Update spaCy pipeline

.gitattributes

@@ -33,3 +33,6 @@ 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
+id_core_news_sm-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+parser/model filter=lfs diff=lfs merge=lfs -text
+tok2vec/model filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,103 @@
+---
+tags:
+- spacy
+- token-classification
+language:
+- id
+model-index:
+- name: id_core_news_sm
+  results:
+  - task:
+      name: TAG
+      type: token-classification
+    metrics:
+    - name: TAG (XPOS) Accuracy
+      type: accuracy
+      value: 0.9051536414
+  - task:
+      name: POS
+      type: token-classification
+    metrics:
+    - name: POS (UPOS) Accuracy
+      type: accuracy
+      value: 0.9125297415
+  - task:
+      name: MORPH
+      type: token-classification
+    metrics:
+    - name: Morph (UFeats) Accuracy
+      type: accuracy
+      value: 0.9296115526
+  - task:
+      name: LEMMA
+      type: token-classification
+    metrics:
+    - name: Lemma Accuracy
+      type: accuracy
+      value: 0.9369920335
+  - task:
+      name: UNLABELED_DEPENDENCIES
+      type: token-classification
+    metrics:
+    - name: Unlabeled Attachment Score (UAS)
+      type: f_score
+      value: 0.7753785754
+  - task:
+      name: LABELED_DEPENDENCIES
+      type: token-classification
+    metrics:
+    - name: Labeled Attachment Score (LAS)
+      type: f_score
+      value: 0.6871555348
+  - task:
+      name: SENTS
+      type: token-classification
+    metrics:
+    - name: Sentences F-Score
+      type: f_score
+      value: 0.857881137
+---
+| Feature | Description |
+| --- | --- |
+| **Name** | `id_core_news_sm` |
+| **Version** | `0.0.0` |
+| **spaCy** | `>=3.7.2,<3.8.0` |
+| **Default Pipeline** | `tok2vec`, `tagger`, `morphologizer`, `trainable_lemmatizer`, `parser` |
+| **Components** | `tok2vec`, `tagger`, `morphologizer`, `trainable_lemmatizer`, `parser` |
+| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
+| **Sources** | n/a |
+| **License** | n/a |
+| **Author** | [n/a]() |
+
+### Label Scheme
+
+<details>
+
+<summary>View label scheme (166 labels for 3 components)</summary>
+
+| Component | Labels |
+| --- | --- |
+| **`tagger`** | `APP`, `ASP`, `ASP+PS3`, `ASS`, `B--`, `B--+PS3`, `CC-`, `CCONJ`, `CD-`, `CO-`, `D--`, `D--+PS3`, `F--`, `F--+PS2`, `G--`, `G--+PS3`, `H--`, `I--`, `M--`, `M--+PS3`, `NOUN`, `NPD`, `NSD`, `NSD+PS3`, `NSF`, `NSM`, `NUM`, `O--`, `PP1`, `PP2`, `PP3`, `PROPN`, `PS1`, `PS1+VSA`, `PS2`, `PS3`, `R--`, `R--+PS3`, `S--`, `SYM`, `T--`, `VERB`, `VPA`, `VSA`, `VSA+PS2`, `VSA+PS3`, `VSP`, `W--`, `X--`, `Z--` |
+| **`morphologizer`** | `POS=PROPN`, `POS=AUX`, `Definite=Ind\|POS=DET\|PronType=Art`, `Number=Sing\|POS=NOUN`, `POS=PRON\|PronType=Rel`, `Mood=Ind\|POS=VERB\|Voice=Pass`, `POS=ADP`, `POS=PUNCT`, `POS=NOUN`, `POS=ADV`, `POS=CCONJ`, `POS=SCONJ`, `Mood=Ind\|POS=VERB\|Voice=Act`, `POS=VERB`, `POS=DET\|PronType=Tot`, `Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `POS=PRON\|PronType=Prs\|Reflex=Yes`, `POS=DET\|PronType=Dem`, `NumType=Card\|POS=NUM`, `POS=ADJ`, `Number=Plur\|POS=DET\|PronType=Ind`, `NumType=Card\|POS=NUM\|PronType=Tot`, `POS=PART\|Polarity=Neg`, `POS=PRON\|PronType=Int`, `NumType=Ord\|POS=ADJ`, `POS=PART`, `POS=PRON\|PronType=Dem`, `POS=DET\|PronType=Ind`, `Number=Plur\|POS=NOUN`, `Number=Sing\|POS=PRON\|Person=1\|Polite=Form\|PronType=Prs`, `POS=ADV\|PronType=Int`, `Clusivity=In\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `Definite=Def\|POS=DET\|PronType=Art`, `POS=SYM`, `Degree=Sup\|POS=ADJ`, `POS=INTJ`, `Number=Sing\|POS=PRON\|Person=2\|Polite=Infm\|PronType=Prs`, `POS=ADV\|PronType=Ind`, `Number=Sing\|POS=PRON\|Person=3\|Polite=Form\|PronType=Prs`, `Number=Sing\|POS=PRON\|Person=1\|Polite=Infm\|PronType=Prs`, `Number=Sing\|POS=PRON\|PronType=Ind`, `POS=VERB\|Voice=Act`, `POS=DET\|PronType=Emp`, `POS=VERB\|Voice=Pass`, `POS=ADV\|PronType=Dem`, `POS=NOUN\|Typo=Yes`, `POS=ADP\|Typo=Yes`, `Number=Plur\|POS=PRON\|PronType=Ind`, `POS=VERB\|Typo=Yes\|Voice=Pass`, `POS=X`, `POS=PRON\|PronType=Tot`, `POS=SCONJ\|Typo=Yes`, `Number=Plur\|POS=PRON\|Person=2\|Polite=Infm\|PronType=Prs`, `NumType=Card\|POS=NUM\|Typo=Yes`, `Clusivity=Ex\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `Number=Sing\|POS=PRON\|Person=2\|Polite=Form\|PronType=Prs`, `Foreign=Yes\|POS=X`, `POS=ADV\|PronType=Rel`, `Mood=Imp\|POS=VERB\|Voice=Act`, `Number=Sing\|POS=NOUN\|Typo=Yes`, `POS=PROPN\|Typo=Yes`, `POS=DET`, `Number=Sing\|POS=DET\|PronType=Ind`, `POS=DET\|PronType=Ind\|Typo=Yes`, `Abbr=Yes\|POS=DET\|PronType=Dem`, `POS=PRON\|PronType=Ind`, `POS=VERB\|Typo=Yes`, `Abbr=Yes\|POS=PROPN`, `Abbr=Yes\|POS=PRON\|PronType=Rel`, `Number=Plur\|POS=PRON\|PronType=Int`, `Abbr=Yes\|POS=PART\|Polarity=Neg`, `POS=ADV\|PronType=Tot`, `Abbr=Yes\|POS=ADV`, `POS=ADV\|Typo=Yes`, `POS=X\|Typo=Yes`, `Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `POS=ADV\|PronType=Int\|Typo=Yes`, `NumType=Ord\|POS=ADJ\|Typo=Yes` |
+| **`parser`** | `ROOT`, `acl`, `acl:relcl`, `advcl`, `advmod`, `advmod:emph`, `amod`, `appos`, `aux`, `case`, `case:adv`, `cc`, `ccomp`, `compound`, `conj`, `cop`, `dep`, `det`, `fixed`, `flat`, `flat:foreign`, `flat:name`, `mark`, `nmod`, `nmod:lmod`, `nmod:poss`, `nmod:tmod`, `nsubj`, `nsubj:pass`, `nummod`, `obj`, `obl`, `obl:agent`, `obl:tmod`, `parataxis`, `punct`, `xcomp` |
+
+</details>
+
+### Accuracy
+
+| Type | Score |
+| --- | --- |
+| `TAG_ACC` | 90.52 |
+| `POS_ACC` | 91.25 |
+| `MORPH_ACC` | 92.96 |
+| `LEMMA_ACC` | 93.70 |
+| `DEP_UAS` | 77.54 |
+| `DEP_LAS` | 68.72 |
+| `SENTS_P` | 82.72 |
+| `SENTS_R` | 89.09 |
+| `SENTS_F` | 85.79 |
+| `TOK2VEC_LOSS` | 756743.38 |
+| `TAGGER_LOSS` | 73614.38 |
+| `MORPHOLOGIZER_LOSS` | 155689.33 |
+| `TRAINABLE_LEMMATIZER_LOSS` | 35033.93 |
+| `PARSER_LOSS` | 1037857.66 |

