ljvmiranda921 commited on
Commit
bc4f3b2
1 Parent(s): e9546e4

(calamanCy 0.1.0): Update spaCy pipeline

Browse files
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ ner/model filter=lfs diff=lfs merge=lfs -text
37
+ tl_calamancy_trf-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
38
+ transformer/model filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - spacy
4
+ - token-classification
5
+ language:
6
+ - tl
7
+ license: cc-by-sa-3.0
8
+ ---
9
+ calamanCy: Tagalog NLP pipelines in spaCy
10
+
11
+ | Feature | Description |
12
+ | --- | --- |
13
+ | **Name** | `tl_calamancy_trf` |
14
+ | **Version** | `0.1.0` |
15
+ | **spaCy** | `>=3.5.0` |
16
+ | **Default Pipeline** | `transformer`, `tagger`, `morphologizer`, `parser`, `ner` |
17
+ | **Components** | `transformer`, `tagger`, `morphologizer`, `parser`, `ner` |
18
+ | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
19
+ | **Sources** | [TLUnified dataset](https://aclanthology.org/2022.lrec-1.703/) (Jan Christian Blaise Cruz and Charibeth Cheng)<br />[UD_Tagalog-TRG](https://universaldependencies.org/treebanks/tl_trg/index.html) (Stephanie Samson, Daniel Zeman, and Mary Ann C. Tan)<br />[UD_Tagalog-Ugnayan](https://universaldependencies.org/treebanks/tl_ugnayan/index.html) (Angelina Aquino) |
20
+ | **License** | `CC BY-SA 3.0` |
21
+ | **Author** | [Lester James V. Miranda](https://github.com/ljvmiranda921/calamanCy) |
22
+
23
+ ### Label Scheme
24
+
25
+ <details>
26
+
27
+ <summary>View label scheme (120 labels for 4 components)</summary>
28
+
29
+ | Component | Labels |
30
+ | --- | --- |
31
+ | **`tagger`** | `ADJ`, `ADJ_PART`, `ADP`, `ADV`, `ADV_PART`, `AUX`, `CCONJ`, `DET`, `DET_ADP`, `DET_PART`, `INTJ`, `NOUN`, `NOUN_PART`, `NUM`, `NUM_PART`, `PART`, `PRON`, `PRON_PART`, `PROPN`, `PUNCT`, `SCONJ`, `VERB`, `VERB_PART` |
32
+ | **`morphologizer`** | `Aspect=Perf\|Mood=Ind\|POS=VERB\|Voice=Act`, `Case=Nom\|POS=ADP`, `POS=NOUN`, `POS=PUNCT`, `Aspect=Perf\|Mood=Ind\|POS=VERB\|Voice=Pass`, `Case=Gen\|POS=ADP`, `Case=Gen\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Aspect=Imp\|Mood=Ind\|POS=VERB\|Voice=Act`, `POS=ADV\|PronType=Dem`, `Foreign=Yes\|POS=NOUN`, `Degree=Pos\|POS=ADJ`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Nom\|Deixis=Med\|Number=Sing\|POS=PRON\|PronType=Dem`, `Gender=Masc\|POS=PROPN`, `Case=Gen\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Degree=Pos\|Link=Yes\|POS=ADJ`, `POS=ADP`, `Case=Dat\|POS=ADP`, `POS=VERB\|Polarity=Pos`, `Aspect=Hab\|POS=VERB`, `POS=SCONJ`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Aspect=Prosp\|Mood=Ind\|POS=VERB\|Voice=Act`, `POS=ADV`, `POS=PART\|Polarity=Neg`, `Aspect=Imp\|Mood=Ind\|POS=VERB\|Voice=Pass`, `Aspect=Perf\|Mood=Ind\|POS=VERB\|Voice=Lfoc`, `POS=PROPN`, `Case=Nom\|Deixis=Prox\|Number=Sing\|POS=PRON\|PronType=Dem`, `Gender=Masc\|POS=NOUN`, `Gender=Fem\|POS=NOUN`, `Degree=Pos\|Gender=Fem\|POS=ADJ`, `Gender=Fem\|POS=PROPN`, `Case=Nom\|Clusivity=In\|Number=Dual\|POS=PRON\|Person=1\|PronType=Prs`, `Number=Plur\|POS=DET\|PronType=Ind`, `Case=Nom\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `POS=PRON\|PronType=Prs\|Reflex=Yes`, `Gender=Masc\|POS=DET\|PronType=Emp`, `Case=Nom\|POS=PRON\|PronType=Int`, `Link=Yes\|POS=NOUN`, `POS=PART\|PartType=Int`, `POS=INTJ\|Polarity=Pos`, `Link=Yes\|POS=PART\|PartType=Int`, `POS=VERB\|Polarity=Neg`, `Degree=Pos\|POS=ADJ\|PronType=Int`, `Case=Gen\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `Aspect=Perf\|Mood=Ind\|POS=VERB\|PronType=Int\|Voice=Act`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Aspect=Perf\|Mood=Ind\|POS=VERB\|PronType=Int\|Voice=Pass`, `Aspect=Perf\|Mood=Ind\|POS=VERB\|Voice=Ifoc`, `POS=ADV\|PronType=Int`, `Aspect=Prog\|Mood=Ind\|POS=VERB\|Voice=Act`, `POS=PART\|PartType=Nfh`, `Deixis=Remt\|POS=ADV\|PronType=Dem`, `Aspect=Imp\|Mood=Pot\|POS=VERB\|Voice=Act`, `Link=Yes\|POS=VERB\|Polarity=Pos`, `Link=Yes\|POS=VERB\|Polarity=Neg`, `POS=PART\|PartType=Des`, `Mood=Imp\|POS=AUX\|Polarity=Neg`, `Case=Nom\|Link=Yes\|Number=Plur\|POS=PRON\|Person=2\|PronType=Prs`, `Case=Nom\|Link=Yes\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Aspect=Prog\|Mood=Ind\|POS=VERB\|Voice=Pass`, `Aspect=Prog\|Mood=Ind\|POS=VERB\|Voice=Lfoc`, `Aspect=Prog\|Mood=Ind\|POS=VERB\|Voice=Bfoc`, `POS=DET\|PronType=Tot`, `Case=Dat\|Link=Yes\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Link=Yes\|POS=PRON\|PronType=Prs\|Reflex=Yes`, `Mood=Imp\|POS=VERB\|Voice=Act`, `Case=Dat\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Mood=Imp\|POS=VERB\|Voice=Lfoc`, `Case=Gen\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Mood=Imp\|POS=VERB\|Voice=Pass`, `Case=Gen\|Clusivity=In\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `Aspect=Hab\|POS=VERB\|Voice=Pass`, `Gender=Masc\|Link=Yes\|POS=PROPN`, `Case=Gen\|Link=Yes\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Gen\|Link=Yes\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `POS=ADJ`, `POS=PART`, `POS=PRON`, `POS=VERB`, `POS=INTJ`, `POS=CCONJ`, `POS=NUM`, `POS=DET` |
33
+ | **`parser`** | `ROOT`, `advmod`, `case`, `dep`, `nmod`, `nsubj`, `obj`, `obl`, `punct` |
34
+ | **`ner`** | `LOC`, `ORG`, `PER` |
35
+
36
+ </details>
config.cfg ADDED
@@ -0,0 +1,229 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [paths]
2
+ parser_model = "training/parser_tagger_trf/model-best"
3
+ ner_model = "training/ner_trf/model-best"
4
+ train = null
5
+ dev = null
6
+ vectors = null
7
+ init_tok2vec = null
8
+
9
+ [system]
10
+ seed = 0
11
+ gpu_allocator = null
12
+
13
+ [nlp]
14
+ lang = "tl"
15
+ pipeline = ["transformer","tagger","morphologizer","parser","ner"]
16
+ tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
17
+ disabled = []
18
+ before_creation = null
19
+ after_creation = null
20
+ after_pipeline_creation = null
21
+ batch_size = 1000
22
+
23
+ [components]
24
+
25
+ [components.morphologizer]
26
+ factory = "morphologizer"
27
+ extend = false
28
+ overwrite = true
29
+ scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
30
+
31
+ [components.morphologizer.model]
32
+ @architectures = "spacy.Tagger.v2"
33
+ nO = null
34
+ normalize = false
35
+
36
+ [components.morphologizer.model.tok2vec]
37
+ @architectures = "spacy-transformers.TransformerListener.v1"
38
+ grad_factor = 1.0
39
+ pooling = {"@layers":"reduce_mean.v1"}
40
+ upstream = "*"
41
+
42
+ [components.ner]
43
+ factory = "ner"
44
+ incorrect_spans_key = null
45
+ moves = null
46
+ scorer = {"@scorers":"spacy.ner_scorer.v1"}
47
+ update_with_oracle_cut_size = 100
48
+
49
+ [components.ner.model]
50
+ @architectures = "spacy.TransitionBasedParser.v2"
51
+ state_type = "ner"
52
+ extra_state_tokens = false
53
+ hidden_width = 64
54
+ maxout_pieces = 2
55
+ use_upper = false
56
+ nO = null
57
+
58
+ [components.ner.model.tok2vec]
59
+ @architectures = "spacy-transformers.Tok2VecTransformer.v3"
60
+ name = "jcblaise/roberta-tagalog-base"
61
+ mixed_precision = false
62
+ pooling = {"@layers":"reduce_mean.v1"}
63
+ grad_factor = 1.0
64
+
65
+ [components.ner.model.tok2vec.get_spans]
66
+ @span_getters = "spacy-transformers.strided_spans.v1"
67
+ window = 128
68
+ stride = 96
69
+
70
+ [components.ner.model.tok2vec.grad_scaler_config]
71
+
72
+ [components.ner.model.tok2vec.tokenizer_config]
73
+ use_fast = true
74
+
75
+ [components.ner.model.tok2vec.transformer_config]
76
+
77
+ [components.parser]
78
+ factory = "parser"
79
+ learn_tokens = false
80
+ min_action_freq = 30
81
+ moves = null
82
+ scorer = {"@scorers":"spacy.parser_scorer.v1"}
83
+ update_with_oracle_cut_size = 100
84
+
85
+ [components.parser.model]
86
+ @architectures = "spacy.TransitionBasedParser.v2"
87
+ state_type = "parser"
88
+ extra_state_tokens = false
89
+ hidden_width = 128
90
+ maxout_pieces = 3
91
+ use_upper = false
92
+ nO = null
93
+
94
+ [components.parser.model.tok2vec]
95
+ @architectures = "spacy-transformers.TransformerListener.v1"
96
+ grad_factor = 1.0
97
+ pooling = {"@layers":"reduce_mean.v1"}
98
+ upstream = "*"
99
+
100
+ [components.tagger]
101
+ factory = "tagger"
102
+ neg_prefix = "!"
103
+ overwrite = false
104
+ scorer = {"@scorers":"spacy.tagger_scorer.v1"}
105
+
106
+ [components.tagger.model]
107
+ @architectures = "spacy.Tagger.v2"
108
+ nO = null
109
+ normalize = false
110
+
111
+ [components.tagger.model.tok2vec]
112
+ @architectures = "spacy-transformers.TransformerListener.v1"
113
+ grad_factor = 1.0
114
+ pooling = {"@layers":"reduce_mean.v1"}
