Hugging Face's logo

explosion
/
af_udv25_afrikaansafribooms_trf

Token Classification
spaCy
Afrikaans
Eval Results
Model card Files
xet
Community
Adriane Boyd commited on
Commit
cbfa96e
·
1 Parent(s): 4f5bd8d

Add af_udv25_afrikaansafribooms_trf-0.0.1

Browse files
Files changed (28) hide show
  1. .gitattributes +5 -0
  2. LICENSE.txt +4 -0
  3. README.md +108 -0
  4. af_udv25_afrikaansafribooms_trf-any-py3-none-any.whl +3 -0
  5. config.cfg +254 -0
  6. experimental_char_ner_tokenizer/cfg +13 -0
  7. experimental_char_ner_tokenizer/model +3 -0
  8. experimental_char_ner_tokenizer/moves +1 -0
  9. experimental_edit_tree_lemmatizer/cfg +275 -0
  10. experimental_edit_tree_lemmatizer/model +3 -0
  11. experimental_edit_tree_lemmatizer/trees +0 -0
  12. meta.json +735 -0
  13. morphologizer/cfg +130 -0
  14. morphologizer/model +3 -0
  15. parser/cfg +13 -0
  16. parser/model +3 -0
  17. parser/moves +1 -0
  18. senter/cfg +3 -0
  19. senter/model +3 -0
  20. tagger/cfg +101 -0
  21. tagger/model +3 -0
  22. transformer/cfg +3 -0
  23. transformer/model +3 -0
  24. vocab/key2row +1 -0
  25. vocab/lookups.bin +3 -0
  26. vocab/strings.json +3 -0
  27. vocab/vectors +3 -0
  28. vocab/vectors.cfg +3 -0
.gitattributes CHANGED
@@ -25,3 +25,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ *.whl filter=lfs diff=lfs merge=lfs -text
29
+ *.npz filter=lfs diff=lfs merge=lfs -text
30
+ *strings.json filter=lfs diff=lfs merge=lfs -text
31
+ vectors filter=lfs diff=lfs merge=lfs -text
32
+ model filter=lfs diff=lfs merge=lfs -text
LICENSE.txt ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ The treebank is licensed under the Creative Commons License Attribution-ShareAlike 4.0 International.
2
+
3
+ The complete license text is available at:
4
+ http://creativecommons.org/licenses/by-sa/4.0/legalcode
README.md ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - spacy
4
+ - token-classification
5
+ language:
6
+ - af
7
+ license: cc-by-sa-4.0
8
+ model-index:
9
+ - name: af_udv25_afrikaansafribooms_trf
10
+ results:
11
+ - task:
12
+ name: TAG
13
+ type: token-classification
14
+ metrics:
15
+ - name: TAG (XPOS) Accuracy
16
+ type: accuracy
17
+ value: 0.9601278917
18
+ - task:
19
+ name: POS
20
+ type: token-classification
21
+ metrics:
22
+ - name: POS (UPOS) Accuracy
23
+ type: accuracy
24
+ value: 0.9852374236
25
+ - task:
26
+ name: MORPH
27
+ type: token-classification
28
+ metrics:
29
+ - name: Morph (UFeats) Accuracy
30
+ type: accuracy
31
+ value: 0.9751739703
32
+ - task:
33
+ name: LEMMA
34
+ type: token-classification
35
+ metrics:
36
+ - name: Lemma Accuracy
37
+ type: accuracy
38
+ value: 0.9786593964
39
+ - task:
40
+ name: UNLABELED_DEPENDENCIES
41
+ type: token-classification
42
+ metrics:
43
+ - name: Unlabeled Attachment Score (UAS)
44
+ type: f_score
45
+ value: 0.9078427294
46
+ - task:
47
+ name: LABELED_DEPENDENCIES
48
+ type: token-classification
49
+ metrics:
50
+ - name: Labeled Attachment Score (LAS)
51
+ type: f_score
52
+ value: 0.8749739963
53
+ - task:
54
+ name: SENTS
55
+ type: token-classification
56
+ metrics:
57
+ - name: Sentences F-Score
58
+ type: f_score
59
+ value: 1.0
60
+ ---
61
+ UD v2.5 benchmarking pipeline for UD_Afrikaans-AfriBooms
62
+
63
+ | Feature | Description |
64
+ | --- | --- |
65
+ | **Name** | `af_udv25_afrikaansafribooms_trf` |
66
+ | **Version** | `0.0.1` |
67
+ | **spaCy** | `>=3.2.1,<3.3.0` |
68
+ | **Default Pipeline** | `experimental_char_ner_tokenizer`, `transformer`, `tagger`, `morphologizer`, `parser`, `experimental_edit_tree_lemmatizer` |
69
+ | **Components** | `experimental_char_ner_tokenizer`, `transformer`, `senter`, `tagger`, `morphologizer`, `parser`, `experimental_edit_tree_lemmatizer` |
70
+ | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
71
+ | **Sources** | [Universal Dependencies v2.5](https://lindat.mff.cuni.cz/repository/xmlui/handle/11234/1-3105) (Zeman, Daniel; et al.) |
72
+ | **License** | `CC BY-SA 4.0` |
73
+ | **Author** | [Explosion](https://explosion.ai) |
74
+
75
+ ### Label Scheme
76
+
77
+ <details>
78
+
79
+ <summary>View label scheme (455 labels for 6 components)</summary>
80
+
81
+ | Component | Labels |
82
+ | --- | --- |
83
+ | **`experimental_char_ner_tokenizer`** | `TOKEN` |
84
+ | **`senter`** | `I`, `S` |
85
+ | **`tagger`** | `AOA`, `AOP`, `ASA`, `ASP`, `AVA`, `AVP`, `BO`, `BS`, `BV`, `KN`, `KO`, `LB`, `LO`, `NA`, `NEE`, `NM`, `NME`, `NSE`, `NSED`, `NSM`, `PA`, `PB`, `PDHEB`, `PDHEDP`, `PDHENP`, `PDHEW`, `PDMB`, `PDMP`, `PDMW`, `PDOENP`, `PDOEW`, `PDVEB`, `PDVEDP`, `PDVENP`, `PDVEW`, `PEEB`, `PEEDP`, `PEENP`, `PEMB`, `PEMP`, `PEMW`, `PO`, `PTEB`, `PTEDP`, `PTENP`, `PTEW`, `PTMP`, `PV`, `PW`, `RA`, `RK`, `RL`, `RO`, `RS`, `RSF`, `RV`, `RWD`, `SVS`, `THAB`, `THAO`, `THBB`, `THBO`, `THNB`, `THPB`, `THPO`, `TRAB`, `TRAO`, `TRBB`, `UPB`, `UPD`, `UPI`, `UPO`, `UPS`, `UPV`, `UPW`, `UXD`, `VTHOG`, `VTHOK`, `VTHOO`, `VTHOV`, `VTHSG`, `VTHSO`, `VTUOA`, `VTUOM`, `VTUOP`, `VUOT`, `VVHOG`, `VVHOK`, `VVHOO`, `VVUOM`, `VVUOP`, `ZE`, `ZM`, `ZPL`, `ZPR` |
86
+ | **`morphologizer`** | `Definite=Def\|POS=DET\|PronType=Art`, `Number=Sing\|POS=NOUN`, `AdpType=Prep\|POS=ADP`, `AdjType=Attr\|Case=Nom\|Degree=Pos\|POS=ADJ`, `Number=Plur\|POS=NOUN`, `POS=AUX\|Tense=Pres\|VerbForm=Fin,Inf\|VerbType=Cop`, `Definite=Ind\|POS=DET\|PronType=Art`, `POS=NUM`, `POS=PART\|PartType=Inf`, `POS=VERB\|Subcat=Tran\|Tense=Pres\|VerbForm=Fin,Inf`, `POS=PRON\|PronType=Rel`, `POS=AUX\|Tense=Pres\|VerbForm=Fin,Inf\|VerbType=Pas`, `POS=PUNCT`, `POS=CCONJ`, `POS=SCONJ`, `POS=VERB\|Subcat=Intr\|Tense=Pres\|VerbForm=Fin,Inf`, `POS=VERB\|Subcat=Intr\|Tense=Past\|VerbForm=Part`, `POS=AUX\|Tense=Past\|VerbForm=Fin\|VerbType=Pas`, `Degree=Pos\|POS=ADV`, `POS=AUX\|Tense=Pres\|VerbForm=Fin,Inf\|VerbType=Mod`, `POS=DET\|PronType=Ind`, `POS=X`, `Number=Sing\|POS=PROPN`, `POS=PRON\|PronType=Ind`, `POS=PART\|PartType=Neg`, `POS=VERB\|Subcat=Tran\|Tense=Past\|VerbForm=Part`, `AdjType=Pred\|Case=Nom\|Degree=Pos\|POS=ADJ`, `POS=DET\|PronType=Dem`, `Degree=Cmp\|POS=ADV`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `POS=SYM`, `Case=Acc,Nom\|Number=Plur\|POS=PRON\|Person=1\|PronType=Prs`, `POS=PART\|PartType=Gen`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `Number=Sing\|POS=PRON\|Person=2\|PronType=Prs\|Reflex=Yes`, `Degree=Sup\|POS=ADV`, `Degree=Dim\|Number=Sing\|POS=NOUN`, `Number=Sing\|POS=PRON\|Person=2\|Poss=Yes\|PronType=Prs`, `POS=PRON\|PronType=Int`, `Number=Plur\|POS=PRON\|Person=1\|Poss=Yes\|PronType=Prs`, `Number=Sing\|POS=PRON\|Person=3\|PronType=Prs\|Reflex=Yes`, `Number=Plur\|POS=PRON\|Person=3\|Poss=Yes\|PronType=Prs`, `AdjType=Attr\|Case=Nom\|Degree=Sup\|POS=ADJ`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=2\|PronType=Prs`, `AdjType=Pred\|Case=Nom\|Degree=Cmp\|POS=ADJ`, `POS=VERB\|Subcat=Prep\|Tense=Pres\|VerbForm=Fin,Inf`, `POS=AUX\|Tense=Pres\|VerbForm=Fin,Inf\|VerbType=Aux`, `Number=Sing\|POS=PRON\|Person=3\|Poss=Yes\|PronType=Prs`, `POS=PRON\|PronType=Rcp`, `POS=AUX\|Tense=Past\|VerbForm=Fin\|VerbType=Mod`, `Case=Acc,Nom\|Number=Plur\|POS=PRON\|Person=3\|PronType=Prs`, `POS=AUX\|Tense=Past\|VerbForm=Fin\|VerbType=Cop`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=3\|PronType=Prs`, `Case=Nom\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `Number=Sing\|POS=PRON\|Person=1\|Poss=Yes\|PronType=Prs`, `Case=Acc,Nom\|Number=Plur\|POS=PRON\|Person=2\|PronType=Prs`, `Number=Plur\|POS=PRON\|Person=3\|PronType=Prs\|Reflex=Yes`, `AdjType=Attr\|Case=Nom\|Degree=Cmp\|POS=ADJ`, `Number=Plur\|POS=PRON\|Person=1\|PronType=Prs\|Reflex=Yes`, `Case=Acc\|Number=Sing\|POS=PRON\|Person=1\|PronType=Prs`, `AdjType=Pred\|Case=Nom\|Degree=Sup\|POS=ADJ` |