config.cfg

@@ -0,0 +1,205 @@
+[paths]
+train = "./id_gsd-ud-train.spacy"
+dev = "./id_gsd-ud-dev.spacy"
+vectors = null
+init_tok2vec = null
+
+[system]
+gpu_allocator = null
+seed = 0
+
+[nlp]
+lang = "id"
+pipeline = ["tok2vec","tagger","morphologizer","trainable_lemmatizer","parser"]
+batch_size = 1000
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
+vectors = {"@vectors":"spacy.Vectors.v1"}
+
+[components]
+
+[components.morphologizer]
+factory = "morphologizer"
+extend = false
+label_smoothing = 0.05
+overwrite = true
+scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
+
+[components.morphologizer.model]
+@architectures = "spacy.Tagger.v2"
+nO = null
+normalize = false
+
+[components.morphologizer.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode.width}
+upstream = "*"
+
+[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 = true
+nO = null
+
+[components.parser.model.tok2vec]
+@architectures = "spacy.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode.width}
+upstream = "*"
+
+[components.tagger]
+factory = "tagger"
+label_smoothing = 0.05
+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.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode.width}
+upstream = "*"
+
+[components.tok2vec]
+factory = "tok2vec"
+
+[components.tok2vec.model]
+@architectures = "spacy.Tok2Vec.v2"
+
+[components.tok2vec.model.embed]
+@architectures = "spacy.MultiHashEmbed.v2"
+width = ${components.tok2vec.model.encode.width}
+attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
+rows = [5000,1000,2500,2500]
+include_static_vectors = true
+
+[components.tok2vec.model.encode]
+@architectures = "spacy.MaxoutWindowEncoder.v2"
+width = 256
+depth = 8
+window_size = 1
+maxout_pieces = 3
+
+[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.Tok2VecListener.v1"
+width = ${components.tok2vec.model.encode.width}
+upstream = "*"
+
+[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]
+dev_corpus = "corpora.dev"
+train_corpus = "corpora.train"
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
+dropout = 0.1
+accumulate_gradient = 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_words.v1"
+discard_oversize = false
+tolerance = 0.2
+get_length = null
+
+[training.batcher.size]
+@schedules = "compounding.v1"
+start = 100
+stop = 1000
+compound = 1.001
+t = 0.0
+
+[training.logger]
+@loggers = "spacy.ConsoleLogger.v1"
+progress_bar = false
+
+[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
+learn_rate = 0.001
+
+[training.score_weights]
+tag_acc = 0.26
+pos_acc = 0.12
+morph_acc = 0.12
+morph_per_feat = null
+lemma_acc = 0.26
+dep_uas = 0.12
+dep_las = 0.12
+dep_las_per_type = null
+sents_p = null
+sents_r = null
+sents_f = 0.0
+
+[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]

