483.2597508011,
685
+ "ner_loss":1200.5906777256
686
+ },
687
+ "requirements":[
688
+ "spacy_transformers>=1.0.1,<1.1.0"
689
+ ]
690
+ }
ner/cfg ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "moves":null,
3
+ "update_with_oracle_cut_size":100,
4
+ "multitasks":[
5
+
6
+ ],
7
+ "min_action_freq":1,
8
+ "learn_tokens":false,
9
+ "beam_width":1,
10
+ "beam_density":0.0,
11
+ "beam_update_prob":0.0,
12
+ "incorrect_spans_key":null
13
+ }
ner/model ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f003ff50afc73e6063b0aba491562c8857a56b9ef9322bb4c5a22f00341dba9a
3
+ size 251051
ner/moves ADDED
@@ -0,0 +1 @@
 
1
+ ��moves� {"0":{},"1":{"Person":18626,"Organization":10396,"Miscellaneous":8297,"Location":7772,"Date":6889,"Time":1935,"Money":1835,"Percent":650},"2":{"Person":18626,"Organization":10396,"Miscellaneous":8297,"Location":7772,"Date":6889,"Time":1935,"Money":1835,"Percent":650},"3":{"Person":18626,"Organization":10396,"Miscellaneous":8297,"Location":7772,"Date":6889,"Time":1935,"Money":1835,"Percent":650},"4":{"Person":18626,"Organization":10396,"Miscellaneous":8297,"Location":7772,"Date":6889,"Time":1935,"Money":1835,"Percent":650,"":1},"5":{"":1}}�cfg��neg_key�
parser/cfg ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "moves":null,
3
+ "update_with_oracle_cut_size":100,
4
+ "multitasks":[
5
+
6
+ ],
7
+ "min_action_freq":30,
8
+ "learn_tokens":false,
9
+ "beam_width":1,
10
+ "beam_density":0.0,
11
+ "beam_update_prob":0.0,
12
+ "incorrect_spans_key":null
13
+ }
parser/model ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7034fa5d6ff0618ed8c186d494bee059f3c62399805795d62702c126855035cf
3
+ size 878055
parser/moves ADDED
@@ -0,0 +1 @@
 
1
+ ��moves��{"0":{"":7268},"1":{"":7033},"2":{"case":1647,"nsubj":1243,"mark":709,"amod":709,"cc":523,"punct":394,"advmod":390,"aux":381,"cop":348,"det":235,"nummod":218,"obl":202,"nmod":114,"advcl":53,"dep":0},"3":{"punct":1151,"nmod":766,"obj":644,"obl":638,"conj":597,"nmod:poss":595,"fixed":311,"flat:name":267,"advmod":256,"obl:arg":250,"acl:relcl":239,"xcomp":222,"nsubj":220,"appos":142,"acl":133,"advcl":132,"compound:prt":108,"ccomp":91,"parataxis":70,"nummod":36,"dep":0},"4":{"ROOT":797}}�cfg��neg_key�
tagger/cfg ADDED
@@ -0,0 +1,558 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "labels":[
3
+ "aa",
4
+ "aae",
5
+ "aam",
6
+ "af",
7
+ "afe",
8
+ "afm",
9
+ "au",
10
+ "c",
11
+ "cn",
12
+ "ct",