87
+ | **`parser`** | `ROOT`, `advmod`, `amod`, `appos`, `aux`, `aux:pass`, `case`, `cc`, `ccomp`, `compound:prt`, `conj`, `cop`, `dep`, `det`, `flat`, `iobj`, `mark`, `nmod`, `nsubj`, `nsubj:pass`, `nummod`, `obj`, `obl`, `punct`, `xcomp` |
88
+ | **`experimental_edit_tree_lemmatizer`** | `1`, `2`, `4`, `7`, `8`, `10`, `12`, `14`, `16`, `18`, `21`, `24`, `26`, `28`, `31`, `32`, `34`, `37`, `39`, `40`, `42`, `44`, `46`, `47`, `49`, `51`, `53`, `54`, `56`, `57`, `58`, `59`, `61`, `64`, `66`, `68`, `69`, `72`, `74`, `75`, `77`, `78`, `81`, `83`, `84`, `85`, `86`, `87`, `90`, `92`, `94`, `96`, `99`, `101`, `103`, `105`, `108`, `110`, `113`, `116`, `117`, `118`, `121`, `123`, `124`, `125`, `127`, `128`, `129`, `133`, `136`, `138`, `141`, `143`, `145`, `147`, `151`, `153`, `154`, `156`, `158`, `159`, `160`, `162`, `164`, `165`, `167`, `168`, `170`, `172`, `174`, `176`, `178`, `179`, `180`, `181`, `183`, `185`, `189`, `190`, `191`, `192`, `194`, `195`, `197`, `198`, `201`, `202`, `203`, `204`, `206`, `207`, `209`, `213`, `214`, `216`, `217`, `218`, `220`, `221`, `222`, `223`, `225`, `226`, `228`, `229`, `231`, `233`, `234`, `236`, `238`, `240`, `241`, `244`, `247`, `248`, `249`, `250`, `252`, `253`, `255`, `256`, `257`, `258`, `261`, `262`, `263`, `265`, `267`, `269`, `270`, `271`, `273`, `275`, `276`, `278`, `279`, `281`, `283`, `285`, `287`, `289`, `291`, `294`, `296`, `297`, `298`, `299`, `300`, `301`, `302`, `303`, `305`, `306`, `307`, `309`, `310`, `311`, `313`, `314`, `315`, `317`, `320`, `321`, `323`, `325`, `326`, `327`, `328`, `329`, `330`, `332`, `333`, `335`, `336`, `337`, `338`, `339`, `340`, `341`, `343`, `344`, `347`, `348`, `349`, `351`, `353`, `355`, `357`, `359`, `360`, `361`, `362`, `365`, `366`, `367`, `369`, `371`, `373`, `374`, `375`, `377`, `379`, `381`, `383`, `386`, `388`, `390`, `392`, `393`, `395`, `397`, `398`, `400`, `401`, `402`, `403`, `405`, `406`, `408`, `409`, `411`, `412`, `414`, `417`, `215`, `418`, `419`, `420`, `421`, `422`, `424`, `425`, `426`, `427`, `429`, `431`, `432`, `433`, `434`, `436`, `438`, `439`, `440`, `442`, `443`, `444`, `447`, `449`, `450`, `452` |
89
+
90
+ </details>
91
+
92
+ ### Accuracy
93
+
94
+ | Type | Score |
95
+ | --- | --- |
96
+ | `TOKEN_F` | 99.92 |
97
+ | `TOKEN_P` | 99.89 |
98
+ | `TOKEN_R` | 99.94 |
99
+ | `TOKEN_ACC` | 100.00 |
100
+ | `SENTS_F` | 100.00 |
101
+ | `SENTS_P` | 100.00 |
102
+ | `SENTS_R` | 100.00 |
103
+ | `TAG_ACC` | 96.01 |
104
+ | `POS_ACC` | 98.52 |
105
+ | `MORPH_ACC` | 97.52 |
106
+ | `DEP_UAS` | 90.78 |
107
+ | `DEP_LAS` | 87.50 |
108
+ | `LEMMA_ACC` | 97.87 |
af_udv25_afrikaansafribooms_trf-any-py3-none-any.whl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c162c324d3bd14b68e43091b3b54cd8a4a688592678f4957b3123971eecd2b3
3
+ size 842552429
config.cfg ADDED
@@ -0,0 +1,254 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [paths]
2
+ train = "corpus/UD_Afrikaans-AfriBooms/train.spacy"
3
+ dev = "corpus/UD_Afrikaans-AfriBooms/dev.spacy"
4
+ vectors = null
5
+ init_tok2vec = null
6
+ tokenizer_source = "training/UD_Afrikaans-AfriBooms/tokenizer/model-best"
7
+ transformer_source = "training/UD_Afrikaans-AfriBooms/transformer/model-best"
8
+
9
+ [system]
10
+ gpu_allocator = "pytorch"
11
+ seed = 0
12
+
13
+ [nlp]
14
+ lang = "af"
15
+ pipeline = ["experimental_char_ner_tokenizer","transformer","senter","tagger","morphologizer","parser","experimental_edit_tree_lemmatizer"]
16
+ batch_size = 64
17
+ disabled = ["senter"]
18
+ before_creation = null
19
+ after_creation = null
20
+ after_pipeline_creation = null
21
+ tokenizer = {"@tokenizers":"spacy-experimental.char_pretokenizer.v1"}
22
+
23
+ [components]
24
+
25
+ [components.experimental_char_ner_tokenizer]
26
+ factory = "experimental_char_ner_tokenizer"
27
+ scorer = {"@scorers":"spacy-experimental.tokenizer_scorer.v1"}
28
+
29
+ [components.experimental_char_ner_tokenizer.model]
30
+ @architectures = "spacy.TransitionBasedParser.v2"
31
+ state_type = "ner"
32
+ extra_state_tokens = false
33
+ hidden_width = 64
34
+ maxout_pieces = 2
35
+ use_upper = true
36
+ nO = null
37
+
38
+ [components.experimental_char_ner_tokenizer.model.tok2vec]
39
+ @architectures = "spacy.Tok2Vec.v2"
40
+
41
+ [components.experimental_char_ner_tokenizer.model.tok2vec.embed]
42
+ @architectures = "spacy.MultiHashEmbed.v2"
43
+ width = 128
44
+ attrs = ["ORTH","LOWER","IS_DIGIT","IS_ALPHA","IS_SPACE","IS_PUNCT"]
45
+ rows = [1000,500,50,50,50,50]
46
+ include_static_vectors = false
47
+
48
+ [components.experimental_char_ner_tokenizer.model.tok2vec.encode]
49
+ @architectures = "spacy.MaxoutWindowEncoder.v2"
50
+ width = 128
51
+ depth = 4
52
+ window_size = 4
53
+ maxout_pieces = 2
54
+
55
+ [components.experimental_edit_tree_lemmatizer]
56
+ factory = "experimental_edit_tree_lemmatizer"
57
+ backoff = "orth"
58
+ min_tree_freq = 1
59
+ overwrite = false
60
+ scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
61
+ top_k = 1
62
+
63
+ [components.experimental_edit_tree_lemmatizer.model]
64
+ @architectures = "spacy.Tagger.v1"
65
+ nO = null
66
+
67
+ [components.experimental_edit_tree_lemmatizer.model.tok2vec]
68
+ @architectures = "spacy-transformers.TransformerListener.v1"
69
+ grad_factor = 1.0
70
+ upstream = "transformer"
71
+ pooling = {"@layers":"reduce_mean.v1"}
72
+
73
+ [components.morphologizer]
74
+ factory = "morphologizer"
75
+ extend = false
76
+ overwrite = false
77
+ scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
78
+
79
+ [components.morphologizer.model]
80
+ @architectures = "spacy.Tagger.v1"
81
+ nO = null
82
+
83
+ [components.morphologizer.model.tok2vec]
84
+ @architectures = "spacy-transformers.TransformerListener.v1"
85
+ grad_factor = 1.0
86
+ upstream = "transformer"
87
+ pooling = {"@layers":"reduce_mean.v1"}
88
+
89
+ [components.parser]
90
+ factory = "parser"
91
+ learn_tokens = false
92
+ min_action_freq = 5
93
+ moves = null
94
+ scorer = {"@scorers":"spacy.parser_scorer.v1"}
95
+ update_with_oracle_cut_size = 100
96
+
97
+ [components.parser.model]
98
+ @architectures = "spacy.TransitionBasedParser.v2"
99
+ state_type = "parser"
100
+ extra_state_tokens = false
101
+ hidden_width = 64
102
+ maxout_pieces = 3
103
+ use_upper = false
104
+ nO = null
105
+
106
+ [components.parser.model.tok2vec]
107
+ @architectures = "spacy-transformers.TransformerListener.v1"
108
+ grad_factor = 1.0
109
+ upstream = "transformer"
110
+ pooling = {"@layers":"reduce_mean.v1"}
111
+
112
+ [components.senter]
113
+ factory = "senter"
114
+ overwrite = false
115
+ scorer = {"@scorers":"spacy.senter_scorer.v1"}
116
+
117
+ [components.senter.model]
118
+ @architectures = "spacy.Tagger.v1"
119
+ nO = null
120
+
121
+ [components.senter.model.tok2vec]
122
+ @architectures = "spacy-transformers.TransformerListener.v1"
123
+ grad_factor = 1.0
124
+ upstream = "transformer"
125
+ pooling = {"@layers":"reduce_mean.v1"}
126
+
127
+ [components.tagger]
128
+ factory = "tagger"
129
+ neg_prefix = "!"