id_core_news_sm-any-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a5e1c6460adf7bbaa1cbf52f3ef60fbd73a088fff0128bebefe8f7cde3158c5
+size 34069443

meta.json

@@ -0,0 +1,515 @@
+{
+  "lang":"id",
+  "name":"core_news_sm",
+  "version":"0.0.0",
+  "description":"",
+  "author":"",
+  "email":"",
+  "url":"",
+  "license":"",
+  "spacy_version":">=3.7.2,<3.8.0",
+  "spacy_git_version":"a89eae928",
+  "vectors":{
+    "width":0,
+    "vectors":0,
+    "keys":0,
+    "name":null
+  },
+  "labels":{
+    "tok2vec":[
+
+    ],
+    "tagger":[
+      "APP",
+      "ASP",
+      "ASP+PS3",
+      "ASS",
+      "B--",
+      "B--+PS3",
+      "CC-",
+      "CCONJ",
+      "CD-",
+      "CO-",
+      "D--",
+      "D--+PS3",
+      "F--",
+      "F--+PS2",
+      "G--",
+      "G--+PS3",
+      "H--",
+      "I--",
+      "M--",
+      "M--+PS3",
+      "NOUN",
+      "NPD",
+      "NSD",
+      "NSD+PS3",
+      "NSF",
+      "NSM",
+      "NUM",
+      "O--",
+      "PP1",
+      "PP2",
+      "PP3",
+      "PROPN",
+      "PS1",
+      "PS1+VSA",
+      "PS2",
+      "PS3",
+      "R--",
+      "R--+PS3",
+      "S--",
+      "SYM",
+      "T--",
+      "VERB",
+      "VPA",
+      "VSA",
+      "VSA+PS2",
+      "VSA+PS3",
+      "VSP",
+      "W--",
+      "X--",
+      "Z--"
+    ],
+    "morphologizer":[
+      "POS=PROPN",
+      "POS=AUX",
+      "Definite=Ind|POS=DET|PronType=Art",
+      "Number=Sing|POS=NOUN",
+      "POS=PRON|PronType=Rel",
+      "Mood=Ind|POS=VERB|Voice=Pass",
+      "POS=ADP",
+      "POS=PUNCT",
+      "POS=NOUN",
+      "POS=ADV",
+      "POS=CCONJ",
+      "POS=SCONJ",
+      "Mood=Ind|POS=VERB|Voice=Act",
+      "POS=VERB",
+      "POS=DET|PronType=Tot",
+      "Number=Sing|POS=PRON|Person=3|PronType=Prs",
+      "Number=Plur|POS=PRON|Person=3|PronType=Prs",
+      "POS=PRON|PronType=Prs|Reflex=Yes",
+      "POS=DET|PronType=Dem",
+      "NumType=Card|POS=NUM",
+      "POS=ADJ",
+      "Number=Plur|POS=DET|PronType=Ind",
+      "NumType=Card|POS=NUM|PronType=Tot",
+      "POS=PART|Polarity=Neg",
+      "POS=PRON|PronType=Int",
+      "NumType=Ord|POS=ADJ",
+      "POS=PART",
+      "POS=PRON|PronType=Dem",
+      "POS=DET|PronType=Ind",
+      "Number=Plur|POS=NOUN",
+      "Number=Sing|POS=PRON|Person=1|Polite=Form|PronType=Prs",
+      "POS=ADV|PronType=Int",
+      "Clusivity=In|Number=Plur|POS=PRON|Person=1|PronType=Prs",
+      "Definite=Def|POS=DET|PronType=Art",
+      "POS=SYM",
+      "Degree=Sup|POS=ADJ",
+      "POS=INTJ",
+      "Number=Sing|POS=PRON|Person=2|Polite=Infm|PronType=Prs",
+      "POS=ADV|PronType=Ind",
+      "Number=Sing|POS=PRON|Person=3|Polite=Form|PronType=Prs",
+      "Number=Sing|POS=PRON|Person=1|Polite=Infm|PronType=Prs",
+      "Number=Sing|POS=PRON|PronType=Ind",
+      "POS=VERB|Voice=Act",
+      "POS=DET|PronType=Emp",
+      "POS=VERB|Voice=Pass",
+      "POS=ADV|PronType=Dem",
+      "POS=NOUN|Typo=Yes",
+      "POS=ADP|Typo=Yes",
+      "Number=Plur|POS=PRON|PronType=Ind",
+      "POS=VERB|Typo=Yes|Voice=Pass",
+      "POS=X",
+      "POS=PRON|PronType=Tot",
+      "POS=SCONJ|Typo=Yes",
+      "Number=Plur|POS=PRON|Person=2|Polite=Infm|PronType=Prs",
+      "NumType=Card|POS=NUM|Typo=Yes",
+      "Clusivity=Ex|Number=Plur|POS=PRON|Person=1|PronType=Prs",
+      "Number=Sing|POS=PRON|Person=2|Polite=Form|PronType=Prs",
+      "Foreign=Yes|POS=X",
+      "POS=ADV|PronType=Rel",
+      "Mood=Imp|POS=VERB|Voice=Act",
+      "Number=Sing|POS=NOUN|Typo=Yes",
+      "POS=PROPN|Typo=Yes",
+      "POS=DET",
+      "Number=Sing|POS=DET|PronType=Ind",
+      "POS=DET|PronType=Ind|Typo=Yes",
+      "Abbr=Yes|POS=DET|PronType=Dem",
+      "POS=PRON|PronType=Ind",
+      "POS=VERB|Typo=Yes",
+      "Abbr=Yes|POS=PROPN",
+      "Abbr=Yes|POS=PRON|PronType=Rel",
+      "Number=Plur|POS=PRON|PronType=Int",
+      "Abbr=Yes|POS=PART|Polarity=Neg",
+      "POS=ADV|PronType=Tot",
+      "Abbr=Yes|POS=ADV",
+      "POS=ADV|Typo=Yes",
+      "POS=X|Typo=Yes",
+      "Number=Sing|POS=PRON|Person=2|PronType=Prs",
+      "POS=ADV|PronType=Int|Typo=Yes",
+      "NumType=Ord|POS=ADJ|Typo=Yes"
+    ],
+    "parser":[
+      "ROOT",
+      "acl",
+      "acl:relcl",
+      "advcl",
+      "advmod",
+      "advmod:emph",
+      "amod",
+      "appos",
+      "aux",
+      "case",
+      "case:adv",
+      "cc",
+      "ccomp",
+      "compound",
+      "conj",
+      "cop",
+      "dep",
+      "det",
+      "fixed",
+      "flat",
+      "flat:foreign",
+      "flat:name",
+      "mark",
+      "nmod",
+      "nmod:lmod",
+      "nmod:poss",
+      "nmod:tmod",
+      "nsubj",
+      "nsubj:pass",
+      "nummod",
+      "obj",
+      "obl",
+      "obl:agent",
+      "obl:tmod",
+      "parataxis",
+      "punct",
+      "xcomp"
+    ]
+  },
+  "pipeline":[
+    "tok2vec",
+    "tagger",
+    "morphologizer",
+    "trainable_lemmatizer",
+    "parser"
+  ],
+  "components":[
+    "tok2vec",
+    "tagger",
+    "morphologizer",
+    "trainable_lemmatizer",
+    "parser"
+  ],
+  "disabled":[
+
+  ],
+  "performance":{
+    "tag_acc":0.9051536414,
+    "pos_acc":0.9125297415,
+    "morph_acc":0.9296115526,
+    "morph_per_feat":{
+      "Number":{
+        "p":0.9799159271,
+        "r":0.8237141735,
+        "f":0.8950511945
+      },
+      "Mood":{
+        "p":0.997098646,
+        "r":0.9246636771,
+        "f":0.959516054
+      },
+      "Voice":{
+        "p":0.9942084942,
+        "r":0.9221128021,
+        "f":0.9568044589
+      },
+      "PronType":{
+        "p":0.9915662651,
+        "r":0.7786187323,
+        "f":0.8722840488
+      },
+      "Polarity":{
+        "p":1.0,