13
+ "e",
14
+ "fahee",
15
+ "fahen",
16
+ "faheo",
17
+ "fahe\u00fe",
18
+ "fahfe",
19
+ "fahfn",
20
+ "fahfo",
21
+ "fahf\u00fe",
22
+ "fakee",
23
+ "faken",
24
+ "fakeo",
25
+ "fake\u00fe",
26
+ "fakfe",
27
+ "fakfn",
28
+ "fakfo",
29
+ "fakf\u00fe",
30
+ "favee",
31
+ "faven",
32
+ "faveo",
33
+ "fave\u00fe",
34
+ "favfe",
35
+ "favfn",
36
+ "favfo",
37
+ "favf\u00fe",
38
+ "fbhee",
39
+ "fbhen",
40
+ "fbheo",
41
+ "fbhe\u00fe",
42
+ "fbhfe",
43
+ "fbhfn",
44
+ "fbhfo",
45
+ "fbhf\u00fe",
46
+ "fbkee",
47
+ "fbken",
48
+ "fbkeo",
49
+ "fbke\u00fe",
50
+ "fbkfe",
51
+ "fbkfn",
52
+ "fbkfo",
53
+ "fbkf\u00fe",
54
+ "fbvee",
55
+ "fbven",
56
+ "fbveo",
57
+ "fbve\u00fe",
58
+ "fbvfe",
59
+ "fbvfn",
60
+ "fbvfo",
61
+ "fbvf\u00fe",
62
+ "fehee",
63
+ "fehen",
64
+ "feheo",
65
+ "fehe\u00fe",
66
+ "fehfe",
67
+ "fehfn",
68
+ "fehfo",
69
+ "fehf\u00fe",
70
+ "fekee",
71
+ "feken",
72
+ "fekeo",
73
+ "feke\u00fe",
74
+ "fekfe",
75
+ "fekfn",
76
+ "fekfo",
77
+ "fekf\u00fe",
78
+ "fevee",
79
+ "feven",
80
+ "feveo",
81
+ "feve\u00fe",
82
+ "fevfe",
83
+ "fevfn",
84
+ "fevfo",
85
+ "fevf\u00fe",
86
+ "fohee",
87
+ "fohen",
88
+ "foheo",
89
+ "fohe\u00fe",
90
+ "fohfe",
91
+ "fohfn",
92
+ "fohfo",
93
+ "fohf\u00fe",
94
+ "fokee",
95
+ "foken",
96
+ "fokeo",
97
+ "foke\u00fe",
98
+ "fokfe",
99
+ "fokfn",
100
+ "fokfo",
101
+ "fokf\u00fe",
102
+ "fovee",
103
+ "foven",
104
+ "foveo",
105
+ "fove\u00fe",
106
+ "fovfe",
107
+ "fovfn",
108
+ "fovfo",
109
+ "fovf\u00fe",
110
+ "fp1ee",
111
+ "fp1en",
112
+ "fp1eo",
113
+ "fp1e\u00fe",
114
+ "fp1fe",
115
+ "fp1fn",
116
+ "fp1fo",
117
+ "fp1f\u00fe",
118
+ "fp2ee",
119
+ "fp2en",
120
+ "fp2eo",
121
+ "fp2e\u00fe",
122
+ "fp2fe",
123
+ "fp2fn",
124
+ "fp2fo",
125
+ "fp2f\u00fe",
126
+ "fphee",
127
+ "fphen",
128
+ "fpheo",
129
+ "fphe\u00fe",
130
+ "fphfe",
131
+ "fphfn",
132
+ "fphfo",
133
+ "fphf\u00fe",
134
+ "fpkee",
135
+ "fpken",
136
+ "fpkeo",
137
+ "fpke\u00fe",
138
+ "fpkfe",
139
+ "fpkfn",
140
+ "fpkfo",
141
+ "fpkf\u00fe",
142
+ "fpvee",
143
+ "fpven",
144
+ "fpveo",
145
+ "fpve\u00fe",
146
+ "fpvfe",
147
+ "fpvfn",
148
+ "fpvfo",
149
+ "fpvf\u00fe",
150
+ "fshee",
151
+ "fshen",
152
+ "fsheo",
153
+ "fshe\u00fe",
154
+ "fshfe",
155
+ "fshfn",
156
+ "fshfo",
157
+ "fshf\u00fe",
158
+ "fskee",
159
+ "fsken",
160
+ "fskeo",
161
+ "fske\u00fe",
162
+ "fskfe",
163
+ "fskfn",
164
+ "fskfo",
165
+ "fskf\u00fe",
166
