ljvmiranda921 commited on Nov 27, 2023

Commit

e13be7b

•

1 Parent(s): cea4452

xx_fro_sigtyp_trf-0.1.0: Update SIGTYP pipeline

Browse files

Files changed (21) hide show

.gitattributes +4 -0
README.md +85 -0
config.cfg +190 -0
meta.json +359 -0
parser/cfg +13 -0
parser/model +3 -0
parser/moves +1 -0
tagger/cfg +98 -0
tagger/model +0 -0
tokenizer +3 -0
trainable_lemmatizer/cfg +785 -0
trainable_lemmatizer/model +3 -0
trainable_lemmatizer/trees +0 -0
transformer/cfg +3 -0
transformer/model +3 -0
vocab/key2row +1 -0
vocab/lookups.bin +3 -0
vocab/strings.json +0 -0
vocab/vectors +0 -0
vocab/vectors.cfg +3 -0
xx_fro_sigtyp_trf-any-py3-none-any.whl +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+parser/model filter=lfs diff=lfs merge=lfs -text
+trainable_lemmatizer/model filter=lfs diff=lfs merge=lfs -text
+transformer/model filter=lfs diff=lfs merge=lfs -text
+xx_fro_sigtyp_trf-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text

README.md ADDED Viewed

	@@ -0,0 +1,85 @@

+---
+tags:
+- spacy
+- token-classification
+language:
+- multilingual
+model-index:
+- name: xx_fro_sigtyp_trf
+  results:
+  - task:
+      name: TAG
+      type: token-classification
+    metrics:
+    - name: TAG (XPOS) Accuracy
+      type: accuracy
+      value: 0.8626325088
+  - task:
+      name: LEMMA
+      type: token-classification
+    metrics:
+    - name: Lemma Accuracy
+      type: accuracy
+      value: 0.8348421285
+  - task:
+      name: UNLABELED_DEPENDENCIES
+      type: token-classification
+    metrics:
+    - name: Unlabeled Attachment Score (UAS)
+      type: f_score
+      value: 0.6967152383
+  - task:
+      name: LABELED_DEPENDENCIES
+      type: token-classification
+    metrics:
+    - name: Labeled Attachment Score (LAS)
+      type: f_score
+      value: 0.6162015312
+  - task:
+      name: SENTS
+      type: token-classification
+    metrics:
+    - name: Sentences F-Score
+      type: f_score
+      value: 0.8357487923
+---
+| Feature | Description |
+| --- | --- |
+| **Name** | `xx_fro_sigtyp_trf` |
+| **Version** | `0.1.0` |
+| **spaCy** | `>=3.6.1,<3.7.0` |
+| **Default Pipeline** | `transformer`, `parser`, `trainable_lemmatizer`, `tagger` |
+| **Components** | `transformer`, `parser`, `trainable_lemmatizer`, `tagger` |
+| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
+| **Sources** | n/a |
+| **License** | n/a |
+| **Author** | [n/a]() |
+### Label Scheme
+<details>
+<summary>View label scheme (124 labels for 2 components)</summary>
+| Component | Labels |
+| --- | --- |
+| **`parser`** | `ROOT`, `acl`, `acl:relcl`, `advcl`, `advmod`, `amod`, `appos`, `aux`, `aux:pass`, `case`, `case:det`, `cc`, `cc:nc`, `ccomp`, `conj`, `cop`, `csubj`, `dep`, `det`, `expl`, `flat`, `iobj`, `mark`, `nmod`, `nsubj`, `nummod`, `obj`, `obl`, `obl:advmod`, `parataxis`, `punct`, `vocative`, `xcomp` |
+| **`tagger`** | `ADJcar__NumType=Card`, `ADJind__PronType=Ind`, `ADJord`, `ADJpos__Poss=Yes`, `ADJqua`, `ADJqua__Tense=Past\|VerbForm=Part`, `ADJqua__Tense=Pres\|VerbForm=Part`, `ADVgen`, `ADVgen.PROper`, `ADVgen__PronType=Ind`, `ADVgen__PronType=Prs,Rel`, `ADVgen__PronType=Rel`, `ADVint__PronType=Int`, `ADVneg`, `ADVneg.PROper__Polarity=Neg\|PronType=Prs`, `ADVneg__Polarity=Neg`, `ADVsub`, `CONcoo`, `CONcoo__PronType=Prs,Rel`, `CONsub`, `CONsub.PROper`, `CONsub__PronType=Rel`, `DETcar__NumType=Card`, `DETdef__Definite=Def`, `DETdef__Definite=Def\|PronType=Art`, `DETdef__PronType=Ind`, `DETdef__PronType=Prs`, `DETdem__PronType=Dem`, `DETdem__PronType=Prs`, `DETind__PronType=Ind`, `DETint__PronType=Int`, `DETndf__Definite=Ind`, `DETndf__Definite=Ind\|PronType=Art`, `DETord`, `DETord__NumType=Ord`, `DETpos__Poss=Yes`, `DETrel__PronType=Rel`, `INJ`, `NOMcom`, `NOMcom__Morph=VFin`, `NOMcom__VerbForm=Inf`, `NOMpro`, `PONfbl`, `PONfrt`, `PONpdr`, `PONpga`, `PONpxx`, `PRE`, `PRE.DETdef__Definite=Def\|PronType=Art`, `PRE.PROper`, `PRE.PROper__Definite=Def\|PronType=Art`, `PRE__Morph=VFin`, `PRE__PronType=Dem`, `PREdetdef__PronType=Prs,Rel`, `PROadv`, `PROadv__PronType=Dem`, `PROcar`, `PROcar__NumType=Card`, `PROdem__PronType=Dem`, `PROdem__PronType=Prs,Rel`, `PROimp`, `PROimp__PronType=Prs`, `PROind`, `PROind__PronType=Ind`, `PROind__PronType=Rel`, `PROint__PronType=Int`, `PROord__NumType=Ord`, `PROper`, `PROper.PROper__PronType=Prs`, `PROper__Poss=Yes`, `PROper__PronType=Prs`, `PROpos__Poss=Yes`, `PROpos__Poss=Yes\|PronType=Prs`, `PROrel`, `PROrel__PronType=Prs,Rel`, `PROrel__PronType=Rel`, `RED`, `VERcjg`, `VERcjg__VerbForm=Fin`, `VERcjg__VerbForm=Inf`, `VERinf__VerbForm=Inf`, `VERppa__Tense=Pres\|VerbForm=Part`, `VERppe`, `VERppe__Tense=Past`, `VERppe__Tense=Past\|VerbForm=Part`, `devenir__Tense=Past\|VerbForm=Part`, `devenir__VerbForm=Fin`, `laisser__VerbForm=Fin`, `remanoir__VerbForm=Fin`, `ressembler__VerbForm=Fin`, `sembler__VerbForm=Fin` |
+</details>
+### Accuracy
+| Type | Score |
+| --- | --- |
+| `DEP_UAS` | 69.67 |
+| `DEP_LAS` | 61.62 |
+| `SENTS_P` | 78.82 |
+| `SENTS_R` | 88.95 |
+| `SENTS_F` | 83.57 |
+| `LEMMA_ACC` | 83.48 |
+| `TAG_ACC` | 86.26 |
+| `TRANSFORMER_LOSS` | 44338.10 |
+| `PARSER_LOSS` | 6886.30 |
+| `TRAINABLE_LEMMATIZER_LOSS` | 1446.31 |
+| `TAGGER_LOSS` | 3500.05 |