+        "r":0.862745098,
+        "f":0.9263157895
+      },
+      "Person":{
+        "p":1.0,
+        "r":0.4039735099,
+        "f":0.5754716981
+      },
+      "NumType":{
+        "p":0.9952606635,
+        "r":0.9480812641,
+        "f":0.9710982659
+      },
+      "Typo":{
+        "p":1.0,
+        "r":0.4,
+        "f":0.5714285714
+      },
+      "Definite":{
+        "p":0.9838709677,
+        "r":0.7922077922,
+        "f":0.8776978417
+      },
+      "Polite":{
+        "p":1.0,
+        "r":0.71875,
+        "f":0.8363636364
+      },
+      "Reflex":{
+        "p":1.0,
+        "r":0.5,
+        "f":0.6666666667
+      },
+      "Degree":{
+        "p":0.9375,
+        "r":0.8823529412,
+        "f":0.9090909091
+      },
+      "Foreign":{
+        "p":1.0,
+        "r":0.0625,
+        "f":0.1176470588
+      },
+      "Clusivity":{
+        "p":1.0,
+        "r":1.0,
+        "f":1.0
+      },
+      "Abbr":{
+        "p":1.0,
+        "r":0.2,
+        "f":0.3333333333
+      }
+    },
+    "lemma_acc":0.9369920335,
+    "dep_uas":0.7753785754,
+    "dep_las":0.6871555348,
+    "dep_las_per_type":{
+      "nsubj":{
+        "p":0.7731092437,
+        "r":0.7459459459,
+        "f":0.7592847318
+      },
+      "compound":{
+        "p":0.6962676963,
+        "r":0.6874205845,
+        "f":0.6918158568
+      },
+      "root":{
+        "p":0.7585616438,
+        "r":0.7924865832,
+        "f":0.7751531059
+      },
+      "obj":{
+        "p":0.7978142077,
+        "r":0.7630662021,
+        "f":0.7800534283
+      },
+      "case":{
+        "p":0.9049295775,
+        "r":0.8877374784,
+        "f":0.8962510898
+      },
+      "obl":{
+        "p":0.6753246753,
+        "r":0.6409861325,
+        "f":0.6577075099
+      },
+      "amod":{
+        "p":0.6421568627,
+        "r":0.568329718,
+        "f":0.6029919448
+      },
+      "conj":{
+        "p":0.5394736842,
+        "r":0.5354477612,
+        "f":0.5374531835
+      },
+      "cc":{
+        "p":0.8705882353,
+        "r":0.8433048433,
+        "f":0.8567293777
+      },
+      "acl:relcl":{
+        "p":0.7086614173,
+        "r":0.6428571429,
+        "f":0.6741573034
+      },
+      "flat:name":{
+        "p":0.7908571429,
+        "r":0.8218527316,
+        "f":0.8060570763
+      },
+      "advmod":{
+        "p":0.7546174142,
+        "r":0.7132169576,
+        "f":0.7333333333
+      },
+      "nmod":{
+        "p":0.6468085106,
+        "r":0.5435041716,
+        "f":0.5906735751
+      },
+      "nsubj:pass":{
+        "p":0.698630137,
+        "r":0.7083333333,
+        "f":0.7034482759
+      },
+      "det":{
+        "p":0.8745980707,
+        "r":0.7661971831,
+        "f":0.8168168168
+      },
+      "aux":{
+        "p":0.9064748201,
+        "r":0.9402985075,
+        "f":0.9230769231
+      },
+      "nmod:poss":{
+        "p":0.5714285714,
+        "r":0.0727272727,
+        "f":0.1290322581
+      },
+      "dep":{
+        "p":0.0967741935,
+        "r":0.0535714286,
+        "f":0.0689655172
+      },
+      "mark":{
+        "p":0.8391959799,
+        "r":0.7076271186,
+        "f":0.767816092
+      },
+      "cop":{
+        "p":0.9607843137,
+        "r":0.9423076923,
+        "f":0.9514563107
+      },
+      "acl":{
+        "p":0.2297297297,
+        "r":0.3035714286,
+        "f":0.2615384615
+      },
+      "nummod":{
+        "p":0.7834224599,
+        "r":0.7855227882,
+        "f":0.7844712182
+      },
+      "appos":{
+        "p":0.5615384615,
+        "r":0.553030303,
+        "f":0.5572519084
+      },
+      "xcomp":{
+        "p":0.3630573248,
+        "r":0.456,
+        "f":0.4042553191
+      },
+      "ccomp":{
+        "p":0.4,
+        "r":0.0408163265,
+        "f":0.0740740741
+      },
+      "obl:tmod":{
+        "p":0.6551724138,
+        "r":0.6229508197,
+        "f":0.6386554622
+      },
+      "advcl":{
+        "p":0.2831858407,
+        "r":0.2269503546,
+        "f":0.2519685039
+      },
+      "advmod:emph":{
+        "p":0.6666666667,
+        "r":0.0434782609,
+        "f":0.0816326531
+      },
+      "case:adv":{
+        "p":0.6666666667,
+        "r":0.4615384615,
+        "f":0.5454545455
+      },
+      "obl:agent":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
+      },
+      "flat":{
+        "p":0.5185185185,
+        "r":0.3255813953,
+        "f":0.4
+      },
+      "parataxis":{
+        "p":0.25,
+        "r":0.1020408163,
+        "f":0.1449275362
+      },
+      "nmod:lmod":{
+        "p":0.8333333333,
+        "r":0.3846153846,
+        "f":0.5263157895
+      },
+      "flat:foreign":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
+      },
+      "nmod:tmod":{
+        "p":0.4,
+        "r":0.3636363636,
+        "f":0.380952381
+      },
+      "iobj":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
+      },
+      "csubj":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
+      },
+      "fixed":{
+        "p":0.5555555556,
+        "r":0.3846153846,
+        "f":0.4545454545
+      },
+      "discourse":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
+      },
+      "cc:preconj":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
+      },
+      "compound:a":{
+        "p":0.0,
+        "r":0.0,
+        "f":0.0
+      }
+    },
+    "sents_p":0.8272425249,
+    "sents_r":0.8908765653,
+    "sents_f":0.857881137,
+    "tok2vec_loss":7567.4337583379,
+    "tagger_loss":736.1438090745,
+    "morphologizer_loss":1556.8932885677,
+    "trainable_lemmatizer_loss":350.339323577,
+    "parser_loss":10378.5765946195
+  },
+  "requirements":[
+
+  ]
+}