115
+ upstream = "*"
116
+
117
+ [components.transformer]
118
+ factory = "transformer"
119
+ max_batch_items = 4096
120
+ set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
121
+
122
+ [components.transformer.model]
123
+ @architectures = "spacy-transformers.TransformerModel.v3"
124
+ name = "jcblaise/roberta-tagalog-base"
125
+ mixed_precision = false
126
+
127
+ [components.transformer.model.get_spans]
128
+ @span_getters = "spacy-transformers.strided_spans.v1"
129
+ window = 128
130
+ stride = 96
131
+
132
+ [components.transformer.model.grad_scaler_config]
133
+
134
+ [components.transformer.model.tokenizer_config]
135
+ use_fast = true
136
+
137
+ [components.transformer.model.transformer_config]
138
+
139
+ [corpora]
140
+
141
+ [corpora.dev]
142
+ @readers = "spacy.Corpus.v1"
143
+ path = ${paths.dev}
144
+ gold_preproc = false
145
+ max_length = 0
146
+ limit = 0
147
+ augmenter = null
148
+
149
+ [corpora.train]
150
+ @readers = "spacy.Corpus.v1"
151
+ path = ${paths.train}
152
+ gold_preproc = false
153
+ max_length = 0
154
+ limit = 0
155
+ augmenter = null
156
+
157
+ [training]
158
+ seed = ${system.seed}
159
+ gpu_allocator = ${system.gpu_allocator}
160
+ dropout = 0.1
161
+ accumulate_gradient = 1
162
+ patience = 1600
163
+ max_epochs = 0
164
+ max_steps = 20000
165
+ eval_frequency = 200
166
+ frozen_components = []
167
+ annotating_components = []
168
+ dev_corpus = "corpora.dev"
169
+ train_corpus = "corpora.train"
170
+ before_to_disk = null
171
+ before_update = null
172
+
173
+ [training.batcher]
174
+ @batchers = "spacy.batch_by_words.v1"
175
+ discard_oversize = false
176
+ tolerance = 0.2
177
+ get_length = null
178
+
179
+ [training.batcher.size]
180
+ @schedules = "compounding.v1"
181
+ start = 100
182
+ stop = 1000
183
+ compound = 1.001
184
+ t = 0.0
185
+
186
+ [training.logger]
187
+ @loggers = "spacy.ConsoleLogger.v1"
188
+ progress_bar = false
189
+
190
+ [training.optimizer]
191
+ @optimizers = "Adam.v1"
192
+ beta1 = 0.9
193
+ beta2 = 0.999
194
+ L2_is_weight_decay = true
195
+ L2 = 0.01
196
+ grad_clip = 1.0
197
+ use_averages = false
198
+ eps = 0.00000001
199
+ learn_rate = 0.001
200
+
201
+ [training.score_weights]
202
+ tag_acc = 0.26
203
+ pos_acc = 0.12
204
+ morph_acc = 0.12
205
+ morph_per_feat = null
206
+ dep_uas = 0.12
207
+ dep_las = 0.12
208
+ dep_las_per_type = null
209
+ sents_p = null
210
+ sents_r = null
211
+ sents_f = 0.0
212
+ ents_f = 0.26
213
+ ents_p = 0.0
214
+ ents_r = 0.0
215
+ ents_per_type = null
216
+
217
+ [pretraining]
218
+
219
+ [initialize]
220
+ vectors = ${paths.vectors}
221
+ init_tok2vec = ${paths.init_tok2vec}
222
+ vocab_data = null
223
+ lookups = null
224
+ before_init = null
225
+ after_init = null
226
+
227
+ [initialize.components]
228
+
229
+ [initialize.tokenizer]
meta.json ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "lang":"tl",
3
+ "name":"calamancy_trf",
4
+ "version":"0.1.0",
5
+ "description":"calamanCy: Tagalog NLP pipelines in spaCy",
6
+ "author":"Lester James V. Miranda",
7
+ "email":"ljvmiranda@gmail.com",
8
+ "url":"https://github.com/ljvmiranda921/calamanCy",
9
+ "license":"CC BY-SA 3.0",
10
+ "spacy_version":">=3.5.0",
11
+ "spacy_git_version":"Unknown",
12
+ "vectors":{
13
+ "width":0,
14
+ "vectors":0,
15
+ "keys":0,
16
+ "name":null
17
+ },
18
+ "labels":{
19
+ "transformer":[
20
+
21
+ ],
22
+ "tagger":[
23
+ "ADJ",
24
+ "ADJ_PART",
25
+ "ADP",
26
+ "ADV",
27
+ "ADV_PART",
28
+ "AUX",
29
+ "CCONJ",
30
+ "DET",
31
+ "DET_ADP",
32
+ "DET_PART",
33
+ "INTJ",
34
+ "NOUN",
35
+ "NOUN_PART",
36
+ "NUM",
37
+ "NUM_PART",
38
+ "PART",
39
+ "PRON",
40
+ "PRON_PART",
41
+ "PROPN",
42
+ "PUNCT",
43
+ "SCONJ",
44
+ "VERB",
45
+ "VERB_PART"
46
+ ],
47
+ "morphologizer":[
48
+ "Aspect=Perf|Mood=Ind|POS=VERB|Voice=Act",
49
+ "Case=Nom|POS=ADP",
50
+ "POS=NOUN",
51
+ "POS=PUNCT",
52
+ "Aspect=Perf|Mood=Ind|POS=VERB|Voice=Pass",
53
+ "Case=Gen|POS=ADP",
54
+ "Case=Gen|Number=Sing|POS=PRON|Person=1|PronType=Prs",
55
+ "Aspect=Imp|Mood=Ind|POS=VERB|Voice=Act",
56
+ "POS=ADV|PronType=Dem",
57
+ "Foreign=Yes|POS=NOUN",
58
+ "Degree=Pos|POS=ADJ",
59
+ "Case=Nom|Number=Sing|POS=PRON|Person=3|PronType=Prs",
60