130
+ overwrite = false
131
+ scorer = {"@scorers":"spacy.tagger_scorer.v1"}
132
+
133
+ [components.tagger.model]
134
+ @architectures = "spacy.Tagger.v1"
135
+ nO = null
136
+
137
+ [components.tagger.model.tok2vec]
138
+ @architectures = "spacy-transformers.TransformerListener.v1"
139
+ grad_factor = 1.0
140
+ upstream = "transformer"
141
+ pooling = {"@layers":"reduce_mean.v1"}
142
+
143
+ [components.transformer]
144
+ factory = "transformer"
145
+ max_batch_items = 4096
146
+ set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
147
+
148
+ [components.transformer.model]
149
+ @architectures = "spacy-transformers.TransformerModel.v3"
150
+ name = "xlm-roberta-base"
151
+ mixed_precision = true
152
+
153
+ [components.transformer.model.get_spans]
154
+ @span_getters = "spacy-transformers.strided_spans.v1"
155
+ window = 128
156
+ stride = 96
157
+
158
+ [components.transformer.model.grad_scaler_config]
159
+
160
+ [components.transformer.model.tokenizer_config]
161
+ use_fast = true
162
+
163
+ [components.transformer.model.transformer_config]
164
+
165
+ [corpora]
166
+
167
+ [corpora.dev]
168
+ @readers = "spacy.Corpus.v1"
169
+ path = ${paths.dev}
170
+ max_length = 0
171
+ gold_preproc = false
172
+ limit = 0
173
+ augmenter = null
174
+
175
+ [corpora.train]
176
+ @readers = "spacy.Corpus.v1"
177
+ path = ${paths.train}
178
+ max_length = 0
179
+ gold_preproc = false
180
+ limit = 0
181
+ augmenter = null
182
+
183
+ [training]
184
+ train_corpus = "corpora.train"
185
+ dev_corpus = "corpora.dev"
186
+ seed = ${system:seed}
187
+ gpu_allocator = ${system:gpu_allocator}
188
+ dropout = 0.1
189
+ accumulate_gradient = 3
190
+ patience = 5000
191
+ max_epochs = 0
192
+ max_steps = 20000
193
+ eval_frequency = 200
194
+ frozen_components = []
195
+ before_to_disk = null
196
+ annotating_components = []
197
+
198
+ [training.batcher]
199
+ @batchers = "spacy.batch_by_padded.v1"
200
+ discard_oversize = true
201
+ get_length = null
202
+ size = 2000
203
+ buffer = 256
204
+
205
+ [training.logger]
206
+ @loggers = "spacy.ConsoleLogger.v1"
207
+ progress_bar = false
208
+
209
+ [training.optimizer]
210
+ @optimizers = "Adam.v1"
211
+ beta1 = 0.9
212
+ beta2 = 0.999
213
+ L2_is_weight_decay = true
214
+ L2 = 0.01
215
+ grad_clip = 1.0
216
+ use_averages = true
217
+ eps = 0.00000001
218
+
219
+ [training.optimizer.learn_rate]
220
+ @schedules = "warmup_linear.v1"
221
+ warmup_steps = 250
222
+ total_steps = 20000
223
+ initial_rate = 0.00005
224
+
225
+ [training.score_weights]
226
+ token_f = 0.0
227
+ token_p = null
228
+ token_r = null
229
+ token_acc = null
230
+ sents_f = 0.05
231
+ sents_p = 0.0
232
+ sents_r = 0.0
233
+ tag_acc = 0.11
234
+ pos_acc = 0.05
235
+ morph_acc = 0.05
236
+ morph_per_feat = null
237
+ dep_uas = 0.11
238
+ dep_las = 0.11
239
+ dep_las_per_type = null
240
+ lemma_acc = 0.52
241
+
242
+ [pretraining]
243
+
244
+ [initialize]
245
+ vectors = ${paths.vectors}
246
+ init_tok2vec = ${paths.init_tok2vec}
247
+ vocab_data = null
248
+ lookups = null
249
+ before_init = null
250
+ after_init = null
251
+
252
+ [initialize.components]
253
+
254
+ [initialize.tokenizer]
experimental_char_ner_tokenizer/cfg ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "moves":null,
3
+ "update_with_oracle_cut_size":100,
4
+ "multitasks":[
5
+
6
+ ],
7
+ "min_action_freq":1,
8
+ "learn_tokens":false,
9
+ "beam_width":1,
10
+ "beam_density":0.0,
11
+ "beam_update_prob":0.0,
12
+ "incorrect_spans_key":null
13
+ }
experimental_char_ner_tokenizer/model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d1451ad867d113c07a1655e5bc3c2cf2b32a5413cac9998fb65e48f36cf083d
3
+ size 6922248
experimental_char_ner_tokenizer/moves ADDED
@@ -0,0 +1 @@
 
 
1
+ ��moves�l{"0":{},"1":{"TOKEN":168807},"2":{"TOKEN":168807},"3":{"TOKEN":168807},"4":{"TOKEN":168807,"":1},"5":{"":1}}�cfg��neg_key�
experimental_edit_tree_lemmatizer/cfg ADDED
@@ -0,0 +1,275 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "labels":[
3
+ 1,
4
+ 2,
5
+ 4,
6
+ 7,
7
+ 8,
8
+ 10,
9
+ 12,
10
+ 14,
11
+ 16,
12
+ 18,
13
+ 21,
14
+ 24,
15
+ 26,
16
+ 28,
17
+ 31,
18
+ 32,
19
+ 34,
20
+ 37,
21
+ 39,
22
+ 40,
23
+ 42,
24
+ 44,
25
+ 46,
26
+ 47,
27
+ 49,
28
+ 51,
29
+ 53,
30
+ 54,
31
+ 56,
32
+ 57,
33
+ 58,
34
+ 59,
35
+ 61,
36
+ 64,
37
+ 66,
38
+ 68,
39
+ 69,
40
+ 72,
41
+ 74,
42
+ 75,
43
+ 77,
44
+ 78,
45
+ 81,
46
+ 83,
47
+ 84,
48
+ 85,
49
+ 86,
50
+ 87,
51
+ 90,
52
+ 92,
53
+ 94,
54
+ 96,
55
+ 99,
56
+ 101,
57
+ 103,
58
+ 105,
59
+ 108,
60
+ 110,
61
+ 113,
62
+ 116,
63
+ 117,
64
+ 118,
65
+ 121,
66
+ 123,
67
+ 124,
68
+ 125,
69
+ 127,
70
+ 128,
71
+ 129,
72
+ 133,
73
+ 136,
74
+ 138,
75
+ 141,
76
+ 143,
77
+ 145,
78
+ 147,
79
+ 151,
80
+ 153,
81
+ 154,
82
+ 156,
83
+ 158,
84
+ 159,
85
+ 160,
86
+ 162,
87
+ 164,
88
+ 165,
89
+ 167,
90
+ 168,
91
+ 170,
92
+ 172,
93
+ 174,
94
+ 176,
95
+ 178,
96
+ 179,
97
+ 180,
98
+ 181,
99
+ 183,
100
+ 185,
101
+ 189,
102
+ 190,
103
+ 191,
104
+ 192,
105
+ 194,
106
+ 195,
107
+ 197,
108
+ 198,
109
+ 201,
110
+ 202,
111
+ 203,
112
+ 204,
113
+ 206,
114
+ 207,
115
+ 209,
116
+ 213,
117
+ 214,
118
+ 216,
119
+ 217,
120
+ 218,
121
+ 220,
122
+ 221,
123
+ 222,
124
+ 223,
125
+ 225,
126
+ 226,
127
+ 228,
128
+ 229,
129
+ 231,
130
+ 233,
131
+ 234,
132
+ 236,
133
+ 238,
134
+ 240,
135
+ 241,