+ "fsvee",
167
+ "fsven",
168
+ "fsveo",
169
+ "fsve\u00fe",
170
+ "fsvfe",
171
+ "fsvfn",
172
+ "fsvfo",
173
+ "fsvf\u00fe",
174
+ "ghee",
175
+ "ghen",
176
+ "gheo",
177
+ "ghe\u00fe",
178
+ "ghfe",
179
+ "ghfn",
180
+ "ghfo",
181
+ "ghf\u00fe",
182
+ "gkee",
183
+ "gken",
184
+ "gkeo",
185
+ "gke\u00fe",
186
+ "gkfe",
187
+ "gkfn",
188
+ "gkfo",
189
+ "gkf\u00fe",
190
+ "gvee",
191
+ "gven",
192
+ "gveo",
193
+ "gve\u00fe",
194
+ "gvfe",
195
+ "gvfn",
196
+ "gvfo",
197
+ "gvf\u00fe",
198
+ "ks",
199
+ "kt",
200
+ "lheeof",
201
+ "lheesf",
202
+ "lheeve",
203
+ "lheevf",
204
+ "lheevm",
205
+ "lhenof",
206
+ "lhense",
207
+ "lhensf",
208
+ "lhenve",
209
+ "lhenvf",
210
+ "lhenvm",
211
+ "lheoof",
212
+ "lheose",
213
+ "lheosf",
214
+ "lheosm",
215
+ "lheove",
216
+ "lheovf",
217
+ "lheovm",
218
+ "lhe\u00feof",
219
+ "lhe\u00fese",
220
+ "lhe\u00fesf",
221
+ "lhe\u00feve",
222
+ "lhe\u00fevf",
223
+ "lhe\u00fevm",
224
+ "lhfeof",
225
+ "lhfese",
226
+ "lhfesf",
227
+ "lhfeve",
228
+ "lhfevf",
229
+ "lhfevm",
230
+ "lhfnof",
231
+ "lhfnse",
232
+ "lhfnsf",
233
+ "lhfnve",
234
+ "lhfnvf",
235
+ "lhfnvm",
236
+ "lhfoof",
237
+ "lhfose",
238
+ "lhfosf",
239
+ "lhfove",
240
+ "lhfovf",
241
+ "lhfovm",
242
+ "lhf\u00feof",
243
+ "lhf\u00fese",
244
+ "lhf\u00fesf",
245
+ "lhf\u00feve",
246
+ "lhf\u00fevf",
247
+ "lhf\u00fevm",
248
+ "lkeeof",
249
+ "lkeesf",
250
+ "lkeeve",
251
+ "lkeevf",
252
+ "lkeevm",
253
+ "lkenof",
254
+ "lkense",
255
+ "lkensf",
256
+ "lkenve",
257
+ "lkenvf",
258
+ "lkenvm",
259
+ "lkeoof",
260
+ "lkeose",
261
+ "lkeosf",
262
+ "lkeove",
263
+ "lkeovf",
264
+ "lkeovm",
265
+ "lke\u00feof",
266
+ "lke\u00fese",
267
+ "lke\u00fesf",
268
+ "lke\u00feve",
269
+ "lke\u00fevf",
270
+ "lke\u00fevm",
271
+ "lkfeof",
272
+ "lkfese",
273
+ "lkfesf",
274
+ "lkfeve",
275
+ "lkfevf",
276
+ "lkfevm",
277
+ "lkfnof",
278
+ "lkfnse",
279
+ "lkfnsf",
280
+ "lkfnve",
281
+ "lkfnvf",
282
+ "lkfnvm",
283
+ "lkfoof",
284
+ "lkfose",
285
+ "lkfosf",
286
+ "lkfove",
287
+ "lkfovf",
288
+ "lkfovm",
289
+ "lkf\u00feof",
290
+ "lkf\u00fese",
291
+ "lkf\u00fesf",
292
+ "lkf\u00fesm",
293
+ "lkf\u00feve",
294
+ "lkf\u00fevf",
295
+ "lkf\u00fevm",
296
+ "lveeof",
297
+ "lveese",
298
+ "lveesf",
299
+ "lveeve",
300
+ "lveevf",
301
+ "lveevm",
302
+ "lvenof",
303
+ "lvense",
304
+ "lvensf",
305
+ "lvenve",
306
+ "lvenvf",
307
+ "lvenvm",
308
+ "lveoof",
309
+ "lveose",
310
+ "lveosf",
311
+ "lveove",
312
+ "lveovf",
313
+ "lveovm",
314
+ "lve\u00feof",
315
+ "lve\u00fese",
316
+ "lve\u00fesf",
317
+ "lve\u00feve",
318
+ "lve\u00fevf",
319
+ "lve\u00fevm",
320
+ "lvfeof",
321
+ "lvfese",
322
+ "lvfesf",
323
+ "lvfeve",
324
+ "lvfevf",
325
+ "lvfevm",
326
+ "lvfnof",
327
+ "lvfnse",
328
+ "lvfnsf",
329
+ "lvfnve",
330
+ "lvfnvf",
331
+ "lvfnvm",
332
+ "lvfoof",
333
+ "lvfose",
334
+ "lvfosf",
335
+ "lvfove",
336
+ "lvfovf",
337
+ "lvfovm",
338
+ "lvf\u00feof",
339
+ "lvf\u00fese",
340
+ "lvf\u00fesf",
341
+ "lvf\u00fesm",
342
+ "lvf\u00feve",
343
+ "lvf\u00fevf",
344
+ "lvf\u00fevm",
345
+ "m",
346
+ "n----s",
347
+ "n-ee",
348
+ "n-ee-s",
349
+ "n-en",
350
+ "n-en-s",
351
+ "n-eng",
352
+ "n-eo",
353
+ "n-eo-s",
354
+ "n-e\u00fe",
355
+ "n-e\u00fe-s",
356
+ "n-fn",
357
+ "nhee",
358
+ "nhee-s",
359
+ "nheeg",
360
+ "nheegs",
361
+ "nhen",
362
+ "nhen-s",
363
+ "nheng",
364
+ "nhengs",
365
+ "nheo",
366
+ "nheo-s",
367
+ "nheog",
368
+ "nheogs",
369
+ "nhe\u00fe",
370
+ "nhe\u00fe-s",
371
+ "nhe\u00feg",
372
+ "nhe\u00fegs",
373
+ "nhfe",
374
+ "nhfe-s",
375
+ "nhfeg",
376
+ "nhfegs",
377
+ "nhfn",
378
+ "nhfn-s",
379
+ "nhfng",
380
+ "nhfngs",
381
+ "nhfo",
382
+ "nhfo-s",
383
+ "nhfog",
384
+ "nhfogs",
385
+ "nhf\u00fe",
386
+ "nhf\u00fe-s",
387
+ "nhf\u00feg",
388
+ "nhf\u00fegs",
389
+ "nkee",
390
+ "nkee-s",
391
+ "nkeeg",
392
+ "nkeegs",
393
+ "nken",
394
+ "nken-s",
395
+ "nkeng",
396
+ "nkengs",
397
+ "nkeo",
398
+ "nkeo-s",
399
+ "nkeog",
400
+ "nkeogs",
401
+ "nke\u00fe",
402
+ "nke\u00fe-s",
403
+ "nke\u00feg",
404
+ "nke\u00fegs",
405
+ "nkfe",
406
+ "nkfe-s",
407
+ "nkfeg",
408
+ "nkfegs",
409
+ "nkfn",
410
+ "nkfn-s",
411
+ "nkfng",
412
+ "nkfngs",
413
+ "nkfo",
414
+ "nkfo-s",
415
+ "nkfog",
416
+ "nkfogs",
417
+ "nkf\u00fe",
418
+ "nkf\u00fe-s",
419
+ "nkf\u00feg",
420
+ "nkf\u00fegs",
421
+ "nvee",
422
+ "nvee-s",
423
+ "nveeg",
424
+ "nveegs",
425
+ "nven",
426
+ "nven-s",
427
+ "nveng",
428
+ "nvengs",
429
+ "nveo",
430
+ "nveo-s",
431
+ "nveog",
432
+ "nveogs",
433
+ "nve\u00fe",
434
+ "nve\u00fe-s",
435
+ "nve\u00feg",
436
+ "nve\u00fegs",
437
+ "nvfe",
438
+ "nvfe-s",
439
+ "nvfeg",
440
+ "nvfegs",
441
+ "nvfn",
442
+ "nvfn-s",
443
+ "nvfng",
444
+ "nvfngs",
445
+ "nvfo",
446
+ "nvfo-s",
447
+ "nvfog",
448
+ "nvfogs",
449
+ "nvf\u00fe",
450
+ "nvf\u00fe-s",
451
+ "nvf\u00feg",
452
+ "nvf\u00fegs",
453
+ "pa",