config.cfg ADDED Viewed

	@@ -0,0 +1,190 @@

+[paths]
+train = "corpus/train/fro_train.spacy"
+dev = "corpus/dev/fro_valid.spacy"
+vectors = null
+init_tok2vec = null
+[system]
+gpu_allocator = "pytorch"
+seed = 42
+[nlp]
+lang = "xx"
+pipeline = ["transformer","parser","trainable_lemmatizer","tagger"]
+batch_size = 128
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
+[components]
+[components.parser]
+factory = "parser"
+learn_tokens = false
+min_action_freq = 30
+moves = null
+scorer = {"@scorers":"spacy.parser_scorer.v1"}
+update_with_oracle_cut_size = 100
+[components.parser.model]
+@architectures = "spacy.TransitionBasedParser.v2"
+state_type = "parser"
+extra_state_tokens = false
+hidden_width = 128
+maxout_pieces = 3
+use_upper = false
+nO = null
+[components.parser.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+pooling = {"@layers":"reduce_mean.v1"}
+upstream = "*"
+[components.tagger]
+factory = "tagger"
+label_smoothing = 0.0
+neg_prefix = "!"
+overwrite = false
+scorer = {"@scorers":"spacy.tagger_scorer.v1"}
+[components.tagger.model]
+@architectures = "spacy.Tagger.v2"
+nO = null
+normalize = false
+[components.tagger.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+pooling = {"@layers":"reduce_mean.v1"}
+upstream = "*"
+[components.trainable_lemmatizer]
+factory = "trainable_lemmatizer"
+backoff = "orth"
+min_tree_freq = 3
+overwrite = false
+scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
+top_k = 1
+[components.trainable_lemmatizer.model]
+@architectures = "spacy.Tagger.v2"
+nO = null
+normalize = false
+[components.trainable_lemmatizer.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+pooling = {"@layers":"reduce_mean.v1"}
+upstream = "*"
+[components.transformer]
+factory = "transformer"
+max_batch_items = 4096
+set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
+[components.transformer.model]
+@architectures = "spacy-transformers.TransformerModel.v3"
+name = "ljvmiranda921/LiBERTus-base"
+mixed_precision = false
+[components.transformer.model.get_spans]
+@span_getters = "spacy-transformers.strided_spans.v1"
+window = 128
+stride = 96
+[components.transformer.model.grad_scaler_config]
+[components.transformer.model.tokenizer_config]
+use_fast = true
+[components.transformer.model.transformer_config]
+[corpora]
+[corpora.dev]
+@readers = "spacy.Corpus.v1"
+path = ${paths.dev}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+[corpora.train]
+@readers = "spacy.Corpus.v1"
+path = ${paths.train}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+[training]
+accumulate_gradient = 3
+dev_corpus = "corpora.dev"
+train_corpus = "corpora.train"
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
+dropout = 0.1
+patience = 1600
+max_epochs = 0
+max_steps = 20000
+eval_frequency = 200
+frozen_components = []
+annotating_components = []
+before_to_disk = null
+before_update = null
+[training.batcher]
+@batchers = "spacy.batch_by_padded.v1"
+discard_oversize = true
+size = 2000
+buffer = 256
+get_length = null
+[training.logger]
+@loggers = "spacy.ConsoleLogger.v3"
+console_output = true
+progress_bar = "eval"
+output_file = null
+[training.optimizer]
+@optimizers = "Adam.v1"
+beta1 = 0.9
+beta2 = 0.999
+L2_is_weight_decay = true
+L2 = 0.01
+grad_clip = 1.0
+use_averages = false
+eps = 0.00000001
+[training.optimizer.learn_rate]
+@schedules = "warmup_linear.v1"
+warmup_steps = 250
+total_steps = 20000
+initial_rate = 0.00005
+[training.score_weights]
+dep_uas = 0.17
+dep_las = 0.17
+dep_las_per_type = null
+sents_p = null
+sents_r = null
+sents_f = 0.0
+lemma_acc = 0.33
+tag_acc = 0.33
+[pretraining]
+[initialize]
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+vocab_data = null
+lookups = null
+before_init = null
+after_init = null
+[initialize.components]
+[initialize.tokenizer]