136
+ 244,
137
+ 247,
138
+ 248,
139
+ 249,
140
+ 250,
141
+ 252,
142
+ 253,
143
+ 255,
144
+ 256,
145
+ 257,
146
+ 258,
147
+ 261,
148
+ 262,
149
+ 263,
150
+ 265,
151
+ 267,
152
+ 269,
153
+ 270,
154
+ 271,
155
+ 273,
156
+ 275,
157
+ 276,
158
+ 278,
159
+ 279,
160
+ 281,
161
+ 283,
162
+ 285,
163
+ 287,
164
+ 289,
165
+ 291,
166
+ 294,
167
+ 296,
168
+ 297,
169
+ 298,
170
+ 299,
171
+ 300,
172
+ 301,
173
+ 302,
174
+ 303,
175
+ 305,
176
+ 306,
177
+ 307,
178
+ 309,
179
+ 310,
180
+ 311,
181
+ 313,
182
+ 314,
183
+ 315,
184
+ 317,
185
+ 320,
186
+ 321,
187
+ 323,
188
+ 325,
189
+ 326,
190
+ 327,
191
+ 328,
192
+ 329,
193
+ 330,
194
+ 332,
195
+ 333,
196
+ 335,
197
+ 336,
198
+ 337,
199
+ 338,
200
+ 339,
201
+ 340,
202
+ 341,
203
+ 343,
204
+ 344,
205
+ 347,
206
+ 348,
207
+ 349,
208
+ 351,
209
+ 353,
210
+ 355,
211
+ 357,
212
+ 359,
213
+ 360,
214
+ 361,
215
+ 362,
216
+ 365,
217
+ 366,
218
+ 367,
219
+ 369,
220
+ 371,
221
+ 373,
222
+ 374,
223
+ 375,
224
+ 377,
225
+ 379,
226
+ 381,
227
+ 383,
228
+ 386,
229
+ 388,
230
+ 390,
231
+ 392,
232
+ 393,
233
+ 395,
234
+ 397,
235
+ 398,
236
+ 400,
237
+ 401,
238
+ 402,
239
+ 403,
240
+ 405,
241
+ 406,
242
+ 408,
243
+ 409,
244
+ 411,
245
+ 412,
246
+ 414,
247
+ 417,
248
+ 215,
249
+ 418,
250
+ 419,
251
+ 420,
252
+ 421,
253
+ 422,
254
+ 424,
255
+ 425,
256
+ 426,
257
+ 427,
258
+ 429,
259
+ 431,
260
+ 432,
261
+ 433,
262
+ 434,
263
+ 436,
264
+ 438,
265
+ 439,
266
+ 440,
267
+ 442,
268
+ 443,
269
+ 444,
270
+ 447,
271
+ 449,
272
+ 450,
273
+ 452
274
+ ]
275
+ }
experimental_edit_tree_lemmatizer/model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f440416add1f6b780a89284f4bdfee9ba38635a91fd347722b1963e21652d90
3
+ size 834197
experimental_edit_tree_lemmatizer/trees ADDED
Binary file (36.1 kB). View file
 
meta.json ADDED
@@ -0,0 +1,735 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "lang":"af",
3
+ "name":"udv25_afrikaansafribooms_trf",
4
+ "version":"0.0.1",
5
+ "description":"UD v2.5 benchmarking pipeline for UD_Afrikaans-AfriBooms",
6
+ "author":"Explosion",
7
+ "email":"[email protected]",
8
+ "url":"https://explosion.ai",
9
+ "license":"CC BY-SA 4.0",
10
+ "spacy_version":">=3.2.1,<3.3.0",
11
+ "spacy_git_version":"800737b41",
12
+ "vectors":{
13
+ "width":0,
14
+ "vectors":0,
15
+ "keys":0,
16
+ "name":null
17
+ },
18
+ "labels":{
19
+ "experimental_char_ner_tokenizer":[
20
+ "TOKEN"
21
+ ],
22
+ "transformer":[
23
+
24
+ ],
25
+ "senter":[
26
+ "I",
27
+ "S"
28
+ ],
29
+ "tagger":[
30
+ "AOA",
31
+ "AOP",
32
+ "ASA",
33
+ "ASP",
34
+ "AVA",
35
+ "AVP",
36
+ "BO",
37
+ "BS",
38
+ "BV",
39
+ "KN",
40
+ "KO",
41
+ "LB",
42
+ "LO",
43
+ "NA",
44
+ "NEE",
45
+ "NM",
46
+ "NME",
47
+ "NSE",
48
+ "NSED",
49
+ "NSM",
50
+ "PA",
51
+ "PB",
52
+ "PDHEB",
53
+ "PDHEDP",
54
+ "PDHENP",
55
+ "PDHEW",
56
+ "PDMB",
57
+ "PDMP",
58
+ "PDMW",
59
+ "PDOENP",
60
+ "PDOEW",
61
+ "PDVEB",
62
+ "PDVEDP",
63
+ "PDVENP",
64
+ "PDVEW",
65
+ "PEEB",
66
+ "PEEDP",
67
+ "PEENP",
68
+ "PEMB",
69
+ "PEMP",
70
+ "PEMW",
71
+ "PO",
72
+ "PTEB",
73
+ "PTEDP",
74
+ "PTENP",
75
+ "PTEW",
76
+ "PTMP",
77
+ "PV",
78
+ "PW",
79
+ "RA",
80
+ "RK",
81
+ "RL",
82
+ "RO",
83
+ "RS",
84
+ "RSF",
85
+ "RV",
86
+ "RWD",
87
+ "SVS",
88
+ "THAB",
89
+ "THAO",
90
+ "THBB",
91
+ "THBO",
92
+ "THNB",
93
+ "THPB",
94
+ "THPO",
95
+ "TRAB",
96
+ "TRAO",
97
+ "TRBB",
98
+ "UPB",
99
+ "UPD",
100
+ "UPI",
101
+ "UPO",
102
+ "UPS",
103
+ "UPV",
104
+ "UPW",
105
+ "UXD",
106
+ "VTHOG",
107
+ "VTHOK",
108
+ "VTHOO",
109
+ "VTHOV",
110
+ "VTHSG",
111
+ "VTHSO",
112
+ "VTUOA",
113
+ "VTUOM",
114
+ "VTUOP",
115
+ "VUOT",
116
+ "VVHOG",
117
+ "VVHOK",
118
+ "VVHOO",
119
+ "VVUOM",
120
+ "VVUOP",
121
+ "ZE",
122
+ "ZM",
123
+ "ZPL",
124
+ "ZPR"
125
+ ],
126
+ "morphologizer":[
127
+ "Definite=Def|POS=DET|PronType=Art",
128
+ "Number=Sing|POS=NOUN",
129
+ "AdpType=Prep|POS=ADP",
130
+ "AdjType=Attr|Case=Nom|Degree=Pos|POS=ADJ",
131
+ "Number=Plur|POS=NOUN",
132
+ "POS=AUX|Tense=Pres|VerbForm=Fin,Inf|VerbType=Cop",
133
+ "Definite=Ind|POS=DET|PronType=Art",
134
+ "POS=NUM",
135
+ "POS=PART|PartType=Inf",
136
+ "POS=VERB|Subcat=Tran|Tense=Pres|VerbForm=Fin,Inf",
137
+ "POS=PRON|PronType=Rel",
138
+ "POS=AUX|Tense=Pres|VerbForm=Fin,Inf|VerbType=Pas",
139
+ "POS=PUNCT",
140
+ "POS=CCONJ",
141
+ "POS=SCONJ",
142
+ "POS=VERB|Subcat=Intr|Tense=Pres|VerbForm=Fin,Inf",
143
+ "POS=VERB|Subcat=Intr|Tense=Past|VerbForm=Part",
144
+ "POS=AUX|Tense=Past|VerbForm=Fin|VerbType=Pas",
145
+ "Degree=Pos|POS=ADV",
146
+ "POS=AUX|Tense=Pres|VerbForm=Fin,Inf|VerbType=Mod",
147
+ "POS=DET|PronType=Ind",
148
+ "POS=X",
149
+ "Number=Sing|POS=PROPN",
150
+ "POS=PRON|PronType=Ind",
151
+ "POS=PART|PartType=Neg",
152
+ "POS=VERB|Subcat=Tran|Tense=Past|VerbForm=Part",
153
+ "AdjType=Pred|Case=Nom|Degree=Pos|POS=ADJ",
154
+ "POS=DET|PronType=Dem",
155
+ "Degree=Cmp|POS=ADV",
156
+ "Case=Nom|Number=Sing|POS=PRON|Person=3|PronType=Prs",
157
+ "POS=SYM",
158
+ "Case=Acc,Nom|Number=Plur|POS=PRON|Person=1|PronType=Prs",
159
+ "POS=PART|PartType=Gen",
160
+ "Case=Acc|Number=Sing|POS=PRON|Person=2|PronType=Prs",
161
+ "Number=Sing|POS=PRON|Person=2|PronType=Prs|Reflex=Yes",
162
+ "Degree=Sup|POS=ADV",
163
+ "Degree=Dim|Number=Sing|POS=NOUN",
164
+ "Number=Sing|POS=PRON|Person=2|Poss=Yes|PronType=Prs",
165
+ "POS=PRON|PronType=Int",