454
+ "pg",
455
+ "pk",
456
+ "pl",
457
+ "sbg2en",
458
+ "sbg2fn",
459
+ "sbm2en",
460
+ "sbm2fn",
461
+ "sfg1en",
462
+ "sfg1e\u00fe",
463
+ "sfg1fn",
464
+ "sfg1f\u00fe",
465
+ "sfg2en",
466
+ "sfg2e\u00fe",
467
+ "sfg2fn",
468
+ "sfg2f\u00fe",
469
+ "sfg3en",
470
+ "sfg3e\u00fe",
471
+ "sfg3fn",
472
+ "sfg3f\u00fe",
473
+ "sfm1en",
474
+ "sfm1e\u00fe",
475
+ "sfm1fn",
476
+ "sfm1f\u00fe",
477
+ "sfm2en",
478
+ "sfm2e\u00fe",
479
+ "sfm2fn",
480
+ "sfm2f\u00fe",
481
+ "sfm3en",
482
+ "sfm3e\u00fe",
483
+ "sfm3fn",
484
+ "sfm3f\u00fe",
485
+ "slg",
486
+ "sng",
487
+ "snm",
488
+ "svg1en",
489
+ "svg1e\u00fe",
490
+ "svg1fn",
491
+ "svg1f\u00fe",
492
+ "svg2en",
493
+ "svg2e\u00fe",
494
+ "svg2fn",
495
+ "svg2f\u00fe",
496
+ "svg3en",
497
+ "svg3e\u00fe",
498
+ "svg3fn",
499
+ "svg3f\u00fe",
500
+ "svm1en",
501
+ "svm1e\u00fe",
502
+ "svm1fn",
503
+ "svm1f\u00fe",
504
+ "svm2en",
505
+ "svm2e\u00fe",
506
+ "svm2fn",
507
+ "svm3en",
508
+ "svm3e\u00fe",
509
+ "svm3fn",
510
+ "svm3f\u00fe",
511
+ "s\u00feghen",
512
+ "s\u00fegheo",
513
+ "s\u00feghfn",
514
+ "s\u00feghfo",
515
+ "s\u00fegken",
516
+ "s\u00fegkeo",
517
+ "s\u00fegkfn",
518
+ "s\u00fegkfo",
519
+ "s\u00fegven",
520
+ "s\u00fegveo",
521
+ "s\u00fegvfn",
522
+ "s\u00fegvfo",
523
+ "s\u00fegvf\u00fe",
524
+ "s\u00femhen",
525
+ "s\u00femheo",
526
+ "s\u00femken",
527
+ "s\u00femven",
528
+ "ta",
529
+ "tfhee",
530
+ "tfhen",
531
+ "tfheo",
532
+ "tfhe\u00fe",
533
+ "tfhfe",
534
+ "tfhfn",
535
+ "tfhfo",
536
+ "tfhf\u00fe",
537
+ "tfkee",
538
+ "tfken",
539
+ "tfkeo",
540
+ "tfke\u00fe",
541
+ "tfkfe",
542
+ "tfkfn",
543
+ "tfkfo",
544
+ "tfkf\u00fe",
545
+ "tfvee",
546
+ "tfven",
547
+ "tfveo",
548
+ "tfve\u00fe",
549
+ "tfvfe",
550
+ "tfvfn",
551
+ "tfvfo",
552
+ "tfvf\u00fe",
553
+ "to",
554
+ "tp",
555
+ "v",
556
+ "x"
557
+ ]
558
+ }
tagger/model ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bab2b588c80aae9926182c1d8aa3e156e22a6af1395108cc5c9e58e7442aa1e1
3
+ size 10201974
tokenizer ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ ��prefix_search� ~^§|^%|^=|^—|^–|^\+(?![0-9])|^…|^……|^,|^:|^;|^\!|^\?|^¿|^؟|^¡|^\(|^\)|^\[|^\]|^\{|^\}|^<|^>|^_|^#|^\*|^&|^。|^?|^!|^,|^、|^;|^:|^~|^·|^।|^،|^۔|^؛|^٪|^\.\.+|^…|^\'|^"|^”|^“|^`|^‘|^´|^’|^‚|^,|^„|^»|^«|^「|^」|^『|^』|^(|^)|^〔|^〕|^【|^】|^《|^》|^〈|^〉|^\$|^£|^€|^¥|^฿|^US\$|^C\$|^A\$|^₽|^﷼|^₴|^₠|^₡|^₢|^₣|^₤|^₥|^₦|^₧|^₨|^₩|^₪|^₫|^€|^₭|^₮|^₯|^₰|^₱|^₲|^₳|^₴|^₵|^₶|^₷|^₸|^₹|^₺|^₻|^₼|^₽|^₾|^₿|^[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]�suffix_search�2"…$|……$|,$|:$|;$|\!