morphologizer/cfg

@@ -0,0 +1,167 @@
+{
+  "extend":false,
+  "label_smoothing":0.05,
+  "labels_morph":{
+    "POS=PROPN":"",
+    "POS=AUX":"",
+    "Definite=Ind|POS=DET|PronType=Art":"Definite=Ind|PronType=Art",
+    "Number=Sing|POS=NOUN":"Number=Sing",
+    "POS=PRON|PronType=Rel":"PronType=Rel",
+    "Mood=Ind|POS=VERB|Voice=Pass":"Mood=Ind|Voice=Pass",
+    "POS=ADP":"",
+    "POS=PUNCT":"",
+    "POS=NOUN":"",
+    "POS=ADV":"",
+    "POS=CCONJ":"",
+    "POS=SCONJ":"",
+    "Mood=Ind|POS=VERB|Voice=Act":"Mood=Ind|Voice=Act",
+    "POS=VERB":"",
+    "POS=DET|PronType=Tot":"PronType=Tot",
+    "Number=Sing|POS=PRON|Person=3|PronType=Prs":"Number=Sing|Person=3|PronType=Prs",
+    "Number=Plur|POS=PRON|Person=3|PronType=Prs":"Number=Plur|Person=3|PronType=Prs",
+    "POS=PRON|PronType=Prs|Reflex=Yes":"PronType=Prs|Reflex=Yes",
+    "POS=DET|PronType=Dem":"PronType=Dem",
+    "NumType=Card|POS=NUM":"NumType=Card",
+    "POS=ADJ":"",
+    "Number=Plur|POS=DET|PronType=Ind":"Number=Plur|PronType=Ind",
+    "NumType=Card|POS=NUM|PronType=Tot":"NumType=Card|PronType=Tot",
+    "POS=PART|Polarity=Neg":"Polarity=Neg",
+    "POS=PRON|PronType=Int":"PronType=Int",
+    "NumType=Ord|POS=ADJ":"NumType=Ord",
+    "POS=PART":"",
+    "POS=PRON|PronType=Dem":"PronType=Dem",
+    "POS=DET|PronType=Ind":"PronType=Ind",
+    "Number=Plur|POS=NOUN":"Number=Plur",
+    "Number=Sing|POS=PRON|Person=1|Polite=Form|PronType=Prs":"Number=Sing|Person=1|Polite=Form|PronType=Prs",
+    "POS=ADV|PronType=Int":"PronType=Int",
+    "Clusivity=In|Number=Plur|POS=PRON|Person=1|PronType=Prs":"Clusivity=In|Number=Plur|Person=1|PronType=Prs",
+    "Definite=Def|POS=DET|PronType=Art":"Definite=Def|PronType=Art",
+    "POS=SYM":"",
+    "Degree=Sup|POS=ADJ":"Degree=Sup",
+    "POS=INTJ":"",
+    "Number=Sing|POS=PRON|Person=2|Polite=Infm|PronType=Prs":"Number=Sing|Person=2|Polite=Infm|PronType=Prs",
+    "POS=ADV|PronType=Ind":"PronType=Ind",
+    "Number=Sing|POS=PRON|Person=3|Polite=Form|PronType=Prs":"Number=Sing|Person=3|Polite=Form|PronType=Prs",
+    "Number=Sing|POS=PRON|Person=1|Polite=Infm|PronType=Prs":"Number=Sing|Person=1|Polite=Infm|PronType=Prs",
+    "Number=Sing|POS=PRON|PronType=Ind":"Number=Sing|PronType=Ind",
+    "POS=VERB|Voice=Act":"Voice=Act",
+    "POS=DET|PronType=Emp":"PronType=Emp",
+    "POS=VERB|Voice=Pass":"Voice=Pass",
+    "POS=ADV|PronType=Dem":"PronType=Dem",
+    "POS=NOUN|Typo=Yes":"Typo=Yes",
+    "POS=ADP|Typo=Yes":"Typo=Yes",
+    "Number=Plur|POS=PRON|PronType=Ind":"Number=Plur|PronType=Ind",
+    "POS=VERB|Typo=Yes|Voice=Pass":"Typo=Yes|Voice=Pass",
+    "POS=X":"",
+    "POS=PRON|PronType=Tot":"PronType=Tot",
+    "POS=SCONJ|Typo=Yes":"Typo=Yes",
+    "Number=Plur|POS=PRON|Person=2|Polite=Infm|PronType=Prs":"Number=Plur|Person=2|Polite=Infm|PronType=Prs",
+    "NumType=Card|POS=NUM|Typo=Yes":"NumType=Card|Typo=Yes",
+    "Clusivity=Ex|Number=Plur|POS=PRON|Person=1|PronType=Prs":"Clusivity=Ex|Number=Plur|Person=1|PronType=Prs",
+    "Number=Sing|POS=PRON|Person=2|Polite=Form|PronType=Prs":"Number=Sing|Person=2|Polite=Form|PronType=Prs",
+    "Foreign=Yes|POS=X":"Foreign=Yes",
+    "POS=ADV|PronType=Rel":"PronType=Rel",
+    "Mood=Imp|POS=VERB|Voice=Act":"Mood=Imp|Voice=Act",
+    "Number=Sing|POS=NOUN|Typo=Yes":"Number=Sing|Typo=Yes",
+    "POS=PROPN|Typo=Yes":"Typo=Yes",
+    "POS=DET":"",
+    "Number=Sing|POS=DET|PronType=Ind":"Number=Sing|PronType=Ind",
+    "POS=DET|PronType=Ind|Typo=Yes":"PronType=Ind|Typo=Yes",
+    "Abbr=Yes|POS=DET|PronType=Dem":"Abbr=Yes|PronType=Dem",
+    "POS=PRON|PronType=Ind":"PronType=Ind",