166
+ "Number=Plur|POS=PRON|Person=1|Poss=Yes|PronType=Prs",
167
+ "Number=Sing|POS=PRON|Person=3|PronType=Prs|Reflex=Yes",
168
+ "Number=Plur|POS=PRON|Person=3|Poss=Yes|PronType=Prs",
169
+ "AdjType=Attr|Case=Nom|Degree=Sup|POS=ADJ",
170
+ "Case=Nom|Number=Sing|POS=PRON|Person=2|PronType=Prs",
171
+ "AdjType=Pred|Case=Nom|Degree=Cmp|POS=ADJ",
172
+ "POS=VERB|Subcat=Prep|Tense=Pres|VerbForm=Fin,Inf",
173
+ "POS=AUX|Tense=Pres|VerbForm=Fin,Inf|VerbType=Aux",
174
+ "Number=Sing|POS=PRON|Person=3|Poss=Yes|PronType=Prs",
175
+ "POS=PRON|PronType=Rcp",
176
+ "POS=AUX|Tense=Past|VerbForm=Fin|VerbType=Mod",
177
+ "Case=Acc,Nom|Number=Plur|POS=PRON|Person=3|PronType=Prs",
178
+ "POS=AUX|Tense=Past|VerbForm=Fin|VerbType=Cop",
179
+ "Case=Acc|Number=Sing|POS=PRON|Person=3|PronType=Prs",
180
+ "Case=Nom|Number=Sing|POS=PRON|Person=1|PronType=Prs",
181
+ "Number=Sing|POS=PRON|Person=1|Poss=Yes|PronType=Prs",
182
+ "Case=Acc,Nom|Number=Plur|POS=PRON|Person=2|PronType=Prs",
183
+ "Number=Plur|POS=PRON|Person=3|PronType=Prs|Reflex=Yes",
184
+ "AdjType=Attr|Case=Nom|Degree=Cmp|POS=ADJ",
185
+ "Number=Plur|POS=PRON|Person=1|PronType=Prs|Reflex=Yes",
186
+ "Case=Acc|Number=Sing|POS=PRON|Person=1|PronType=Prs",
187
+ "AdjType=Pred|Case=Nom|Degree=Sup|POS=ADJ"
188
+ ],
189
+ "parser":[
190
+ "ROOT",
191
+ "advmod",
192
+ "amod",
193
+ "appos",
194
+ "aux",
195
+ "aux:pass",
196
+ "case",
197
+ "cc",
198
+ "ccomp",
199
+ "compound:prt",
200
+ "conj",
201
+ "cop",
202
+ "dep",
203
+ "det",
204
+ "flat",
205
+ "iobj",
206
+ "mark",
207
+ "nmod",
208
+ "nsubj",
209
+ "nsubj:pass",
210
+ "nummod",
211
+ "obj",
212
+ "obl",
213
+ "punct",
214
+ "xcomp"
215
+ ],
216
+ "experimental_edit_tree_lemmatizer":[
217
+ 1,
218
+ 2,
219
+ 4,
220
+ 7,
221
+ 8,
222
+ 10,
223
+ 12,
224
+ 14,
225
+ 16,
226
+ 18,
227
+ 21,
228
+ 24,
229
+ 26,
230
+ 28,
231
+ 31,
232
+ 32,
233
+ 34,
234
+ 37,
235
+ 39,
236
+ 40,
237
+ 42,
238
+ 44,
239
+ 46,
240
+ 47,
241
+ 49,
242
+ 51,
243
+ 53,
244
+ 54,
245
+ 56,
246
+ 57,
247
+ 58,
248
+ 59,
249
+ 61,
250
+ 64,
251
+ 66,
252
+ 68,
253
+ 69,
254
+ 72,
255
+ 74,
256
+ 75,
257
+ 77,
258
+ 78,
259
+ 81,
260
+ 83,
261
+ 84,
262
+ 85,
263
+ 86,
264
+ 87,
265
+ 90,
266
+ 92,
267
+ 94,
268
+ 96,
269
+ 99,
270
+ 101,
271
+ 103,
272
+ 105,
273
+ 108,
274
+ 110,
275
+ 113,
276
+ 116,
277
+ 117,
278
+ 118,
279
+ 121,
280
+ 123,
281
+ 124,
282
+ 125,
283
+ 127,
284
+ 128,
285
+ 129,
286
+ 133,
287
+ 136,
288
+ 138,
289
+ 141,
290
+ 143,
291
+ 145,
292
+ 147,
293
+ 151,
294
+ 153,
295
+ 154,
296
+ 156,
297
+ 158,
298
+ 159,
299
+ 160,
300
+ 162,
301
+ 164,
302
+ 165,
303
+ 167,
304
+ 168,
305
+ 170,
306
+ 172,
307
+ 174,
308
+ 176,
309
+ 178,
310
+ 179,
311
+ 180,
312
+ 181,
313
+ 183,
314
+ 185,
315
+ 189,
316
+ 190,
317
+ 191,
318
+ 192,
319
+ 194,
320
+ 195,
321
+ 197,
322
+ 198,
323
+ 201,
324
+ 202,
325
+ 203,
326
+ 204,
327
+ 206,
328
+ 207,
329
+ 209,
330
+ 213,
331
+ 214,
332
+ 216,
333
+ 217,
334
+ 218,
335
+ 220,
336
+ 221,
337
+ 222,
338
+ 223,
339
+ 225,
340
+ 226,
341
+ 228,
342
+ 229,
343
+ 231,
344
+ 233,
345
+ 234,
346
+ 236,
347
+ 238,
348
+ 240,
349
+ 241,
350
+ 244,
351
+ 247,
352
+ 248,
353
+ 249,
354
+ 250,
355
+ 252,
356
+ 253,
357
+ 255,
358
+ 256,
359
+ 257,
360
+ 258,
361
+ 261,
362
+ 262,
363
+ 263,
364
+ 265,
365
+ 267,
366
+ 269,
367
+ 270,
368
+ 271,
369
+ 273,
370
+ 275,
371
+ 276,
372
+ 278,
373
+ 279,
374
+ 281,
375
+ 283,
376
+ 285,
377
+ 287,
378
+ 289,
379
+ 291,
380
+ 294,
381
+ 296,
382
+ 297,
383
+ 298,
384
+ 299,
385
+ 300,
386
+ 301,
387
+ 302,
388
+ 303,
389
+ 305,
390
+ 306,
391
+ 307,
392
+ 309,
393
+ 310,
394
+ 311,
395
+ 313,
396
+ 314,
397
+ 315,
398
+ 317,
399
+ 320,
400
+ 321,
401
+ 323,
402
+ 325,
403
+ 326,
404
+ 327,
405
+ 328,
406
+ 329,
407
+ 330,
408
+ 332,
409
+ 333,
410
+ 335,
411
+ 336,
412
+ 337,
413
+ 338,
414
+ 339,
415
+ 340,
416
+ 341,
417
+ 343,
418
+ 344,
419
+ 347,
420
+ 348,
421
+ 349,
422
+ 351,
423
+ 353,
424
+ 355,
425
+ 357,
426
+ 359,
427
+ 360,
428
+ 361,
429
+ 362,
430
+ 365,
431
+ 366,
432
+ 367,
433
+ 369,
434
+ 371,
435
+ 373,
436
+ 374,
437
+ 375,
438
+ 377,
439
+ 379,
440
+ 381,
441
+ 383,
442
+ 386,
443
+ 388,
444
+ 390,
445
+ 392,
446
+ 393,
447
+ 395,
448
+ 397,
449
+ 398,
450
+ 400,
451
+ 401,
452
+ 402,
453
+ 403,
454
+ 405,
455
+ 406,
456
+ 408,
457
+ 409,
458
+ 411,
459
+ 412,
460
+ 414,
461
+ 417,
462
+ 215,
463
+ 418,
464
+ 419,
465
+ 420,
466
+ 421,
467
+ 422,
468
+ 424,
469
+ 425,
470
+ 426,
471
+ 427,
472
+ 429,
473
+ 431,
474
+ 432,
475
+ 433,
476
+ 434,
477
+ 436,
478
+ 438,
479
+ 439,
480
+ 440,
481
+ 442,
482
+ 443,
483
+ 444,
484
+ 447,
485
+ 449,
486
+ 450,
487
+ 452
488
+ ]
489
+ },
490
+ "pipeline":[
491
+ "experimental_char_ner_tokenizer",
492
+ "transformer",
493
+ "tagger",
494
+ "morphologizer",
495
+ "parser",
496
+ "experimental_edit_tree_lemmatizer"
497
+ ],
498
+ "components":[
499
+ "experimental_char_ner_tokenizer",
500
+ "transformer",
501
+ "senter",
502
+ "tagger",
503
+ "morphologizer",
504
+ "parser",
505
+ "experimental_edit_tree_lemmatizer"
506
+ ],
507
+ "disabled":[
508
+ "senter"
509
+ ],
510
+ "sources":[
511
+ {
512
+ "name":"Universal Dependencies v2.5",
513
+ "url":"https://lindat.mff.cuni.cz/repository/xmlui/handle/11234/1-3105",
514
+ "author":"Zeman, Daniel; et al."