$|\?$|¿$|؟$|¡$|\($|\)$|\[$|\]$|\{$|\}$|<$|>$|_$|#$|\*$|&$|。$|?$|!$|,$|、$|;$|:$|~$|·$|।$|،$|۔$|؛$|٪$|\.\.+$|…$|\'$|"$|”$|“$|`$|‘$|´$|’$|‚$|,$|„$|»$|«$|「$|」$|『$|』$|($|)$|〔$|〕$|【$|】$|《$|》$|〈$|〉$|[\u00A6\u00A9\u00AE\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]$|'s$|'S$|’s$|’S$|—$|–$|(?<=[0-9])\+$|(?<=°[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\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F%²\-\+…|……|,|:|;|\!|\?|¿|؟|¡|\(|\)|\[|\]|\{|\}|<|>|_|#|\*|&|。|?|!|,|、|;|:|~|·|।|،|۔|؛|٪(?:\'"”“`‘´’‚,„»«「」『』()〔〕【】《》〈〉)])\.$|(?<=[A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F][A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])\.$�infix_finditer�=�\.\.+|…|[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]|(?<=[0-9])[+\-\*^](?=[0-9-])|(?<=[a-z\uFF41-\uFF5A\u00DF-\u00F6\u00F8-\u00FF\u0101\u0103\u0105\u0107\u0109\u010B\u010D\u010F\u0111\u0113\u0115\u0117\u0119\u011B\u011D\u011F\u0121\u0123\u0125\u0127\u0129\u012B\u012D\u012F\u0131\u0133\u0135\u0137\u0138\u013A\u013C\u013E\u0140\u0142\u0144\u0146\u0148\u0149\u014B\u014D\u014F\u0151\u0153\u0155\u0157\u0159\u015B\u015D\u015F\u0161\u0163\u0165\u0167\u0169\u016B\u016D\u016F\u0171\u0173\u0175\u0177\u017A\u017C\u017E\u017F\u0180\u0183\u0185\u0188\u018C\u018D\u0192\u0195\u0199-\u019B\u019E\u01A1\u01A3\u01A5\u01A8\u01AA\u01AB\u01AD\u01B0\u01B4\u01B6\u01B9\u01BA\u01BD-\u01BF\u01C6\u01C9\u01CC\u01CE\u01D0\u01D2\u01D4\u01D6\u01D8\u01DA\u01DC\u01DD\u01DF\u01E1\u01E3\u01E5\u01E7\u01E9\u01EB\u01ED\u01EF\u01F0\u01F3\u01F5\u01F9\u01FB\u01FD\u01FF\u0201\u0203\u0205\u0207\u0209\u020B\u020D\u020F\u0211\u0213\u0215\u0217\u0219\u021B\u021D\u021F\u0221\u0223\u0225\u0227\u0229\u022B\u022D\u022F\u0231\u0233-\u0239\u023C\u023F\u0240\u0242\u0247\u0249\u024B\u024D\u024F\u2C61\u2C65\u2C66\u2C68\u2C6A\u2C6C\u2C71\u2C73\u2C74\u2C76-\u2C7B\uA723\uA725\uA727\uA729\uA72B\uA72D\uA72F-\uA731\uA733\uA735\uA737\uA739\uA73B\uA73D\uA73F\uA741\uA743\uA745\uA747\uA749\uA74B\uA74D\uA74F\uA751\uA753\uA755\uA757\uA759\uA75B\uA75D\uA75F\uA761\uA763\uA765\uA767\uA769\uA76B\uA76D\uA76F\uA771-\uA778\uA77A\uA77C\uA77F\uA781\uA783\uA785\uA787\uA78C\uA78E\uA791\uA793-\uA795\uA797\uA799\uA79B\uA79D\uA79F\uA7A1\uA7A3\uA7A5\uA7A7\uA7A9\uA7AF\uA7B5\uA7B7\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E01\u1E03