meta.json ADDED Viewed

	@@ -0,0 +1,359 @@

+{
+  "lang":"xx",
+  "name":"fro_sigtyp_trf",
+  "version":"0.1.0",
+  "description":"",
+  "author":"",
+  "email":"",
+  "url":"",
+  "license":"",
+  "spacy_version":">=3.6.1,<3.7.0",
+  "spacy_git_version":"458bc5f45",
+  "vectors":{
+    "width":0,
+    "vectors":0,
+    "keys":0,
+    "name":null
+  },
+  "labels":{
+    "transformer":[
+    ],
+    "parser":[
+      "ROOT",
+      "acl",
+      "acl:relcl",
+      "advcl",
+      "advmod",
+      "amod",
+      "appos",
+      "aux",
+      "aux:pass",
+      "case",
+      "case:det",
+      "cc",
+      "cc:nc",
+      "ccomp",
+      "conj",
+      "cop",
+      "csubj",
+      "dep",
+      "det",
+      "expl",
+      "flat",
+      "iobj",
+      "mark",
+      "nmod",
+      "nsubj",
+      "nummod",
+      "obj",
+      "obl",
+      "obl:advmod",
+      "parataxis",
+      "punct",
+      "vocative",
+      "xcomp"
+    ],
+    "tagger":[
+      "ADJcar__NumType=Card",
+      "ADJind__PronType=Ind",
+      "ADJord",
+      "ADJpos__Poss=Yes",
+      "ADJqua",
+      "ADJqua__Tense=Past|VerbForm=Part",
+      "ADJqua__Tense=Pres|VerbForm=Part",
+      "ADVgen",
+      "ADVgen.PROper",
+      "ADVgen__PronType=Ind",
+      "ADVgen__PronType=Prs,Rel",
+      "ADVgen__PronType=Rel",
+      "ADVint__PronType=Int",
+      "ADVneg",
+      "ADVneg.PROper__Polarity=Neg|PronType=Prs",
+      "ADVneg__Polarity=Neg",
+      "ADVsub",
+      "CONcoo",
+      "CONcoo__PronType=Prs,Rel",
+      "CONsub",
+      "CONsub.PROper",
+      "CONsub__PronType=Rel",
+      "DETcar__NumType=Card",
+      "DETdef__Definite=Def",
+      "DETdef__Definite=Def|PronType=Art",
+      "DETdef__PronType=Ind",
+      "DETdef__PronType=Prs",
+      "DETdem__PronType=Dem",
+      "DETdem__PronType=Prs",
+      "DETind__PronType=Ind",
+      "DETint__PronType=Int",
+      "DETndf__Definite=Ind",
+      "DETndf__Definite=Ind|PronType=Art",
+      "DETord",
+      "DETord__NumType=Ord",
+      "DETpos__Poss=Yes",
+      "DETrel__PronType=Rel",
+      "INJ",
+      "NOMcom",
+      "NOMcom__Morph=VFin",
+      "NOMcom__VerbForm=Inf",
+      "NOMpro",
+      "PONfbl",
+      "PONfrt",
+      "PONpdr",
+      "PONpga",
+      "PONpxx",
+      "PRE",
+      "PRE.DETdef__Definite=Def|PronType=Art",
+      "PRE.PROper",
+      "PRE.PROper__Definite=Def|PronType=Art",
+      "PRE__Morph=VFin",
+      "PRE__PronType=Dem",
+      "PREdetdef__PronType=Prs,Rel",
+      "PROadv",
+      "PROadv__PronType=Dem",
+      "PROcar",
+      "PROcar__NumType=Card",
+      "PROdem__PronType=Dem",
+      "PROdem__PronType=Prs,Rel",
+      "PROimp",
+      "PROimp__PronType=Prs",
+      "PROind",
+      "PROind__PronType=Ind",
+      "PROind__PronType=Rel",
+      "PROint__PronType=Int",
+      "PROord__NumType=Ord",
+      "PROper",
+      "PROper.PROper__PronType=Prs",
+      "PROper__Poss=Yes",
+      "PROper__PronType=Prs",
+      "PROpos__Poss=Yes",
+      "PROpos__Poss=Yes|PronType=Prs",
+      "PROrel",
+      "PROrel__PronType=Prs,Rel",
+      "PROrel__PronType=Rel",
+      "RED",
+      "VERcjg",
+      "VERcjg__VerbForm=Fin",
+      "VERcjg__VerbForm=Inf",
+      "VERinf__VerbForm=Inf",
+      "VERppa__Tense=Pres|VerbForm=Part",
+      "VERppe",
+      "VERppe__Tense=Past",
+      "VERppe__Tense=Past|VerbForm=Part",
+      "devenir__Tense=Past|VerbForm=Part",
+      "devenir__VerbForm=Fin",
+      "laisser__VerbForm=Fin",
+      "remanoir__VerbForm=Fin",
+      "ressembler__VerbForm=Fin",
+      "sembler__VerbForm=Fin"
+    ]
+  },
+  "pipeline":[
+    "transformer",
+    "parser",
+    "trainable_lemmatizer",
+    "tagger"
+  ],
+  "components":[
+    "transformer",
+    "parser",
+    "trainable_lemmatizer",
+    "tagger"
+  ],
+  "disabled":[
+  ],
+  "performance":{
+    "dep_uas":0.6967152383,
+    "dep_las":0.6162015312,
+    "dep_las_per_type":{