+ "Case=Nom|Deixis=Med|Number=Sing|POS=PRON|PronType=Dem",
61
+ "Gender=Masc|POS=PROPN",
62
+ "Case=Gen|Number=Sing|POS=PRON|Person=3|PronType=Prs",
63
+ "Degree=Pos|Link=Yes|POS=ADJ",
64
+ "POS=ADP",
65
+ "Case=Dat|POS=ADP",
66
+ "POS=VERB|Polarity=Pos",
67
+ "Aspect=Hab|POS=VERB",
68
+ "POS=SCONJ",
69
+ "Case=Nom|Number=Sing|POS=PRON|Person=1|PronType=Prs",
70
+ "Aspect=Prosp|Mood=Ind|POS=VERB|Voice=Act",
71
+ "POS=ADV",
72
+ "POS=PART|Polarity=Neg",
73
+ "Aspect=Imp|Mood=Ind|POS=VERB|Voice=Pass",
74
+ "Aspect=Perf|Mood=Ind|POS=VERB|Voice=Lfoc",
75
+ "POS=PROPN",
76
+ "Case=Nom|Deixis=Prox|Number=Sing|POS=PRON|PronType=Dem",
77
+ "Gender=Masc|POS=NOUN",
78
+ "Gender=Fem|POS=NOUN",
79
+ "Degree=Pos|Gender=Fem|POS=ADJ",
80
+ "Gender=Fem|POS=PROPN",
81
+ "Case=Nom|Clusivity=In|Number=Dual|POS=PRON|Person=1|PronType=Prs",
82
+ "Number=Plur|POS=DET|PronType=Ind",
83
+ "Case=Nom|Number=Plur|POS=PRON|Person=3|PronType=Prs",
84
+ "POS=PRON|PronType=Prs|Reflex=Yes",
85
+ "Gender=Masc|POS=DET|PronType=Emp",
86
+ "Case=Nom|POS=PRON|PronType=Int",
87
+ "Link=Yes|POS=NOUN",
88
+ "POS=PART|PartType=Int",
89
+ "POS=INTJ|Polarity=Pos",
90
+ "Link=Yes|POS=PART|PartType=Int",
91
+ "POS=VERB|Polarity=Neg",
92
+ "Degree=Pos|POS=ADJ|PronType=Int",
93
+ "Case=Gen|Number=Plur|POS=PRON|Person=3|PronType=Prs",
94
+ "Aspect=Perf|Mood=Ind|POS=VERB|PronType=Int|Voice=Act",
95
+ "Case=Nom|Number=Sing|POS=PRON|Person=2|PronType=Prs",
96
+ "Aspect=Perf|Mood=Ind|POS=VERB|PronType=Int|Voice=Pass",
97
+ "Aspect=Perf|Mood=Ind|POS=VERB|Voice=Ifoc",
98
+ "POS=ADV|PronType=Int",
99
+ "Aspect=Prog|Mood=Ind|POS=VERB|Voice=Act",
100
+ "POS=PART|PartType=Nfh",
101
+ "Deixis=Remt|POS=ADV|PronType=Dem",
102
+ "Aspect=Imp|Mood=Pot|POS=VERB|Voice=Act",
103
+ "Link=Yes|POS=VERB|Polarity=Pos",
104
+ "Link=Yes|POS=VERB|Polarity=Neg",
105
+ "POS=PART|PartType=Des",
106
+ "Mood=Imp|POS=AUX|Polarity=Neg",
107
+ "Case=Nom|Link=Yes|Number=Plur|POS=PRON|Person=2|PronType=Prs",
108
+ "Case=Nom|Link=Yes|Number=Sing|POS=PRON|Person=3|PronType=Prs",
109
+ "Aspect=Prog|Mood=Ind|POS=VERB|Voice=Pass",
110
+ "Aspect=Prog|Mood=Ind|POS=VERB|Voice=Lfoc",
111
+ "Aspect=Prog|Mood=Ind|POS=VERB|Voice=Bfoc",
112
+ "POS=DET|PronType=Tot",
113
+ "Case=Dat|Link=Yes|Number=Sing|POS=PRON|Person=3|PronType=Prs",
114
+ "Link=Yes|POS=PRON|PronType=Prs|Reflex=Yes",
115
+ "Mood=Imp|POS=VERB|Voice=Act",
116
+ "Case=Dat|Number=Sing|POS=PRON|Person=3|PronType=Prs",
117
+ "Mood=Imp|POS=VERB|Voice=Lfoc",
118
+ "Case=Gen|Number=Sing|POS=PRON|Person=2|PronType=Prs",
119
+ "Mood=Imp|POS=VERB|Voice=Pass",
120
+ "Case=Gen|Clusivity=In|Number=Plur|POS=PRON|Person=1|PronType=Prs",
121
+ "Aspect=Hab|POS=VERB|Voice=Pass",
122
+ "Gender=Masc|Link=Yes|POS=PROPN",
123
+ "Case=Gen|Link=Yes|Number=Sing|POS=PRON|Person=3|PronType=Prs",
124
+ "Case=Gen|Link=Yes|Number=Sing|POS=PRON|Person=1|PronType=Prs",
125
+ "POS=ADJ",
126
+ "POS=PART",
127
+ "POS=PRON",
128
+ "POS=VERB",
129
+ "POS=INTJ",
130
+ "POS=CCONJ",
131
+ "POS=NUM",
132
+ "POS=DET"
133
+ ],
134
+ "parser":[
135
+ "ROOT",
136
+ "advmod",
137
+ "case",
138
+ "dep",
139
+ "nmod",
140
+ "nsubj",
141
+ "obj",
142
+ "obl",
143
+ "punct"
144
+ ],
145
+ "ner":[
146
+ "LOC",
147
+ "ORG",
148
+ "PER"
149
+ ]
150
+ },
151
+ "pipeline":[
152
+ "transformer",
153
+ "tagger",
154
+ "morphologizer",
155
+ "parser",
156
+ "ner"
157
+ ],
158
+ "components":[
159
+ "transformer",
160
+ "tagger",
161
+ "morphologizer",
162
+ "parser",
163
+ "ner"
164
+ ],
165
+ "disabled":[
166
+
167
+ ],
168
+ "parent_package":"spacy",
169
+ "requirements":[
170
+ "spacy-transformers>=1.2.0"
171
+ ],
172
+ "sources":[
173
+ {
174
+ "name":"TLUnified dataset",
175
+ "license":"GNU GPL 3.0",
176
+ "author":"Jan Christian Blaise Cruz and Charibeth Cheng",
177
+ "url":"https://aclanthology.org/2022.lrec-1.703/"
178
+ },
179
+ {
180
+ "name":"UD_Tagalog-TRG",
181
+ "license":"CC BY-SA 3.0",
182
+ "author":"Stephanie Samson, Daniel Zeman, and Mary Ann C. Tan",
183
+ "url":"https://universaldependencies.org/treebanks/tl_trg/index.html"
184
+ },
185
+ {
186
+ "name":"UD_Tagalog-Ugnayan",
187
+ "license":"CC BY-NC-SA 4.0",
188
+ "author":"Angelina Aquino",
189
+ "url":"https://universaldependencies.org/treebanks/tl_ugnayan/index.html"