+    "POS=VERB|Typo=Yes":"Typo=Yes",
+    "Abbr=Yes|POS=PROPN":"Abbr=Yes",
+    "Abbr=Yes|POS=PRON|PronType=Rel":"Abbr=Yes|PronType=Rel",
+    "Number=Plur|POS=PRON|PronType=Int":"Number=Plur|PronType=Int",
+    "Abbr=Yes|POS=PART|Polarity=Neg":"Abbr=Yes|Polarity=Neg",
+    "POS=ADV|PronType=Tot":"PronType=Tot",
+    "Abbr=Yes|POS=ADV":"Abbr=Yes",
+    "POS=ADV|Typo=Yes":"Typo=Yes",
+    "POS=X|Typo=Yes":"Typo=Yes",
+    "Number=Sing|POS=PRON|Person=2|PronType=Prs":"Number=Sing|Person=2|PronType=Prs",
+    "POS=ADV|PronType=Int|Typo=Yes":"PronType=Int|Typo=Yes",
+    "NumType=Ord|POS=ADJ|Typo=Yes":"NumType=Ord|Typo=Yes"
+  },
+  "labels_pos":{
+    "POS=PROPN":96,
+    "POS=AUX":87,
+    "Definite=Ind|POS=DET|PronType=Art":90,
+    "Number=Sing|POS=NOUN":92,
+    "POS=PRON|PronType=Rel":95,
+    "Mood=Ind|POS=VERB|Voice=Pass":100,
+    "POS=ADP":85,
+    "POS=PUNCT":97,
+    "POS=NOUN":92,
+    "POS=ADV":86,
+    "POS=CCONJ":89,
+    "POS=SCONJ":98,
+    "Mood=Ind|POS=VERB|Voice=Act":100,
+    "POS=VERB":100,
+    "POS=DET|PronType=Tot":90,
+    "Number=Sing|POS=PRON|Person=3|PronType=Prs":95,
+    "Number=Plur|POS=PRON|Person=3|PronType=Prs":95,
+    "POS=PRON|PronType=Prs|Reflex=Yes":95,
+    "POS=DET|PronType=Dem":90,
+    "NumType=Card|POS=NUM":93,
+    "POS=ADJ":84,
+    "Number=Plur|POS=DET|PronType=Ind":90,
+    "NumType=Card|POS=NUM|PronType=Tot":93,
+    "POS=PART|Polarity=Neg":94,
+    "POS=PRON|PronType=Int":95,
+    "NumType=Ord|POS=ADJ":84,
+    "POS=PART":94,
+    "POS=PRON|PronType=Dem":95,
+    "POS=DET|PronType=Ind":90,
+    "Number=Plur|POS=NOUN":92,
+    "Number=Sing|POS=PRON|Person=1|Polite=Form|PronType=Prs":95,
+    "POS=ADV|PronType=Int":86,
+    "Clusivity=In|Number=Plur|POS=PRON|Person=1|PronType=Prs":95,
+    "Definite=Def|POS=DET|PronType=Art":90,
+    "POS=SYM":99,
+    "Degree=Sup|POS=ADJ":84,
+    "POS=INTJ":91,
+    "Number=Sing|POS=PRON|Person=2|Polite=Infm|PronType=Prs":95,
+    "POS=ADV|PronType=Ind":86,
+    "Number=Sing|POS=PRON|Person=3|Polite=Form|PronType=Prs":95,
+    "Number=Sing|POS=PRON|Person=1|Polite=Infm|PronType=Prs":95,
+    "Number=Sing|POS=PRON|PronType=Ind":95,
+    "POS=VERB|Voice=Act":100,
+    "POS=DET|PronType=Emp":90,
+    "POS=VERB|Voice=Pass":100,
+    "POS=ADV|PronType=Dem":86,
+    "POS=NOUN|Typo=Yes":92,
+    "POS=ADP|Typo=Yes":85,
+    "Number=Plur|POS=PRON|PronType=Ind":95,
+    "POS=VERB|Typo=Yes|Voice=Pass":100,
+    "POS=X":101,
+    "POS=PRON|PronType=Tot":95,
+    "POS=SCONJ|Typo=Yes":98,
+    "Number=Plur|POS=PRON|Person=2|Polite=Infm|PronType=Prs":95,
+    "NumType=Card|POS=NUM|Typo=Yes":93,
+    "Clusivity=Ex|Number=Plur|POS=PRON|Person=1|PronType=Prs":95,
+    "Number=Sing|POS=PRON|Person=2|Polite=Form|PronType=Prs":95,
+    "Foreign=Yes|POS=X":101,
+    "POS=ADV|PronType=Rel":86,
+    "Mood=Imp|POS=VERB|Voice=Act":100,
+    "Number=Sing|POS=NOUN|Typo=Yes":92,
+    "POS=PROPN|Typo=Yes":96,
+    "POS=DET":90,
+    "Number=Sing|POS=DET|PronType=Ind":90,
+    "POS=DET|PronType=Ind|Typo=Yes":90,
+    "Abbr=Yes|POS=DET|PronType=Dem":90,
+    "POS=PRON|PronType=Ind":95,
+    "POS=VERB|Typo=Yes":100,
+    "Abbr=Yes|POS=PROPN":96,
+    "Abbr=Yes|POS=PRON|PronType=Rel":95,
+    "Number=Plur|POS=PRON|PronType=Int":95,
+    "Abbr=Yes|POS=PART|Polarity=Neg":94,
+    "POS=ADV|PronType=Tot":86,
+    "Abbr=Yes|POS=ADV":86,
+    "POS=ADV|Typo=Yes":86,
+    "POS=X|Typo=Yes":101,
+    "Number=Sing|POS=PRON|Person=2|PronType=Prs":95,
+    "POS=ADV|PronType=Int|Typo=Yes":86,
+    "NumType=Ord|POS=ADJ|Typo=Yes":84
+  },
+  "overwrite":true
+}