+      "advmod":{
+        "p":0.7226107226,
+        "r":0.6352459016,
+        "f":0.6761177754
+      },
+      "iobj":{
+        "p":0.6868686869,
+        "r":0.641509434,
+        "f":0.6634146341
+      },
+      "root":{
+        "p":0.7518248175,
+        "r":0.794344473,
+        "f":0.7725
+      },
+      "mark":{
+        "p":0.6597938144,
+        "r":0.5541125541,
+        "f":0.6023529412
+      },
+      "cc:nc":{
+        "p":0.8417721519,
+        "r":0.7430167598,
+        "f":0.7893175074
+      },
+      "expl":{
+        "p":0.3333333333,
+        "r":0.1136363636,
+        "f":0.1694915254
+      },
+      "nsubj":{
+        "p":0.7692307692,
+        "r":0.6068601583,
+        "f":0.6784660767
+      },
+      "case":{
+        "p":0.8333333333,
+        "r":0.7569721116,
+        "f":0.7933194154
+      },
+      "obl":{
+        "p":0.5814977974,
+        "r":0.4599303136,
+        "f":0.513618677
+      },
+      "ccomp":{
+        "p":0.55,
+        "r":0.4583333333,
+        "f":0.5
+      },
+      "obj":{
+        "p":0.6135458167,
+        "r":0.4207650273,
+        "f":0.4991896272
+      },
+      "aux":{
+        "p":0.7415730337,
+        "r":0.4888888889,
+        "f":0.5892857143
+      },
+      "det":{
+        "p":0.9161490683,
+        "r":0.8779761905,
+        "f":0.896656535
+      },
+      "acl":{
+        "p":0.1304347826,
+        "r":0.0588235294,
+        "f":0.0810810811
+      },
+      "xcomp":{
+        "p":0.3979591837,
+        "r":0.4875,
+        "f":0.4382022472
+      },
+      "advcl":{
+        "p":0.4606741573,
+        "r":0.3504273504,
+        "f":0.3980582524
+      },
+      "acl:relcl":{
+        "p":0.6923076923,
+        "r":0.4736842105,
+        "f":0.5625
+      },
+      "amod":{
+        "p":0.7721518987,
+        "r":0.5754716981,
+        "f":0.6594594595
+      },
+      "cc":{
+        "p":0.8558558559,
+        "r":0.7916666667,
+        "f":0.8225108225
+      },
+      "conj":{
+        "p":0.4358974359,
+        "r":0.3805970149,
+        "f":0.406374502
+      },
+      "flat":{
+        "p":0.8157894737,
+        "r":0.8611111111,
+        "f":0.8378378378
+      },
+      "appos":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
+      },
+      "case:det":{
+        "p":1.0,
+        "r":0.92,
+        "f":0.9583333333
+      },
+      "nmod":{
+        "p":0.3829787234,
+        "r":0.3214285714,
+        "f":0.3495145631
+      },
+      "cop":{
+        "p":0.4545454545,
+        "r":0.5,
+        "f":0.4761904762
+      },
+      "dislocated":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
+      },
+      "obl:advmod":{
+        "p":0.4705882353,
+        "r":0.32,
+        "f":0.380952381
+      },
+      "aux:pass":{
+        "p":0.25,
+        "r":0.1052631579,
+        "f":0.1481481481
+      },
+      "nummod":{
+        "p":0.6666666667,
+        "r":0.6666666667,
+        "f":0.6666666667
+      },
+      "discourse":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
+      },
+      "vocative":{
+        "p":0.3571428571,
+        "r":0.5555555556,
+        "f":0.4347826087
+      },
+      "dep":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
+      },
+      "parataxis":{
+        "p":0.5,
+        "r":0.4,
+        "f":0.4444444444
+      },
+      "csubj":{
+        "p":0.3333333333,
+        "r":0.25,
+        "f":0.2857142857
+      },
+      "nsubj:obj":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
+      }
+    },
+    "sents_p":0.7881548975,
+    "sents_r":0.8894601542,
+    "sents_f":0.8357487923,
+    "lemma_acc":0.8348421285,
+    "tag_acc":0.8626325088,
+    "transformer_loss":443.3810498194,
+    "parser_loss":68.8630388519,
+    "trainable_lemmatizer_loss":14.463111954,
+    "tagger_loss":35.0005259109
+  },
+  "requirements":[
+    "spacy-transformers>=1.3.3,<1.4.0"
+  ]
+}