190
+ }
191
+ ]
192
+ }
morphologizer/cfg ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "extend":false,
3
+ "labels_morph":{
4
+ "Aspect=Perf|Mood=Ind|POS=VERB|Voice=Act":"Aspect=Perf|Mood=Ind|Voice=Act",
5
+ "Case=Nom|POS=ADP":"Case=Nom",
6
+ "POS=NOUN":"",
7
+ "POS=PUNCT":"",
8
+ "Aspect=Perf|Mood=Ind|POS=VERB|Voice=Pass":"Aspect=Perf|Mood=Ind|Voice=Pass",
9
+ "Case=Gen|POS=ADP":"Case=Gen",
10
+ "Case=Gen|Number=Sing|POS=PRON|Person=1|PronType=Prs":"Case=Gen|Number=Sing|Person=1|PronType=Prs",
11
+ "Aspect=Imp|Mood=Ind|POS=VERB|Voice=Act":"Aspect=Imp|Mood=Ind|Voice=Act",
12
+ "POS=ADV|PronType=Dem":"PronType=Dem",
13
+ "Foreign=Yes|POS=NOUN":"Foreign=Yes",
14
+ "Degree=Pos|POS=ADJ":"Degree=Pos",
15
+ "Case=Nom|Number=Sing|POS=PRON|Person=3|PronType=Prs":"Case=Nom|Number=Sing|Person=3|PronType=Prs",
16
+ "Case=Nom|Deixis=Med|Number=Sing|POS=PRON|PronType=Dem":"Case=Nom|Deixis=Med|Number=Sing|PronType=Dem",
17
+ "Gender=Masc|POS=PROPN":"Gender=Masc",
18
+ "Case=Gen|Number=Sing|POS=PRON|Person=3|PronType=Prs":"Case=Gen|Number=Sing|Person=3|PronType=Prs",
19
+ "Degree=Pos|Link=Yes|POS=ADJ":"Degree=Pos|Link=Yes",
20
+ "POS=ADP":"",
21
+ "Case=Dat|POS=ADP":"Case=Dat",
22
+ "POS=VERB|Polarity=Pos":"Polarity=Pos",
23
+ "Aspect=Hab|POS=VERB":"Aspect=Hab",
24
+ "POS=SCONJ":"",
25
+ "Case=Nom|Number=Sing|POS=PRON|Person=1|PronType=Prs":"Case=Nom|Number=Sing|Person=1|PronType=Prs",
26
+ "Aspect=Prosp|Mood=Ind|POS=VERB|Voice=Act":"Aspect=Prosp|Mood=Ind|Voice=Act",
27
+ "POS=ADV":"",
28
+ "POS=PART|Polarity=Neg":"Polarity=Neg",
29
+ "Aspect=Imp|Mood=Ind|POS=VERB|Voice=Pass":"Aspect=Imp|Mood=Ind|Voice=Pass",
30
+ "Aspect=Perf|Mood=Ind|POS=VERB|Voice=Lfoc":"Aspect=Perf|Mood=Ind|Voice=Lfoc",
31
+ "POS=PROPN":"",
32
+ "Case=Nom|Deixis=Prox|Number=Sing|POS=PRON|PronType=Dem":"Case=Nom|Deixis=Prox|Number=Sing|PronType=Dem",
33
+ "Gender=Masc|POS=NOUN":"Gender=Masc",
34
+ "Gender=Fem|POS=NOUN":"Gender=Fem",
35
+ "Degree=Pos|Gender=Fem|POS=ADJ":"Degree=Pos|Gender=Fem",
36
+ "Gender=Fem|POS=PROPN":"Gender=Fem",
37
+ "Case=Nom|Clusivity=In|Number=Dual|POS=PRON|Person=1|PronType=Prs":"Case=Nom|Clusivity=In|Number=Dual|Person=1|PronType=Prs",
38
+ "Number=Plur|POS=DET|PronType=Ind":"Number=Plur|PronType=Ind",
39
+ "Case=Nom|Number=Plur|POS=PRON|Person=3|PronType=Prs":"Case=Nom|Number=Plur|Person=3|PronType=Prs",
40
+ "POS=PRON|PronType=Prs|Reflex=Yes":"PronType=Prs|Reflex=Yes",
41
+ "Gender=Masc|POS=DET|PronType=Emp":"Gender=Masc|PronType=Emp",
42
+ "Case=Nom|POS=PRON|PronType=Int":"Case=Nom|PronType=Int",
43
+ "Link=Yes|POS=NOUN":"Link=Yes",
44
+ "POS=PART|PartType=Int":"PartType=Int",
45
+ "POS=INTJ|Polarity=Pos":"Polarity=Pos",
46
+ "Link=Yes|POS=PART|PartType=Int":"Link=Yes|PartType=Int",
47
+ "POS=VERB|Polarity=Neg":"Polarity=Neg",
48
+ "Degree=Pos|POS=ADJ|PronType=Int":"Degree=Pos|PronType=Int",
49
+ "Case=Gen|Number=Plur|POS=PRON|Person=3|PronType=Prs":"Case=Gen|Number=Plur|Person=3|PronType=Prs",
50
+ "Aspect=Perf|Mood=Ind|POS=VERB|PronType=Int|Voice=Act":"Aspect=Perf|Mood=Ind|PronType=Int|Voice=Act",
51
+ "Case=Nom|Number=Sing|POS=PRON|Person=2|PronType=Prs":"Case=Nom|Number=Sing|Person=2|PronType=Prs",
52
+ "Aspect=Perf|Mood=Ind|POS=VERB|PronType=Int|Voice=Pass":"Aspect=Perf|Mood=Ind|PronType=Int|Voice=Pass",
53
+ "Aspect=Perf|Mood=Ind|POS=VERB|Voice=Ifoc":"Aspect=Perf|Mood=Ind|Voice=Ifoc",
54
+ "POS=ADV|PronType=Int":"PronType=Int",
55
+ "Aspect=Prog|Mood=Ind|POS=VERB|Voice=Act":"Aspect=Prog|Mood=Ind|Voice=Act",
56
+ "POS=PART|PartType=Nfh":"PartType=Nfh",
57
+ "Deixis=Remt|POS=ADV|PronType=Dem":"Deixis=Remt|PronType=Dem",
58
+ "Aspect=Imp|Mood=Pot|POS=VERB|Voice=Act":"Aspect=Imp|Mood=Pot|Voice=Act",
59
+ "Link=Yes|POS=VERB|Polarity=Pos":"Link=Yes|Polarity=Pos",
60
+ "Link=Yes|POS=VERB|Polarity=Neg":"Link=Yes|Polarity=Neg",
61
+ "POS=PART|PartType=Des":"PartType=Des",
62
+ "Mood=Imp|POS=AUX|Polarity=Neg":"Mood=Imp|Polarity=Neg",
63
+ "Case=Nom|Link=Yes|Number=Plur|POS=PRON|Person=2|PronType=Prs":"Case=Nom|Link=Yes|Number=Plur|Person=2|PronType=Prs",
64
+ "Case=Nom|Link=Yes|Number=Sing|POS=PRON|Person=3|PronType=Prs":"Case=Nom|Link=Yes|Number=Sing|Person=3|PronType=Prs",
65
+ "Aspect=Prog|Mood=Ind|POS=VERB|Voice=Pass":"Aspect=Prog|Mood=Ind|Voice=Pass",