515
+ }
516
+ ],
517
+ "performance":{
518
+ "token_f":0.9991538968,
519
+ "token_p":0.9988721805,
520
+ "token_r":0.9994357721,
521
+ "token_acc":1.0,
522
+ "sents_f":1.0,
523
+ "sents_p":1.0,
524
+ "sents_r":1.0,
525
+ "tag_acc":0.9601278917,
526
+ "pos_acc":0.9852374236,
527
+ "morph_acc":0.9751739703,
528
+ "morph_per_feat":{
529
+ "Case":{
530
+ "p":0.9530332681,
531
+ "r":0.9779116466,
532
+ "f":0.9653121903
533
+ },
534
+ "Number":{
535
+ "p":0.9856733524,
536
+ "r":0.9842632332,
537
+ "f":0.9849677881
538
+ },
539
+ "Person":{
540
+ "p":0.9866666667,
541
+ "r":0.9910714286,
542
+ "f":0.9888641425
543
+ },
544
+ "PronType":{
545
+ "p":0.993877551,
546
+ "r":0.9868287741,
547
+ "f":0.9903406202
548
+ },
549
+ "Subcat":{
550
+ "p":0.9416846652,
551
+ "r":0.9256900212,
552
+ "f":0.9336188437
553
+ },
554
+ "Tense":{
555
+ "p":0.992481203,
556
+ "r":0.982630273,
557
+ "f":0.9875311721
558
+ },
559
+ "VerbForm":{
560
+ "p":0.9912280702,
561
+ "r":0.9813895782,
562
+ "f":0.9862842893
563
+ },
564
+ "AdjType":{
565
+ "p":0.9323943662,
566
+ "r":0.9764011799,
567
+ "f":0.9538904899
568
+ },
569
+ "Degree":{
570
+ "p":0.9627659574,
571
+ "r":0.9679144385,
572
+ "f":0.9653333333
573
+ },
574
+ "AdpType":{
575
+ "p":0.9967845659,
576
+ "r":0.9967845659,
577
+ "f":0.9967845659
578
+ },
579
+ "Definite":{
580
+ "p":1.0,
581
+ "r":1.0,
582
+ "f":1.0
583
+ },
584
+ "PartType":{
585
+ "p":1.0,
586
+ "r":0.9945652174,
587
+ "f":0.9972752044
588
+ },
589
+ "VerbType":{
590
+ "p":0.9820895522,
591
+ "r":0.9820895522,
592
+ "f":0.9820895522
593
+ },
594
+ "Poss":{
595
+ "p":0.9242424242,
596
+ "r":1.0,
597
+ "f":0.9606299213
598
+ },
599
+ "Reflex":{
600
+ "p":1.0,
601
+ "r":0.75,
602
+ "f":0.8571428571
603
+ }
604
+ },
605
+ "dep_uas":0.9078427294,
606
+ "dep_las":0.8749739963,
607
+ "dep_las_per_type":{
608
+ "amod":{
609
+ "p":0.7847082495,
610
+ "r":0.8423326134,
611
+ "f":0.8125
612
+ },
613
+ "nsubj":{
614
+ "p":0.8905775076,
615
+ "r":0.8694362018,
616
+ "f":0.8798798799
617
+ },
618
+ "root":{
619
+ "p":0.9381443299,
620
+ "r":0.9381443299,
621
+ "f":0.9381443299
622
+ },
623
+ "det":{
624
+ "p":0.9713831479,
625
+ "r":0.9546875,
626
+ "f":0.962962963
627
+ },
628
+ "obj":{
629
+ "p":0.8823529412,
630
+ "r":0.8585858586,
631
+ "f":0.8703071672
632
+ },
633
+ "case":{
634
+ "p":0.9578783151,
635
+ "r":0.9684542587,
636
+ "f":0.9631372549
637
+ },
638
+ "nmod":{
639
+ "p":0.8211678832,
640
+ "r":0.8272058824,
641
+ "f":0.8241758242
642
+ },
643
+ "mark":{
644
+ "p":0.9285714286,
645
+ "r":0.8888888889,
646
+ "f":0.9082969432
647
+ },
648
+ "xcomp":{
649
+ "p":0.7714285714,
650
+ "r":0.675,
651
+ "f":0.72
652
+ },
653
+ "aux":{
654
+ "p":0.9397590361,
655
+ "r":0.9285714286,
656
+ "f":0.9341317365
657
+ },
658
+ "dep":{
659
+ "p":0.7515151515,
660
+ "r":0.5961538462,
661
+ "f":0.6648793566
662
+ },
663
+ "cc":{
664
+ "p":0.8552631579,
665
+ "r":0.8705357143,
666
+ "f":0.8628318584
667
+ },
668
+ "conj":{
669
+ "p":0.8486055777,
670
+ "r":0.8486055777,
671
+ "f":0.8486055777
672
+ },
673
+ "obl":{
674
+ "p":0.8155619597,
675
+ "r":0.8299120235,
676
+ "f":0.8226744186
677
+ },
678
+ "cop":{
679
+ "p":0.8970588235,
680
+ "r":0.8133333333,
681
+ "f":0.8531468531
682
+ },
683
+ "ccomp":{
684
+ "p":0.8514851485,
685
+ "r":0.8686868687,
686
+ "f":0.86
687
+ },
688
+ "advmod":{
689
+ "p":0.7912621359,
690
+ "r":0.8232323232,
691
+ "f":0.8069306931
692
+ },
693
+ "compound:prt":{
694
+ "p":0.9705882353,
695
+ "r":0.9428571429,
696
+ "f":0.9565217391
697
+ },
698
+ "aux:pass":{
699
+ "p":0.9782608696,
700
+ "r":1.0,
701
+ "f":0.989010989
702
+ },
703
+ "nummod":{
704
+ "p":0.7073170732,
705
+ "r":0.90625,
706
+ "f":0.7945205479
707
+ },
708
+ "nsubj:pass":{
709
+ "p":0.6724137931,
710
+ "r":0.7959183673,
711
+ "f":0.7289719626
712
+ },
713
+ "iobj":{
714
+ "p":1.0,
715
+ "r":0.625,
716
+ "f":0.7692307692
717
+ },
718
+ "flat":{
719
+ "p":0.6756756757,
720
+ "r":0.8333333333,
721
+ "f":0.7462686567
722
+ },
723
+ "appos":{
724
+ "p":0.4285714286,
725
+ "r":0.5,
726
+ "f":0.4615384615
727
+ }
728
+ },
729
+ "lemma_acc":0.9786593964
730
+ },
731
+ "requirements":[
732
+ "spacy-experimental>=0.2.0,<0.3.0",
733
+ "spacy-transformers>=1.1.3,<1.2.0"
734
+ ]
735
+ }
morphologizer/cfg ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "extend":false,
3
+ "labels_morph":{
4
+ "Definite=Def|POS=DET|PronType=Art":"Definite=Def|PronType=Art",
5
+ "Number=Sing|POS=NOUN":"Number=Sing",
6
+ "AdpType=Prep|POS=ADP":"AdpType=Prep",
7
+ "AdjType=Attr|Case=Nom|Degree=Pos|POS=ADJ":"AdjType=Attr|Case=Nom|Degree=Pos",
8
+ "Number=Plur|POS=NOUN":"Number=Plur",
9
+ "POS=AUX|Tense=Pres|VerbForm=Fin,Inf|VerbType=Cop":"Tense=Pres|VerbForm=Fin,Inf|VerbType=Cop",
10
+ "Definite=Ind|POS=DET|PronType=Art":"Definite=Ind|PronType=Art",
11
+ "POS=NUM":"",
12
+ "POS=PART|PartType=Inf":"PartType=Inf",
13
+ "POS=VERB|Subcat=Tran|Tense=Pres|VerbForm=Fin,Inf":"Subcat=Tran|Tense=Pres|VerbForm=Fin,Inf",
14
+ "POS=PRON|PronType=Rel":"PronType=Rel",
15
+ "POS=AUX|Tense=Pres|VerbForm=Fin,Inf|VerbType=Pas":"Tense=Pres|VerbForm=Fin,Inf|VerbType=Pas",
16
+ "POS=PUNCT":"",
17
+ "POS=CCONJ":"",
18
+ "POS=SCONJ":"",
19
+ "POS=VERB|Subcat=Intr|Tense=Pres|VerbForm=Fin,Inf":"Subcat=Intr|Tense=Pres|VerbForm=Fin,Inf",
20
+ "POS=VERB|Subcat=Intr|Tense=Past|VerbForm=Part":"Subcat=Intr|Tense=Past|VerbForm=Part",