parser/cfg ADDED Viewed

	@@ -0,0 +1,13 @@

+{
+  "moves":null,
+  "update_with_oracle_cut_size":100,
+  "multitasks":[
+  ],
+  "min_action_freq":30,
+  "learn_tokens":false,
+  "beam_width":1,
+  "beam_density":0.0,
+  "beam_update_prob":0.0,
+  "incorrect_spans_key":null
+}

parser/model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a3aabf523b69927d6f7324de7ce66f3cce46ea9fb116ec2af1a58642c5b571cb
+size 1113579

parser/moves ADDED Viewed

	@@ -0,0 +1 @@

+ ��moves��{"0":{"":23400},"1":{"":11949},"2":{"advmod":3010,"det":2815,"nsubj":2519,"case":2255,"obj":1853,"mark":1670,"obl":1423,"cc:nc":1402,"punct":1170,"cc":953,"aux":761,"iobj":728,"amod":474,"case:det":317,"expl":289,"advcl":246,"cop":238,"obl:advmod":230,"aux:pass":182,"xcomp":154,"vocative":123,"nummod":103,"parataxis":79,"obj||xcomp":63,"nmod||obj":55,"nmod":38,"acl":34,"dep":0},"3":{"punct":3823,"obl":1072,"conj":905,"obj":866,"advmod":795,"advcl":641,"nsubj":577,"acl:relcl":484,"xcomp":399,"ccomp":308,"nmod":302,"acl":248,"amod":228,"flat":161,"aux":152,"iobj":88,"cop":73,"acl:relcl||nsubj":63,"csubj":48,"acl:relcl||obj":45,"conj||obj":42,"appos":42,"acl||obj":39,"parataxis":36,"vocative":34,"conj||nsubj":33,"dep":0},"4":{"ROOT":3113}}�cfg��neg_key�

tagger/cfg ADDED Viewed

	@@ -0,0 +1,98 @@

+{
+  "label_smoothing":0.0,
+  "labels":[
+    "ADJcar__NumType=Card",
+    "ADJind__PronType=Ind",
+    "ADJord",
+    "ADJpos__Poss=Yes",
+    "ADJqua",
+    "ADJqua__Tense=Past|VerbForm=Part",
+    "ADJqua__Tense=Pres|VerbForm=Part",
+    "ADVgen",
+    "ADVgen.PROper",
+    "ADVgen__PronType=Ind",
+    "ADVgen__PronType=Prs,Rel",
+    "ADVgen__PronType=Rel",
+    "ADVint__PronType=Int",
+    "ADVneg",
+    "ADVneg.PROper__Polarity=Neg|PronType=Prs",
+    "ADVneg__Polarity=Neg",
+    "ADVsub",
+    "CONcoo",
+    "CONcoo__PronType=Prs,Rel",
+    "CONsub",
+    "CONsub.PROper",
+    "CONsub__PronType=Rel",
+    "DETcar__NumType=Card",
+    "DETdef__Definite=Def",
+    "DETdef__Definite=Def|PronType=Art",
+    "DETdef__PronType=Ind",
+    "DETdef__PronType=Prs",
+    "DETdem__PronType=Dem",
+    "DETdem__PronType=Prs",
+    "DETind__PronType=Ind",
+    "DETint__PronType=Int",
+    "DETndf__Definite=Ind",
+    "DETndf__Definite=Ind|PronType=Art",
+    "DETord",
+    "DETord__NumType=Ord",
+    "DETpos__Poss=Yes",
+    "DETrel__PronType=Rel",
+    "INJ",
+    "NOMcom",
+    "NOMcom__Morph=VFin",
+    "NOMcom__VerbForm=Inf",
+    "NOMpro",
+    "PONfbl",
+    "PONfrt",
+    "PONpdr",
+    "PONpga",
+    "PONpxx",
+    "PRE",
+    "PRE.DETdef__Definite=Def|PronType=Art",
+    "PRE.PROper",
+    "PRE.PROper__Definite=Def|PronType=Art",
+    "PRE__Morph=VFin",
+    "PRE__PronType=Dem",
+    "PREdetdef__PronType=Prs,Rel",
+    "PROadv",
+    "PROadv__PronType=Dem",
+    "PROcar",
+    "PROcar__NumType=Card",
+    "PROdem__PronType=Dem",
+    "PROdem__PronType=Prs,Rel",
+    "PROimp",
+    "PROimp__PronType=Prs",
+    "PROind",
+    "PROind__PronType=Ind",
+    "PROind__PronType=Rel",
+    "PROint__PronType=Int",
+    "PROord__NumType=Ord",
+    "PROper",
+    "PROper.PROper__PronType=Prs",
+    "PROper__Poss=Yes",
+    "PROper__PronType=Prs",
+    "PROpos__Poss=Yes",
+    "PROpos__Poss=Yes|PronType=Prs",
+    "PROrel",
+    "PROrel__PronType=Prs,Rel",
+    "PROrel__PronType=Rel",
+    "RED",
+    "VERcjg",
+    "VERcjg__VerbForm=Fin",
+    "VERcjg__VerbForm=Inf",
+    "VERinf__VerbForm=Inf",
+    "VERppa__Tense=Pres|VerbForm=Part",
+    "VERppe",
+    "VERppe__Tense=Past",
+    "VERppe__Tense=Past|VerbForm=Part",
+    "devenir__Tense=Past|VerbForm=Part",
+    "devenir__VerbForm=Fin",
+    "laisser__VerbForm=Fin",
+    "remanoir__VerbForm=Fin",
+    "ressembler__VerbForm=Fin",
+    "sembler__VerbForm=Fin"
+  ],
+  "neg_prefix":"!",
+  "overwrite":false
+}

tagger/model ADDED Viewed

Binary file (281 kB). View file

tokenizer ADDED Viewed

	@@ -0,0 +1,3 @@

+��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�
+��A�
+� ��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)/¯�°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�—�faster_heuristics�

trainable_lemmatizer/cfg ADDED Viewed

	@@ -0,0 +1,785 @@

+{
+  "labels":[
+    1,
+    3,
+    5,
+    6,
+    8,
+    11,
+    12,
+    14,
+    16,
+    20,
+    22,
+    24,
+    26,
+    28,
+    30,
+    34,
+    37,
+    40,
+    42,
+    43,
+    45,
+    47,
+    49,
+    52,
+    56,
+    58,
+    61,
+    64,
+    66,
+    68,
+    72,
+    73,
+    76,
+    80,
+    82,
+    84,
+    88,
+    89,
+    95,
+    96,
+    99,
+    101,
+    102,
+    104,
+    108,
+    109,
+    112,
+    114,
+    117,
+    120,
+    121,
+    123,
+    126,
+    127,
+    129,
+    131,
+    133,
+    138,
+    139,
+    141,
+    142,
+    145,
+    147,
+    151,
+    154,
+    155,
+    157,
+    160,
+    161,
+    162,
+    163,
+    166,
+    169,
+    171,
+    173,
+    174,
+    175,
+    177,
+    179,
+    181,
+    182,
+    183,
+    184,
+    185,
+    188,
+    190,
+    192,
+    193,
+    196,
+    198,
+    200,
+    202,
+    204,
+    205,
+    207,
+    209,
+    211,
+    213,
+    215,
+    217,
+    219,
+    222,
+    224,
+    226,
+    228,
+    229,
+    231,
+    234,
+    237,
+    238,
+    240,
+    242,
+    245,
+    247,
+    249,
+    252,
+    254,
+    257,
+    260,
+    261,
+    263,
+    264,
+    266,
+    270,
+    272,
+    274,
+    277,
+    278,
+    280,
+    282,
+    284,
+    285,
+    287,
+    289,
+    291,
+    294,
+    297,
+    300,
+    304,
+    306,
+    308,
+    309,
+    311,
+    314,
+    316,
+    318,
+    319,
+    322,
+    324,
+    327,
+    331,
+    334,
+    336,
+    339,
+    340,
+    344,
+    347,
+    348,
+    350,
+    352,
+    354,
+    356,
+    358,
+    359,
+    361,
+    363,
+    365,
+    367,
+    370,
+    373,
+    376,
+    377,
+    379,
+    380,
+    383,
+    385,
+    388,
+    389,
+    391,
+    393,
+    395,
+    396,
+    398,
+    399,
+    239,
+    401,
+    403,
+    406,
+    408,
+    412,
+    414,
+    416,
+    418,
+    419,
+    420,
+    421,
+    422,
+    424,
+    427,
+    428,
+    430,
+    434,
+    435,
+    437,
+    438,
+    439,
+    440,
+    442,
+    443,
+    445,
+    446,
+    447,
+    450,
+    451,
+    452,
+    455,
+    458,
+    459,
+    461,
+    463,
+    465,
+    466,
+    470,
+    472,
+    473,
+    475,
+    477,
+    479,
+    480,
+    483,
+    485,
+    487,
+    489,
+    490,
+    493,
+    495,
+    498,
+    503,
+    506,
+    507,
+    509,
+    512,
+    513,
+    514,
+    516,
+    519,
+    520,
+    521,
+    522,
+    524,
+    525,
+    526,
+    528,
+    531,
+    532,
+    533,
+    536,
+    538,
+    539,
+    542,
+    544,
+    547,
+    551,
+    553,
+    555,
+    557,
+    558,
+    561,
+    562,
+    564,
+    566,
+    568,
+    571,
+    575,
+    577,
+    578,
+    580,
+    581,
+    583,
+    584,
+    586,
+    588,
+    591,
+    593,
+    594,
+    596,
+    597,
+    598,
+    600,
+    602,
+    604,
+    607,
+    608,
+    610,
+    611,
+    613,
+    615,
+    617,
+    619,
+    621,
+    625,
+    627,
+    629,
+    631,
+    633,
+    635,
+    638,
+    640,
+    642,
+    644,
+    646,
+    648,
+    651,
+    654,
+    655,
+    657,
+    659,
+    661,
+    662,
+    664,
+    665,
+    668,
+    669,
+    670,
+    671,
+    674,
+    676,
+    679,
+    683,
+    686,
+    688,
+    691,
+    692,
+    693,
+    695,
+    697,
+    699,
+    700,
+    701,
+    702,
+    703,
+    704,
+    706,
+    708,
+    709,
+    710,
+    713,
+    714,
+    715,
+    716,
+    717,
+    719,
+    721,
+    722,
+    725,
+    727,
+    728,
+    729,
+    730,
+    732,
+    733,
+    735,
+    737,
+    739,
+    740,
+    741,
+    743,
+    746,
+    748,
+    751,
+    753,
+    755,
+    757,
+    759,
+    761,
+    763,
+    765,
+    768,
+    771,
+    773,
+    774,
+    775,
+    776,
+    777,
+    780,
+    782,
+    785,
+    786,
+    788,
+    790,
+    791,
+    794,
+    796,
+    799,
+    801,
+    802,
+    805,
+    808,
+    809,
+    812,
+    813,
+    815,
+    817,
+    820,
+    821,
+    823,
+    825,
+    827,
+    829,
+    830,
+    833,
+    834,
+    835,
+    838,
+    839,
+    841,
+    843,
+    846,
+    848,
+    850,
+    853,
+    857,
+    861,
+    863,
+    865,
+    866,
+    867,
+    870,
+    872,
+    873,
+    874,
+    875,
+    877,
+    879,
+    881,
+    883,
+    885,
+    887,
+    890,
+    891,
+    895,
+    897,
+    899,
+    901,
+    902,
+    903,
+    905,
+    907,
+    426,
+    910,
+    912,
+    913,
+    914,