66
+ "Aspect=Prog|Mood=Ind|POS=VERB|Voice=Lfoc":"Aspect=Prog|Mood=Ind|Voice=Lfoc",
67
+ "Aspect=Prog|Mood=Ind|POS=VERB|Voice=Bfoc":"Aspect=Prog|Mood=Ind|Voice=Bfoc",
68
+ "POS=DET|PronType=Tot":"PronType=Tot",
69
+ "Case=Dat|Link=Yes|Number=Sing|POS=PRON|Person=3|PronType=Prs":"Case=Dat|Link=Yes|Number=Sing|Person=3|PronType=Prs",
70
+ "Link=Yes|POS=PRON|PronType=Prs|Reflex=Yes":"Link=Yes|PronType=Prs|Reflex=Yes",
71
+ "Mood=Imp|POS=VERB|Voice=Act":"Mood=Imp|Voice=Act",
72
+ "Case=Dat|Number=Sing|POS=PRON|Person=3|PronType=Prs":"Case=Dat|Number=Sing|Person=3|PronType=Prs",
73
+ "Mood=Imp|POS=VERB|Voice=Lfoc":"Mood=Imp|Voice=Lfoc",
74
+ "Case=Gen|Number=Sing|POS=PRON|Person=2|PronType=Prs":"Case=Gen|Number=Sing|Person=2|PronType=Prs",
75
+ "Mood=Imp|POS=VERB|Voice=Pass":"Mood=Imp|Voice=Pass",
76
+ "Case=Gen|Clusivity=In|Number=Plur|POS=PRON|Person=1|PronType=Prs":"Case=Gen|Clusivity=In|Number=Plur|Person=1|PronType=Prs",
77
+ "Aspect=Hab|POS=VERB|Voice=Pass":"Aspect=Hab|Voice=Pass",
78
+ "Gender=Masc|Link=Yes|POS=PROPN":"Gender=Masc|Link=Yes",
79
+ "Case=Gen|Link=Yes|Number=Sing|POS=PRON|Person=3|PronType=Prs":"Case=Gen|Link=Yes|Number=Sing|Person=3|PronType=Prs",
80
+ "Case=Gen|Link=Yes|Number=Sing|POS=PRON|Person=1|PronType=Prs":"Case=Gen|Link=Yes|Number=Sing|Person=1|PronType=Prs",
81
+ "POS=ADJ":"",
82
+ "POS=PART":"",
83
+ "POS=PRON":"",
84
+ "POS=VERB":"",
85
+ "POS=INTJ":"",
86
+ "POS=CCONJ":"",
87
+ "POS=NUM":"",
88
+ "POS=DET":""
89
+ },
90
+ "labels_pos":{
91
+ "Aspect=Perf|Mood=Ind|POS=VERB|Voice=Act":100,
92
+ "Case=Nom|POS=ADP":85,
93
+ "POS=NOUN":92,
94
+ "POS=PUNCT":97,
95
+ "Aspect=Perf|Mood=Ind|POS=VERB|Voice=Pass":100,
96
+ "Case=Gen|POS=ADP":85,
97
+ "Case=Gen|Number=Sing|POS=PRON|Person=1|PronType=Prs":95,
98
+ "Aspect=Imp|Mood=Ind|POS=VERB|Voice=Act":100,
99
+ "POS=ADV|PronType=Dem":86,
100
+ "Foreign=Yes|POS=NOUN":92,
101
+ "Degree=Pos|POS=ADJ":84,
102
+ "Case=Nom|Number=Sing|POS=PRON|Person=3|PronType=Prs":95,
103
+ "Case=Nom|Deixis=Med|Number=Sing|POS=PRON|PronType=Dem":95,
104
+ "Gender=Masc|POS=PROPN":96,
105
+ "Case=Gen|Number=Sing|POS=PRON|Person=3|PronType=Prs":95,
106
+ "Degree=Pos|Link=Yes|POS=ADJ":84,
107
+ "POS=ADP":85,
108
+ "Case=Dat|POS=ADP":85,
109
+ "POS=VERB|Polarity=Pos":100,
110
+ "Aspect=Hab|POS=VERB":100,
111
+ "POS=SCONJ":98,
112
+ "Case=Nom|Number=Sing|POS=PRON|Person=1|PronType=Prs":95,
113
+ "Aspect=Prosp|Mood=Ind|POS=VERB|Voice=Act":100,
114
+ "POS=ADV":86,
115
+ "POS=PART|Polarity=Neg":94,
116
+ "Aspect=Imp|Mood=Ind|POS=VERB|Voice=Pass":100,
117
+ "Aspect=Perf|Mood=Ind|POS=VERB|Voice=Lfoc":100,
118
+ "POS=PROPN":96,
119
+ "Case=Nom|Deixis=Prox|Number=Sing|POS=PRON|PronType=Dem":95,
120
+ "Gender=Masc|POS=NOUN":92,
121
+ "Gender=Fem|POS=NOUN":92,
122
+ "Degree=Pos|Gender=Fem|POS=ADJ":84,
123
+ "Gender=Fem|POS=PROPN":96,
124
+ "Case=Nom|Clusivity=In|Number=Dual|POS=PRON|Person=1|PronType=Prs":95,
125
+ "Number=Plur|POS=DET|PronType=Ind":90,
126
+ "Case=Nom|Number=Plur|POS=PRON|Person=3|PronType=Prs":95,
127
+ "POS=PRON|PronType=Prs|Reflex=Yes":95,
128
+ "Gender=Masc|POS=DET|PronType=Emp":90,
129
+ "Case=Nom|POS=PRON|PronType=Int":95,
130
+ "Link=Yes|POS=NOUN":92,
131
+ "POS=PART|PartType=Int":94,
132
+ "POS=INTJ|Polarity=Pos":91,
133
+ "Link=Yes|POS=PART|PartType=Int":94,
134
+ "POS=VERB|Polarity=Neg":100,
135
+ "Degree=Pos|POS=ADJ|PronType=Int":84,
136
+ "Case=Gen|Number=Plur|POS=PRON|Person=3|PronType=Prs":95,
137
+ "Aspect=Perf|Mood=Ind|POS=VERB|PronType=Int|Voice=Act":100,
138
+ "Case=Nom|Number=Sing|POS=PRON|Person=2|PronType=Prs":95,
139
+ "Aspect=Perf|Mood=Ind|POS=VERB|PronType=Int|Voice=Pass":100,
140
+ "Aspect=Perf|Mood=Ind|POS=VERB|Voice=Ifoc":100,
141
+ "POS=ADV|PronType=Int":86,
142
+ "Aspect=Prog|Mood=Ind|POS=VERB|Voice=Act":100,
143
+ "POS=PART|PartType=Nfh":94,
144
+ "Deixis=Remt|POS=ADV|PronType=Dem":86,
145
+ "Aspect=Imp|Mood=Pot|POS=VERB|Voice=Act":100,
146
+ "Link=Yes|POS=VERB|Polarity=Pos":100,
147
+ "Link=Yes|POS=VERB|Polarity=Neg":100,
148
+ "POS=PART|PartType=Des":94,
149
+ "Mood=Imp|POS=AUX|Polarity=Neg":87,
150
+ "Case=Nom|Link=Yes|Number=Plur|POS=PRON|Person=2|PronType=Prs":95,
151
+ "Case=Nom|Link=Yes|Number=Sing|POS=PRON|Person=3|PronType=Prs":95,