21
+ "POS=AUX|Tense=Past|VerbForm=Fin|VerbType=Pas":"Tense=Past|VerbForm=Fin|VerbType=Pas",
22
+ "Degree=Pos|POS=ADV":"Degree=Pos",
23
+ "POS=AUX|Tense=Pres|VerbForm=Fin,Inf|VerbType=Mod":"Tense=Pres|VerbForm=Fin,Inf|VerbType=Mod",
24
+ "POS=DET|PronType=Ind":"PronType=Ind",
25
+ "POS=X":"",
26
+ "Number=Sing|POS=PROPN":"Number=Sing",
27
+ "POS=PRON|PronType=Ind":"PronType=Ind",
28
+ "POS=PART|PartType=Neg":"PartType=Neg",
29
+ "POS=VERB|Subcat=Tran|Tense=Past|VerbForm=Part":"Subcat=Tran|Tense=Past|VerbForm=Part",
30
+ "AdjType=Pred|Case=Nom|Degree=Pos|POS=ADJ":"AdjType=Pred|Case=Nom|Degree=Pos",
31
+ "POS=DET|PronType=Dem":"PronType=Dem",
32
+ "Degree=Cmp|POS=ADV":"Degree=Cmp",
33
+ "Case=Nom|Number=Sing|POS=PRON|Person=3|PronType=Prs":"Case=Nom|Number=Sing|Person=3|PronType=Prs",
34
+ "POS=SYM":"",
35
+ "Case=Acc,Nom|Number=Plur|POS=PRON|Person=1|PronType=Prs":"Case=Acc,Nom|Number=Plur|Person=1|PronType=Prs",
36
+ "POS=PART|PartType=Gen":"PartType=Gen",
37
+ "Case=Acc|Number=Sing|POS=PRON|Person=2|PronType=Prs":"Case=Acc|Number=Sing|Person=2|PronType=Prs",
38
+ "Number=Sing|POS=PRON|Person=2|PronType=Prs|Reflex=Yes":"Number=Sing|Person=2|PronType=Prs|Reflex=Yes",
39
+ "Degree=Sup|POS=ADV":"Degree=Sup",
40
+ "Degree=Dim|Number=Sing|POS=NOUN":"Degree=Dim|Number=Sing",
41
+ "Number=Sing|POS=PRON|Person=2|Poss=Yes|PronType=Prs":"Number=Sing|Person=2|Poss=Yes|PronType=Prs",
42
+ "POS=PRON|PronType=Int":"PronType=Int",
43
+ "Number=Plur|POS=PRON|Person=1|Poss=Yes|PronType=Prs":"Number=Plur|Person=1|Poss=Yes|PronType=Prs",
44
+ "Number=Sing|POS=PRON|Person=3|PronType=Prs|Reflex=Yes":"Number=Sing|Person=3|PronType=Prs|Reflex=Yes",
45
+ "Number=Plur|POS=PRON|Person=3|Poss=Yes|PronType=Prs":"Number=Plur|Person=3|Poss=Yes|PronType=Prs",
46
+ "AdjType=Attr|Case=Nom|Degree=Sup|POS=ADJ":"AdjType=Attr|Case=Nom|Degree=Sup",
47
+ "Case=Nom|Number=Sing|POS=PRON|Person=2|PronType=Prs":"Case=Nom|Number=Sing|Person=2|PronType=Prs",
48
+ "AdjType=Pred|Case=Nom|Degree=Cmp|POS=ADJ":"AdjType=Pred|Case=Nom|Degree=Cmp",
49
+ "POS=VERB|Subcat=Prep|Tense=Pres|VerbForm=Fin,Inf":"Subcat=Prep|Tense=Pres|VerbForm=Fin,Inf",
50
+ "POS=AUX|Tense=Pres|VerbForm=Fin,Inf|VerbType=Aux":"Tense=Pres|VerbForm=Fin,Inf|VerbType=Aux",
51
+ "Number=Sing|POS=PRON|Person=3|Poss=Yes|PronType=Prs":"Number=Sing|Person=3|Poss=Yes|PronType=Prs",
52
+ "POS=PRON|PronType=Rcp":"PronType=Rcp",
53
+ "POS=AUX|Tense=Past|VerbForm=Fin|VerbType=Mod":"Tense=Past|VerbForm=Fin|VerbType=Mod",
54
+ "Case=Acc,Nom|Number=Plur|POS=PRON|Person=3|PronType=Prs":"Case=Acc,Nom|Number=Plur|Person=3|PronType=Prs",
55
+ "POS=AUX|Tense=Past|VerbForm=Fin|VerbType=Cop":"Tense=Past|VerbForm=Fin|VerbType=Cop",
56
+ "Case=Acc|Number=Sing|POS=PRON|Person=3|PronType=Prs":"Case=Acc|Number=Sing|Person=3|PronType=Prs",
57
+ "Case=Nom|Number=Sing|POS=PRON|Person=1|PronType=Prs":"Case=Nom|Number=Sing|Person=1|PronType=Prs",
58
+ "Number=Sing|POS=PRON|Person=1|Poss=Yes|PronType=Prs":"Number=Sing|Person=1|Poss=Yes|PronType=Prs",
59
+ "Case=Acc,Nom|Number=Plur|POS=PRON|Person=2|PronType=Prs":"Case=Acc,Nom|Number=Plur|Person=2|PronType=Prs",
60
+ "Number=Plur|POS=PRON|Person=3|PronType=Prs|Reflex=Yes":"Number=Plur|Person=3|PronType=Prs|Reflex=Yes",
61
+ "AdjType=Attr|Case=Nom|Degree=Cmp|POS=ADJ":"AdjType=Attr|Case=Nom|Degree=Cmp",
62
+ "Number=Plur|POS=PRON|Person=1|PronType=Prs|Reflex=Yes":"Number=Plur|Person=1|PronType=Prs|Reflex=Yes",
63
+ "Case=Acc|Number=Sing|POS=PRON|Person=1|PronType=Prs":"Case=Acc|Number=Sing|Person=1|PronType=Prs",
64
+ "AdjType=Pred|Case=Nom|Degree=Sup|POS=ADJ":"AdjType=Pred|Case=Nom|Degree=Sup"
65
+ },
66
+ "labels_pos":{
67
+ "Definite=Def|POS=DET|PronType=Art":90,
68
+ "Number=Sing|POS=NOUN":92,
69
+ "AdpType=Prep|POS=ADP":85,
70
+ "AdjType=Attr|Case=Nom|Degree=Pos|POS=ADJ":84,
71
+ "Number=Plur|POS=NOUN":92,
72
+ "POS=AUX|Tense=Pres|VerbForm=Fin,Inf|VerbType=Cop":87,
73
+ "Definite=Ind|POS=DET|PronType=Art":90,
74
+ "POS=NUM":93,
75
+ "POS=PART|PartType=Inf":94,
76
+ "POS=VERB|Subcat=Tran|Tense=Pres|VerbForm=Fin,Inf":100,
77
+ "POS=PRON|PronType=Rel":95,
78
+ "POS=AUX|Tense=Pres|VerbForm=Fin,Inf|VerbType=Pas":87,
79
+ "POS=PUNCT":97,
80
+ "POS=CCONJ":89,
81
+ "POS=SCONJ":98,
82
+ "POS=VERB|Subcat=Intr|Tense=Pres|VerbForm=Fin,Inf":100,
83
+ "POS=VERB|Subcat=Intr|Tense=Past|VerbForm=Part":100,
84
+ "POS=AUX|Tense=Past|VerbForm=Fin|VerbType=Pas":87,
85
+ "Degree=Pos|POS=ADV":86,
86
+ "POS=AUX|Tense=Pres|VerbForm=Fin,Inf|VerbType=Mod":87,
87
+ "POS=DET|PronType=Ind":90,
88
+ "POS=X":101,
89
+ "Number=Sing|POS=PROPN":96,
90
+ "POS=PRON|PronType=Ind":95,
91
+ "POS=PART|PartType=Neg":94,
92
+ "POS=VERB|Subcat=Tran|Tense=Past|VerbForm=Part":100,
93
+ "AdjType=Pred|Case=Nom|Degree=Pos|POS=ADJ":84,
94
+ "POS=DET|PronType=Dem":90,
95
+ "Degree=Cmp|POS=ADV":86,
96
+ "Case=Nom|Number=Sing|POS=PRON|Person=3|PronType=Prs":95,
97
+ "POS=SYM":99,
98
+ "Case=Acc,Nom|Number=Plur|POS=PRON|Person=1|PronType=Prs":95,
99
+ "POS=PART|PartType=Gen":94,
100
+ "Case=Acc|Number=Sing|POS=PRON|Person=2|PronType=Prs":95,
101
+ "Number=Sing|POS=PRON|Person=2|PronType=Prs|Reflex=Yes":95,
102
+ "Degree=Sup|POS=ADV":86,
103
+ "Degree=Dim|Number=Sing|POS=NOUN":92,
104
+ "Number=Sing|POS=PRON|Person=2|Poss=Yes|PronType=Prs":95,
105
+ "POS=PRON|PronType=Int":95,
106