\u1E05\u1E07\u1E09\u1E0B\u1E0D\u1E0F\u1E11\u1E13\u1E15\u1E17\u1E19\u1E1B\u1E1D\u1E1F\u1E21\u1E23\u1E25\u1E27\u1E29\u1E2B\u1E2D\u1E2F\u1E31\u1E33\u1E35\u1E37\u1E39\u1E3B\u1E3D\u1E3F\u1E41\u1E43\u1E45\u1E47\u1E49\u1E4B\u1E4D\u1E4F\u1E51\u1E53\u1E55\u1E57\u1E59\u1E5B\u1E5D\u1E5F\u1E61\u1E63\u1E65\u1E67\u1E69\u1E6B\u1E6D\u1E6F\u1E71\u1E73\u1E75\u1E77\u1E79\u1E7B\u1E7D\u1E7F\u1E81\u1E83\u1E85\u1E87\u1E89\u1E8B\u1E8D\u1E8F\u1E91\u1E93\u1E95-\u1E9D\u1E9F\u1EA1\u1EA3\u1EA5\u1EA7\u1EA9\u1EAB\u1EAD\u1EAF\u1EB1\u1EB3\u1EB5\u1EB7\u1EB9\u1EBB\u1EBD\u1EBF\u1EC1\u1EC3\u1EC5\u1EC7\u1EC9\u1ECB\u1ECD\u1ECF\u1ED1\u1ED3\u1ED5\u1ED7\u1ED9\u1EDB\u1EDD\u1EDF\u1EE1\u1EE3\u1EE5\u1EE7\u1EE9\u1EEB\u1EED\u1EEF\u1EF1\u1EF3\u1EF5\u1EF7\u1EF9\u1EFB\u1EFD\u1EFFёа-яәөүҗңһα-ωάέίόώήύа-щюяіїєґѓѕјљњќѐѝ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F\'"”“`‘´’‚,„»«「」『』()〔〕【】《》〈〉])\.(?=[A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F\'"”“`‘´’‚,„»«「」『』()〔〕【】《》〈〉])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F]),(?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])(?:-|–|—|--|---|——|~)(?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F0-9])[:<>=/](?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])�token_match��url_match�
2
+ ��A�
3
+ � ��A� �'��A�'�''��A�''�(*_*)��A�(*_*)�(-8��A�(-8�(-:��A�(-:�(-;��A�(-;�(-_-)��A�(-_-)�(._.)��A�(._.)�(:��A�(:�(;��A�(;�(=��A�(=�(>_<)��A�(>_<)�(^_^)��A�(^_^)�(o:��A�(o:�(¬_¬)��A�(¬_¬)�(ಠ_ಠ)��A�(ಠ_ಠ)�(╯°□°)╯︵┻━┻��A�(╯°□°)╯︵┻━┻�)-:��A�)-:�):��A�):�-_-��A�-_-�-__-��A�-__-�._.��A�._.�0.0��A�0.0�0.o��A�0.o�0_0��A�0_0�0_o��A�0_o�8)��A�8)�8-)��A�8-)�8-D��A�8-D�8D��A�8D�:'(��A�:'(�:')��A�:')�:'-(��A�:'-(�:'-)��A�:'-)�:(��A�:(�:((��A�:((�:(((��A�:(((�:()��A�:()�:)��A�:)�:))��A�:))�:)))��A�:)))�:*��A�:*�:-(��A�:-(�:-((��A�:-((�:-(((��A�:-(((�:-)��A�:-)�:-))��A�:-))�:-)))��A�:-)))�:-*��A�:-*�:-/��A�:-/�:-0��A�:-0�:-3��A�:-3�:->��A�:->�:-D��A�:-D�:-O��A�:-O�:-P��A�:-P�:-X��A�:-X�:-]��A�:-]�:-o��A�:-o�:-p��A�:-p�:-x��A�:-x�:-|��A�:-|�:-}��A�:-}�:/��A�:/�:0��A�:0�:1��A�:1�:3��A�:3�:>��A�:>�:D��A�:D�:O��A�:O�:P��A�:P�:X��A�:X�:]��A�:]�:o��A�:o�:o)��A�:o)�:p��A�:p�:x��A�:x�:|��A�:|�:}��A�:}�;)��A�;)�;-)��A�;-)�;-D��A�;-D�;D��A�;D�;_;��A�;_;�<.<��A�<.<�</3��A�</3�<3��A�<3�<33��A�<33�<333��A�<333�<space>��A�<space>�=(��A�=(�=)��A�=)�=/��A�=/�=3��A�=3�=D��A�=D�=[��A�=[�=]��A�=]�=|��A�=|�>.<��A�>.<�>.>��A�>.