parser/cfg

@@ -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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16da2082353eec368fedc44e473009c51f5ee03be764493d78146bf2977b6645
+size 1750016

parser/moves

@@ -0,0 +1 @@
+��moves�{"0":{"":36809},"1":{"":56313},"2":{"case":8690,"punct":6049,"nsubj":5534,"advmod":2999,"cc":2690,"nsubj:pass":1726,"mark":1658,"nummod":1525,"det":1313,"aux":921,"obl":852,"cop":845,"amod":398,"obj":251,"advcl":250,"nmod":217,"obl:tmod":211,"compound":124,"xcomp":112,"case:adv":72,"advmod:emph":57,"acl":51,"parataxis":42,"dep":41,"nmod:lmod":37},"3":{"punct":7872,"flat:name":6453,"nmod":6282,"compound":5703,"obj":4488,"obl":3927,"conj":3876,"amod":2949,"acl:relcl":2164,"appos":2119,"det":1663,"nummod":1602,"nmod:poss":1139,"xcomp":1014,"acl":923,"advcl":798,"advmod":400,"dep":359,"ccomp":336,"obl:tmod":319,"flat":305,"advmod:emph":292,"parataxis":274,"fixed":237,"case":174,"cc":134,"nmod:tmod":83,"nsubj":74,"mark":70,"obl:agent":45,"flat:foreign":41,"nsubj:pass":40},"4":{"ROOT":4482}}�cfg��neg_key�

tagger/cfg

@@ -0,0 +1,57 @@
+{
+  "label_smoothing":0.05,
+  "labels":[
+    "APP",
+    "ASP",
+    "ASP+PS3",
+    "ASS",
+    "B--",
+    "B--+PS3",
+    "CC-",
+    "CCONJ",
+    "CD-",
+    "CO-",
+    "D--",
+    "D--+PS3",
+    "F--",
+    "F--+PS2",
+    "G--",
+    "G--+PS3",
+    "H--",
+    "I--",
+    "M--",
+    "M--+PS3",
+    "NOUN",
+    "NPD",
+    "NSD",
+    "NSD+PS3",
+    "NSF",
+    "NSM",
+    "NUM",
+    "O--",
+    "PP1",
+    "PP2",
+    "PP3",
+    "PROPN",
+    "PS1",
+    "PS1+VSA",
+    "PS2",
+    "PS3",
+    "R--",
+    "R--+PS3",
+    "S--",
+    "SYM",
+    "T--",
+    "VERB",
+    "VPA",
+    "VSA",
+    "VSA+PS2",
+    "VSA+PS3",
+    "VSP",
+    "W--",
+    "X--",
+    "Z--"
+  ],
+  "neg_prefix":"!",
+  "overwrite":false
+}

tok2vec/cfg

@@ -0,0 +1,3 @@
+{
+
+}

tok2vec/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b0c198567f39ac6146d7716317c079ec7977eeac835e0e6d3fb926c4076d8e6
+size 34126801

trainable_lemmatizer/cfg

@@ -0,0 +1,337 @@
+{
+  "labels":[
+    1,
+    2,
+    4,
+    6,
+    9,
+    11,
+    13,
+    15,
+    17,
+    19,
+    21,
+    22,
+    24,
+    26,
+    28,
+    31,
+    33,
+    36,
+    38,
+    39,
+    40,
+    42,
+    44,
+    46,
+    47,
+    49,
+    51,
+    53,
+    55,
+    57,
+    59,
+    61,
+    63,
+    65,
+    67,
+    68,
+    70,
+    71,
+    73,
+    75,
+    77,
+    64,
+    79,
+    80,
+    83,
+    84,
+    85,
+    87,
+    89,
+    91,
+    93,
+    95,
+    97,
+    98,
+    100,
+    101,
+    102,
+    105,
+    107,
+    108,
+    110,
+    112,
+    114,
+    115,
+    117,
+    118,
+    121,
+    123,
+    124,
+    125,
+    127,
+    128,
+    129,
+    131,
+    18,
+    133,
+    135,
+    137,
+    138,
+    139,
+    141,
+    142,
+    144,
+    145,
+    147,
+    149,
+    151,
+    152,
+    153,
+    154,
+    156,
+    157,
+    159,
+    161,
+    162,
+    164,
+    165,
+    167,
+    168,
+    170,
+    172,
+    174,
+    176,
+    178,
+    179,
+    182,
+    183,
+    185,
+    187,
+    188,
+    190,
+    191,
+    193,
+    194,
+    195,
+    58,
+    197,
+    199,
+    200,
+    201,
+    202,
+    204,
+    206,
+    208,
+    210,
+    211,
+    212,
+    213,
+    214,
+    37,
+    216,
+    217,
+    220,
+    221,
+    76,
+    223,
+    224,
+    225,
+    226,
+    227,
+    228,
+    229,
+    231,
+    234,
+    235,
+    237,
+    239,
+    240,
+    241,
+    243,
+    245,
+    246,
+    248,
+    249,
+    251,
+    253,
+    255,
+    257,
+    259,
+    262,
+    263,
+    264,
+    266,
+    267,
+    268,
+    270,
+    271,
+    56,
+    273,
+    274,
+    275,
+    276,
+    278,
+    279,
+    280,
+    282,
+    283,
+    284,
+    286,
+    287,
+    288,
+    289,
+    291,
+    293,
+    295,
+    297,
+    298,
+    299,
+    16,
+    300,
+    301,
+    302,
+    304,
+    305,
+    307,
+    309,
+    109,
+    310,
+    311,
+    313,
+    315,
+    317,
+    318,
+    66,
+    319,
+    62,
+    321,
+    322,
+    323,
+    324,
+    326,
+    328,
+    330,
+    331,
+    333,
+    334,
+    60,
+    50,
+    336,
+    337,
+    338,
+    339,
+    340,
+    341,
+    342,
+    343,
+    345,
+    346,
+    209,
+    348,
+    349,
+    350,
+    351,
+    352,
+    354,
+    356,
+    358,
+    359,
+    360,
+    361,
+    0,
+    362,
+    363,
+    365,
+    367,
+    369,
+    371,
+    372,
+    373,
+    375,
+    377,
+    378,
+    381,
+    382,
+    69,
+    383,
+    386,
+    387,
+    389,
+    390,
+    391,
+    392,
+    393,
+    394,
+    396,
+    397,
+    399,
+    400,
+    401,
+    402,
+    403,
+    404,
+    405,
+    407,
+    408,
+    409,
+    411,
+    413,
+    414,
+    416,
+    418,
+    419,
+    420,
+    421,
+    422,
+    423,
+    424,
+    425,
+    426,
+    427,
+    429,
+    431,
+    432,
+    435,
+    436,
+    437,
+    438,
+    439,
+    440,
+    441,
+    443,
+    444,
+    446,
+    448,
+    449,
+    450,
+    452,
+    453,
+    455,
+    457,
+    459,
+    460,
+    461,
+    462,
+    463,
+    464,
+    466,
+    468,
+    92,
+    469,
+    470,
+    472,
+    474,
+    475,
+    476,
+    477,
+    478,
+    480,
+    482,
+    483,
+    484,
+    485,
+    486
+  ]
+}

vocab/key2row

@@ -0,0 +1 @@
+�

vocab/lookups.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
+size 1

vocab/vectors.cfg

@@ -0,0 +1,3 @@
+{
+  "mode":"default"
+}