152
+ "Aspect=Prog|Mood=Ind|POS=VERB|Voice=Pass":100,
153
+ "Aspect=Prog|Mood=Ind|POS=VERB|Voice=Lfoc":100,
154
+ "Aspect=Prog|Mood=Ind|POS=VERB|Voice=Bfoc":100,
155
+ "POS=DET|PronType=Tot":90,
156
+ "Case=Dat|Link=Yes|Number=Sing|POS=PRON|Person=3|PronType=Prs":95,
157
+ "Link=Yes|POS=PRON|PronType=Prs|Reflex=Yes":95,
158
+ "Mood=Imp|POS=VERB|Voice=Act":100,
159
+ "Case=Dat|Number=Sing|POS=PRON|Person=3|PronType=Prs":95,
160
+ "Mood=Imp|POS=VERB|Voice=Lfoc":100,
161
+ "Case=Gen|Number=Sing|POS=PRON|Person=2|PronType=Prs":95,
162
+ "Mood=Imp|POS=VERB|Voice=Pass":100,
163
+ "Case=Gen|Clusivity=In|Number=Plur|POS=PRON|Person=1|PronType=Prs":95,
164
+ "Aspect=Hab|POS=VERB|Voice=Pass":100,
165
+ "Gender=Masc|Link=Yes|POS=PROPN":96,
166
+ "Case=Gen|Link=Yes|Number=Sing|POS=PRON|Person=3|PronType=Prs":95,
167
+ "Case=Gen|Link=Yes|Number=Sing|POS=PRON|Person=1|PronType=Prs":95,
168
+ "POS=ADJ":84,
169
+ "POS=PART":94,
170
+ "POS=PRON":95,
171
+ "POS=VERB":100,
172
+ "POS=INTJ":91,
173
+ "POS=CCONJ":89,
174
+ "POS=NUM":93,
175
+ "POS=DET":90
176
+ },
177
+ "overwrite":true
178
+ }
morphologizer/model ADDED
Binary file (262 kB). View file
 
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:e7f816c35b974da2755991cff78ddee5acc4e2fd75563a42578d4ae968c5e8d3
3
+ size 438628573
ner/moves ADDED
@@ -0,0 +1 @@
 
 
1
+ ��movesٸ{"0":{},"1":{"PER":10523,"ORG":6754,"LOC":5296},"2":{"PER":10523,"ORG":6754,"LOC":5296},"3":{"PER":10523,"ORG":6754,"LOC":5296},"4":{"PER":10523,"ORG":6754,"LOC":5296,"":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
Binary file (543 kB). View file
 
parser/moves ADDED
@@ -0,0 +1 @@
 
 
1
+ ��movesٓ{"0":{"":498},"1":{"":784},"2":{"case":287,"dep":0},"3":{"punct":220,"nsubj":147,"obj":75,"obl":61,"advmod":50,"nmod":49,"dep":0},"4":{"ROOT":199}}�cfg��neg_key�
tagger/cfg ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "labels":[
3
+ "ADJ",
4
+ "ADJ_PART",
5
+ "ADP",
6
+ "ADV",
7
+ "ADV_PART",
8
+ "AUX",
9
+ "CCONJ",
10
+ "DET",
11
+ "DET_ADP",
12
+ "DET_PART",
13
+ "INTJ",
14
+ "NOUN",
15
+ "NOUN_PART",
16
+ "NUM",
17
+ "NUM_PART",
18
+ "PART",
19
+ "PRON",
20
+ "PRON_PART",
21
+ "PROPN",
22
+ "PUNCT",
23
+ "SCONJ",
24
+ "VERB",
25
+ "VERB_PART"
26
+ ],
27
+ "neg_prefix":"!",
28
+ "overwrite":false
29
+ }
tagger/model ADDED
Binary file (71.4 kB). View file
 
tl_calamancy_trf-any-py3-none-any.whl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4340e618abffa4de882b6164a5e1463f3072995c14f51e73d9c5b4abf70a144d
3
+ size 813029016
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\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][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]|(?<=[0-9])[+\-\*^](?=[0-9-])|(?<=[a-z\uFF41-\uFF5A\u00DF-\u00F6\u00F8-\u00FF\u0101\u0103\u0105\u0107\u0109\u010B\u010D\u010F\u0111\u0113\u0115\u0117\u0119\u011B\u011D\u011F\u0121\u0123\u0125\u0127\u0129\u012B\u012D\u012F\u0131\u0133\u0135\u0137\u0138\u013A\u013C\u013E\u0140\u0142\u0144\u0146\u0148\u0149\u014B\u014D\u014F\u0151\u0153\u0155\u0157\u0159\u015B\u015D\u015F\u0161\u0163\u0165\u0167\u0169\u016B\u016D\u016F\u0171\u0173\u0175\u0177\u017A\u017C\u017E\u017F\u0180\u0183\u0185\u0188\u018C\u018D\u0192\u0195\u0199-\u019B\u019E\u01A1\u01A3\u01A5\u01A8\u01AA\u01AB\u01AD\u01B0\u01B4\u01B6\u01B9\u01BA\u01BD-\u01BF\u01C6\u01C9\u01CC\u01CE\u01D0\u01D2\u01D4\u01D6\u01D8\u01DA\u01DC\u01DD\u01DF\u01E1\u01E3\u01E5\u01E7\u01E9\u01EB\u01ED\u01EF\u01F0\u01F3\u01F5\u01F9\u01FB\u01FD\u01FF\u0201\u0203\u0205\u0207\u0209\u020B\u020D\u020F\u0211\u0213\u0215\u0217\u0219\u021B\u021D\u021F\u0221\u0223\u0225\u0227\u0229\u022B\u022D\u022F\u0231\u0233-\u0239\u023C\u023F\u0240\u0242\u0247\u0249\u024B\u024D\u024F\u2C61\u2C65\u2C66\u2C68\u2C6A\u2C6C\u2C71\u2C73\u2C74\u2C76-\u2C7B\uA723\uA725\uA727\uA729\uA72B\uA72D\uA72F-\uA731\uA733\uA735\uA737\uA739\uA73B\uA73D\uA73F\uA741\uA743\uA745\uA747\uA749\uA74B\uA74D\uA74F\uA751\uA753\uA755\uA757\uA759\uA75B\uA75D\uA75F\uA761\uA763\uA765\uA767\uA769\uA76B\uA76D\uA76F\uA771-\uA778\uA77A\uA77C\uA77F\uA781\uA783\uA785\uA787\uA78C\uA78E\uA791\uA793-\uA795\uA797\uA799\uA79B\uA79D\uA79F\uA7A1\uA7A3\uA7A5\uA7A7\uA7A9\uA7AF\uA7B5\uA7B7\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E01\u1E03\u1