>�>:(��A�>:(�>:o��A�>:o�><(((*>��A�><(((*>�@_@��A�@_@�C++��A�C++�O.O��A�O.O�O.o��A�O.o�O_O��A�O_O�O_o��A�O_o�V.V��A�V.V�V_V��A�V_V�XD��A�XD�XDD��A�XDD�[-:��A�[-:�[:��A�[:�[=��A�[=�\")��A�\")�\n��A�\n�\t��A�\t�]=��A�]=�^_^��A�^_^�^__^��A�^__^�^___^��A�^___^�a.��A�a.�b.��A�b.�c.��A�c.�d.��A�d.�e.��A�e.�f.��A�f.�g.��A�g.�h.��A�h.�i.��A�i.�j.��A�j.�k.��A�k.�l.��A�l.�m.��A�m.�n.��A�n.�o.��A�o.�o.0��A�o.0�o.O��A�o.O�o.o��A�o.o�o_0��A�o_0�o_O��A�o_O�o_o��A�o_o�p.��A�p.�q.��A�q.�r.��A�r.�s.��A�s.�t.��A�t.�u.��A�u.�v.��A�v.�v.v��A�v.v�v_v��A�v_v�w.��A�w.�x.��A�x.�xD��A�xD�xDD��A�xDD�y.��A�y.�z.��A�z.� ��A� C� �¯\(ツ)/¯��A�¯\(ツ)/¯�ä.��A�ä.�ö.��A�ö.�ü.��A�ü.�ಠ_ಠ��A�ಠ_ಠ�ಠ︵ಠ��A�ಠ︵ಠ�—��A�—
transformer/cfg ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ {
2
+ "max_batch_items":4096
3
+ }
transformer/model/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/home/elias/anaconda3/lib/python3.8/site-packages/is_ner_mim_trf/is_ner_mim_trf-0.0.1/transformer/model",
3
+ "architectures": [
4
+ "RobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "transformers_version": "4.5.1",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 50000
26
+ }
transformer/model/merges.txt ADDED
The diff for this file is too large to render. See raw diff
transformer/model/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1ececdf5436dd035467056767e2669d483cc8ad93456d217e20b9b18211b077
3
+ size 497847089
transformer/model/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
transformer/model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
transformer/model/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "special_tokens_map_file": "/home/elias/.cache/huggingface/transformers/b21a20c1d1a8c4ce0f3f9b2a311ea6fa001eaaaee064c36040b1c5885cdc73f0.cb2244924ab24d706b02fd7fcedaea4531566537687a539ebb94db511fd122a0", "name_or_path": "/home/elias/anaconda3/lib/python3.8/site-packages/is_ner_mim_trf/is_ner_mim_trf-0.0.1/transformer/model"}
transformer/model/vocab.json ADDED
The diff for this file is too large to render. See raw diff
vocab/key2row ADDED
@@ -0,0 +1 @@
 
1
+
vocab/lookups.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
3
+ size 1
vocab/strings.json ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7210df54290791ef49831b80a77e46de3d9d622a0216b57d1038360ef148f7a4
3
+ size 9734062
vocab/vectors ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14772b683e726436d5948ad3fff2b43d036ef2ebbe3458aafed6004e05a40706
3
+ size 128