+    917,
+    920,
+    921,
+    922,
+    923,
+    928,
+    930,
+    932,
+    935,
+    937,
+    938,
+    940,
+    942,
+    947,
+    949,
+    951,
+    952,
+    954,
+    957,
+    960,
+    962,
+    965,
+    969,
+    970,
+    972,
+    973,
+    974,
+    975,
+    977,
+    978,
+    979,
+    980,
+    982,
+    983,
+    984,
+    986,
+    988,
+    990,
+    991,
+    994,
+    997,
+    998,
+    999,
+    1002,
+    1003,
+    1004,
+    1006,
+    1009,
+    1013,
+    1015,
+    1016,
+    1017,
+    1020,
+    1021,
+    1023,
+    1024,
+    1027,
+    1030,
+    1031,
+    1033,
+    1036,
+    1037,
+    1040,
+    1042,
+    1044,
+    1046,
+    1047,
+    1048,
+    1050,
+    1051,
+    1054,
+    1057,
+    1060,
+    1061,
+    1064,
+    1067,
+    1068,
+    1069,
+    1071,
+    1072,
+    1073,
+    1077,
+    1078,
+    1080,
+    1082,
+    1085,
+    1086,
+    1088,
+    98,
+    1089,
+    1091,
+    1092,
+    1094,
+    1096,
+    1097,
+    1100,
+    1101,
+    1103,
+    1107,
+    1108,
+    1109,
+    1112,
+    1115,
+    1117,
+    1118,
+    1121,
+    1123,
+    1124,
+    1127,
+    1129,
+    1131,
+    1132,
+    1135,
+    1137,
+    1142,
+    1143,
+    1146,
+    1147,
+    1149,
+    1151,
+    1152,
+    1154,
+    1157,
+    1159,
+    1161,
+    1162,
+    1164,
+    1165,
+    1166,
+    1167,
+    1170,
+    1172,
+    1173,
+    1175,
+    1176,
+    1178,
+    798,
+    1181,
+    1182,
+    1184,
+    1185,
+    1186,
+    1188,
+    1189,
+    1191,
+    1193,
+    1195,
+    1198,
+    1201,
+    1203,
+    1206,
+    1208,
+    1209,
+    1211,
+    1213,
+    1215,
+    1216,
+    1217,
+    1218,
+    1219,
+    1222,
+    1223,
+    1224,
+    1227,
+    1228,
+    1230,
+    1231,
+    1232,
+    1233,
+    1234,
+    1236,
+    1237,
+    1239,
+    1242,
+    1245,
+    939,
+    1247,
+    1248,
+    1250,
+    1251,
+    1252,
+    1254,
+    1258,
+    1260,
+    1261,
+    1263,
+    1264,
+    1266,
+    1267,
+    1268,
+    1270,
+    1273,
+    1275,
+    1278,
+    1280,
+    1281,
+    1282,
+    1284,
+    1286,
+    1288,
+    1289,
+    1290,
+    1291,
+    1293,
+    1296,
+    1297,
+    1300,
+    1301,
+    1303,
+    1305,
+    1309,
+    1312,
+    1315,
+    1316,
+    1319,
+    326,
+    1321,
+    1323,
+    1325,
+    1327,
+    1329,
+    1331,
+    1333,
+    1335,
+    1337,
+    1338,
+    1339,
+    1340,
+    1342,
+    1344,
+    1345,
+    1347,
+    1348,
+    1350,
+    1351,
+    1352,
+    1353,
+    1355,
+    1356,
+    1358,
+    1360,
+    1362,
+    1364,
+    1367,
+    1368,
+    449,
+    1370,
+    1371,
+    1374,
+    1377,
+    1379,
+    1382,
+    819,
+    1384,
+    1387,
+    1389,
+    1391,
+    1393,
+    1396,
+    1398,
+    1399,
+    1401,
+    1404,
+    1407,
+    1408,
+    515,
+    1410,
+    1411,
+    1412,
+    1415,
+    1416,
+    1418,
+    1420,
+    1421,
+    1423,
+    1424,
+    1426,
+    1428,
+    1429,
+    1430,
+    1433,
+    1436,
+    1437,
+    1441,
+    1442,
+    1443,
+    1445,
+    1446,
+    1449,
+    1451,
+    1454,
+    1456,
+    1457,
+    1460,
+    1461,
+    1463,
+    1465,
+    1467,
+    1470,
+    1471,
+    1472,
+    1475,
+    1477,
+    1479,
+    1481,
+    1483,
+    1485,
+    1486,
+    1488,
+    1490,
+    1493,
+    1496,
+    1497,
+    1500,
+    1502,
+    1504,
+    1507,
+    1508,
+    1510,
+    1512,
+    1514,
+    1515,
+    1518,
+    1521,
+    1087,
+    1522,
+    1523,
+    1524
+  ]
+}

trainable_lemmatizer/model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:2b24951bd57adcd3ca5b777dac8d62757afda48c4895fbbc4068a55722995eae
+size 2403009

trainable_lemmatizer/trees ADDED Viewed

Binary file (186 kB). View file

transformer/cfg ADDED Viewed

	@@ -0,0 +1,3 @@

+{
+  "max_batch_items":4096
+}

transformer/model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f6795240341b836093604880478d598fa39014ac10290374f83319e2728b3d2d
+size 509231398

vocab/key2row ADDED Viewed

	@@ -0,0 +1 @@


1	+ �

vocab/lookups.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
+size 1

vocab/strings.json ADDED Viewed

The diff for this file is too large to render. See raw diff

vocab/vectors ADDED Viewed

Binary file (128 Bytes). View file

vocab/vectors.cfg ADDED Viewed

	@@ -0,0 +1,3 @@

+{
+  "mode":"default"
+}

xx_fro_sigtyp_trf-any-py3-none-any.whl ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:086c6fadd962f1c4f2dc2135fd236eacf536a864ce45679da7a0331e365bf057
+size 469524730