E05\u1E07\u1E09\u1E0B\u1E0D\u1E0F\u1E11\u1E13\u1E15\u1E17\u1E19\u1E1B\u1E1D\u1E1F\u1E21\u1E23\u1E25\u1E27\u1E29\u1E2B\u1E2D\u1E2F\u1E31\u1E33\u1E35\u1E37\u1E39\u1E3B\u1E3D\u1E3F\u1E41\u1E43\u1E45\u1E47\u1E49\u1E4B\u1E4D\u1E4F\u1E51\u1E53\u1E55\u1E57\u1E59\u1E5B\u1E5D\u1E5F\u1E61\u1E63\u1E65\u1E67\u1E69\u1E6B\u1E6D\u1E6F\u1E71\u1E73\u1E75\u1E77\u1E79\u1E7B\u1E7D\u1E7F\u1E81\u1E83\u1E85\u1E87\u1E89\u1E8B\u1E8D\u1E8F\u1E91\u1E93\u1E95-\u1E9D\u1E9F\u1EA1\u1EA3\u1EA5\u1EA7\u1EA9\u1EAB\u1EAD\u1EAF\u1EB1\u1EB3\u1EB5\u1EB7\u1EB9\u1EBB\u1EBD\u1EBF\u1EC1\u1EC3\u1EC5\u1EC7\u1EC9\u1ECB\u1ECD\u1ECF\u1ED1\u1ED3\u1ED5\u1ED7\u1ED9\u1EDB\u1EDD\u1EDF\u1EE1\u1EE3\u1EE5\u1EE7\u1EE9\u1EEB\u1EED\u1EEF\u1EF1\u1EF3\u1EF5\u1EF7\u1EF9\u1EFB\u1EFD\u1EFFёа-яәөүҗңһα-ωάέίόώήύа-щюяіїєґѓѕјљњќѐѝ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F\'"”“`‘´’‚,„»«「」『』()〔〕【】《》〈〉〈〉⟦⟧])\.(?=[A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F\'"”“`‘´’‚,„»«「」『』()〔〕【】《》〈〉〈〉⟦⟧])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F]),(?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])(?:-|–|—|--|---|——|~)(?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F0-9])[:<>=/](?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])�token_match��url_match�
2
+ ��A�
3
+ � ��A� �'��A�'�''��A�''�'di��A�'diC�hindi�(*_*)��A�(*_*)�(-8��A�(-8�(-:��A�(-:�(-;��A�(-;�(-_-)��A�(-_-)�(._.)��A�(._.)�(:��A�(:�(;��A�(;�(=��A�(=�(>_<)��A�(>_<)�(^_^)��A�(^_^)�(o:��A�(o:�(¬_¬)��A�(¬_¬)�(ಠ_ಠ)��A�(ಠ_ಠ)�(╯°□°)╯︵┻━┻��A�(╯°□°)╯︵┻━┻�)-:��A�)-:�):��A�):�-_-��A�-_-�-__-��A�-__-�._.��A�._.�0.0��A�0.0�0.o��A�0.o�0_0��A�0_0�0_o��A�0_o�8)��A�8)�8-)��A�8-)�8-D��A�8-D�8D��A�8D�:'(��A�:'(�:')��A�:')�:'-(��A�:'-(�:'-)��A�:'-)�:(��A�:(�:((��A�:((�:(((��A�:(((�:()��A�:()�:)��A�:)�:))��A�:))�:)))��A�:)))�:*��A�:*�:-(��A�:-(�:-((��A�:-((�:-(((��A�:-(((�:-)��A�:-)�:-))��A�:-))�:-)))��A�:-)))�:-*��A�:-*�:-/��A�:-/�:-0��A�:-0�:-3��A�:-3�:->��A�:->�:-D��A�:-D�:-O��A�:-O�:-P��A�:-P�:-X��A�:-X�:-]��A�:-]�:-o��A�:-o�:-p��A�:-p�:-x��A�:-x�:-|��A�:-|�:-}��A�:-}�:/��A�:/�:0��A�:0�:1��A�:1�:3��A�:3�:>��A�:>�:D��A�:D�:O��A�:O�:P��A�:P�:X��A�:X�:]��A�:]�:o��A�:o�:o)��A�:o)�:p��A�:p�:x��A�:x�:|��A�:|�:}��A�:}�:’(��A�:’(�:’)��A�:’)�:’-(��A�:’-(�:’-)��A�:’-)�;)��A�;)�;-)��A�;-)�;-D��A�;-D�;D��A�;D�;_;��A�;_;�<.<��A�<.<�</3��A�</3�<3��A�<3�<33��A�<33�<333��A�<333�<space>��A�<space>�=(��A�=(�=)��A�=)�=/��A�=/�=3��A�=3�=D��A�=D�=[��A�=[�=]��A�=]�=|��A�=|�>.<��A�>.<�>.>��A�>.>�>:(��A�>:(�>:o��A�>:o�><(((*>��A�><(((*>�@_@��A�@_@�C++��A�C++�O.O��A�O.O�O.o��A�O.o�O_O��A�O_O�O_o��A�O_o�V.V��A�V.V�V_V��A�V_V�XD��A�XD�XDD��A�XDD�[-:��A�[-:�[:��A�[:�[=��A�[=�\")��A�\")�\n��A�\n�\t��A�\t�]=��A�]=�^_^��A�^_^�^__^��A�^__^�^___^��A�^___^�a.��A�a.�ano'ng��A�ano�A�'ngC�ang�ano’ng��A�ano�A�’ngC�ang�b.��A�b.�baya'y��A�baya�A�'yC�ay�baya’y��A�baya�A�’yC�ay�c.��A�c.�d.��A�d.�e.��A�e.�f.��A�f.�g.��A�g.�h.��A�h.�i.��A�i.�isa'y��A�isa�A�'yC�ay�isa’y��A�isa�A�’yC�ay�j.��A�j.�k.��A�k.�l.��A�l.�m.��A�m.�n.��A�n.�nawa'y��A�nawa�A�'yC�ay�nawa’y��A�nawa�A�’yC�ay�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.�papa'no��A�papa'noC�papaano�papa’no��A�papa’noC�papaano�q.��A�q.�r.��A�r.�s.��A�s.�sa'yo��A�sa�A�'yoC�iyo�sa’yo��A�sa�A�’yoC�iyo�siya'y��A�siya�A�'yC�ay�siya’y��A�siya�A�’yC�ay�t.��A�t.�tayo'y��A�tayo�A�'yC�ay�tayo’y��A�tayo�A�’yC�ay�u.��A�u.�v.��A�v.�v.v��A�v.v�v_v��A�v_v�w.��A�w.�x.��A�x.�xD��A�xD�xDD��A�xDD�y.��A�y.�z.��A�z.� ��A� C� �¯\(ツ)/¯��A�¯\(ツ)/¯�°C.��A�°�A�C�A�.�°F.��A�°�A�F�A�.�°K.��A�°�A�K�A�.�°c.��A�°�A�c�A�.�°f.��A�°�A�f�A�.�°k.��A�°�A�k�A�.�ä.��A�ä.�ö.��A�ö.�ü.��A�ü.�ಠ_ಠ��A�ಠ_ಠ�ಠ︵ಠ��A�ಠ︵ಠ�—��A�—�’��A�’�’di��A�’diC�hindi�’’��A�’’�faster_heuristics�
transformer/cfg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "max_batch_items":4096
3
+ }
transformer/model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e54f1191a37ae0253ef9da4b7cb7a0944369b632dad7d27b9108f8c9a94b8c1
3
+ size 438408883
vocab/key2row ADDED
@@ -0,0 +1 @@
 
 
1
+
vocab/lookups.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
3
+ size 1
vocab/strings.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab/vectors ADDED
Binary file (128 Bytes). View file
 
vocab/vectors.cfg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "mode":"default"
3
+ }