+ "Number=Plur|POS=PRON|Person=1|Poss=Yes|PronType=Prs":95,
107
+ "Number=Sing|POS=PRON|Person=3|PronType=Prs|Reflex=Yes":95,
108
+ "Number=Plur|POS=PRON|Person=3|Poss=Yes|PronType=Prs":95,
109
+ "AdjType=Attr|Case=Nom|Degree=Sup|POS=ADJ":84,
110
+ "Case=Nom|Number=Sing|POS=PRON|Person=2|PronType=Prs":95,
111
+ "AdjType=Pred|Case=Nom|Degree=Cmp|POS=ADJ":84,
112
+ "POS=VERB|Subcat=Prep|Tense=Pres|VerbForm=Fin,Inf":100,
113
+ "POS=AUX|Tense=Pres|VerbForm=Fin,Inf|VerbType=Aux":87,
114
+ "Number=Sing|POS=PRON|Person=3|Poss=Yes|PronType=Prs":95,
115
+ "POS=PRON|PronType=Rcp":95,
116
+ "POS=AUX|Tense=Past|VerbForm=Fin|VerbType=Mod":87,
117
+ "Case=Acc,Nom|Number=Plur|POS=PRON|Person=3|PronType=Prs":95,
118
+ "POS=AUX|Tense=Past|VerbForm=Fin|VerbType=Cop":87,
119
+ "Case=Acc|Number=Sing|POS=PRON|Person=3|PronType=Prs":95,
120
+ "Case=Nom|Number=Sing|POS=PRON|Person=1|PronType=Prs":95,
121
+ "Number=Sing|POS=PRON|Person=1|Poss=Yes|PronType=Prs":95,
122
+ "Case=Acc,Nom|Number=Plur|POS=PRON|Person=2|PronType=Prs":95,
123
+ "Number=Plur|POS=PRON|Person=3|PronType=Prs|Reflex=Yes":95,
124
+ "AdjType=Attr|Case=Nom|Degree=Cmp|POS=ADJ":84,
125
+ "Number=Plur|POS=PRON|Person=1|PronType=Prs|Reflex=Yes":95,
126
+ "Case=Acc|Number=Sing|POS=PRON|Person=1|PronType=Prs":95,
127
+ "AdjType=Pred|Case=Nom|Degree=Sup|POS=ADJ":84
128
+ },
129
+ "overwrite":false
130
+ }
morphologizer/model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16dda1c66e95145dbb8553c64200c8540d82d37c8cb99ab4764eb734f0c55069
3
+ size 188226
parser/cfg ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "moves":null,
3
+ "update_with_oracle_cut_size":100,
4
+ "multitasks":[
5
+
6
+ ],
7
+ "min_action_freq":5,
8
+ "learn_tokens":false,
9
+ "beam_width":1,
10
+ "beam_density":0.0,
11
+ "beam_update_prob":0.0,
12
+ "incorrect_spans_key":null
13
+ }
parser/model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:844d75edee6630df2c2d324fc146f8f9b7ee95dc6d77829f29b62bb6ccece85d
3
+ size 591617
parser/moves ADDED
@@ -0,0 +1 @@
 
 
1
+ ��moves�9{"0":{"":18776},"1":{"":13805},"2":{"case":4223,"det":4041,"amod":2134,"nsubj":1929,"obj":1368,"obl":1060,"aux":803,"advmod":673,"mark":629,"nsubj:pass":393,"nummod":327,"punct":244,"cop":224,"nmod":174,"compound:prt":144,"aux:pass":102,"advmod||cop":79,"dep":58,"aux||cop":40,"iobj":22,"cc":20,"ccomp":18,"amod||cop":15,"xcomp":14,"case||cop":10,"obl||cop":5,"nsubj||cop":5},"3":{"punct":2775,"nmod":1926,"conj":1440,"cc":1201,"dep":1066,"obl":1043,"amod":819,"ccomp":623,"aux:pass":565,"obj":468,"advmod":346,"cop":272,"aux":227,"xcomp":177,"flat":145,"case":103,"compound:prt":96,"punct||cop":82,"obl||case":73,"cc||case":71,"appos":47,"nsubj":45,"mark":36,"amod||cop":32,"iobj":20,"advmod||cop":15,"punct||case":12,"cc||nsubj":10,"ccomp||nsubj":10,"conj||cop":9,"cc||cop":8,"mark||cop":7,"cop||nmod":5},"4":{"ROOT":1315}}�cfg��neg_key�
senter/cfg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "overwrite":false
3
+ }
senter/model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55481619d8a72a6b13630c397a33fadf61b19a6d08604c407f408561e98acfa6
3
+ size 6740
tagger/cfg ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "labels":[
3
+ "AOA",
4
+ "AOP",
5
+ "ASA",
6
+ "ASP",
7
+ "AVA",
8
+ "AVP",
9
+ "BO",
10
+ "BS",
11
+ "BV",
12
+ "KN",
13
+ "KO",
14
+ "LB",
15
+ "LO",
16
+ "NA",
17
+ "NEE",
18
+ "NM",
19
+ "NME",
20
+ "NSE",
21
+ "NSED",
22
+ "NSM",
23
+ "PA",
24
+ "PB",
25
+ "PDHEB",
26
+ "PDHEDP",
27
+ "PDHENP",
28
+ "PDHEW",
29
+ "PDMB",
30
+ "PDMP",
31
+ "PDMW",
32
+ "PDOENP",
33
+ "PDOEW",
34
+ "PDVEB",
35
+ "PDVEDP",
36
+ "PDVENP",
37
+ "PDVEW",
38
+ "PEEB",
39
+ "PEEDP",
40
+ "PEENP",
41
+ "PEMB",
42
+ "PEMP",
43
+ "PEMW",
44
+ "PO",
45
+ "PTEB",
46
+ "PTEDP",
47
+ "PTENP",
48
+ "PTEW",
49
+ "PTMP",
50
+ "PV",
51
+ "PW",
52
+ "RA",
53
+ "RK",
54
+ "RL",
55
+ "RO",
56
+ "RS",
57
+ "RSF",
58
+ "RV",
59
+ "RWD",
60
+ "SVS",
61
+ "THAB",
62
+ "THAO",
63
+ "THBB",
64
+ "THBO",
65
+ "THNB",
66
+ "THPB",
67
+ "THPO",
68
+ "TRAB",
69
+ "TRAO",
70
+ "TRBB",
71
+ "UPB",
72
+ "UPD",
73
+ "UPI",
74
+ "UPO",
75
+ "UPS",
76
+ "UPV",
77
+ "UPW",
78
+ "UXD",
79
+ "VTHOG",
80
+ "VTHOK",
81
+ "VTHOO",
82
+ "VTHOV",
83
+ "VTHSG",
84
+ "VTHSO",
85
+ "VTUOA",
86
+ "VTUOM",
87
+ "VTUOP",
88
+ "VUOT",
89
+ "VVHOG",
90
+ "VVHOK",
91
+ "VVHOO",
92
+ "VVUOM",
93
+ "VVUOP",
94
+ "ZE",
95
+ "ZM",
96
+ "ZPL",
97
+ "ZPR"
98
+ ],
99
+ "neg_prefix":"!",
100
+ "overwrite":false
101
+ }
tagger/model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e09c3358834624e8c33485b95a8204cf524ca8f8d8d07d72b14c762e7c18bfb0
3
+ size 292811
transformer/cfg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "max_batch_items":4096
3
+ }
transformer/model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0a65559556652a5714561cf861942d697a8ebcc5e672e32c49d2c6876e45437
3
+ size 1126406104
vocab/key2row ADDED
@@ -0,0 +1 @@
 
 
1
+ �
vocab/lookups.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
3
+ size 1
vocab/strings.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8719f892044d9cd123d46078dd8c1b13dcc09d7ca38d122f71bb4b47e4650e35
3
+ size 275533
vocab/vectors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14772b683e726436d5948ad3fff2b43d036ef2ebbe3458aafed6004e05a40706
3
+ size 128
vocab/vectors.cfg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "mode":"default"
3
+ }