ljvmiranda921 commited on
Commit
756425a
1 Parent(s): fae5465

xx_hbo_sigtyp_trf-0.1.0: Update SIGTYP pipeline

Browse files
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ trainable_lemmatizer/model filter=lfs diff=lfs merge=lfs -text
37
+ transformer/model filter=lfs diff=lfs merge=lfs -text
38
+ xx_hbo_sigtyp_trf-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - spacy
4
+ - token-classification
5
+ language:
6
+ - multilingual
7
+ model-index:
8
+ - name: xx_hbo_sigtyp_trf
9
+ results:
10
+ - task:
11
+ name: TAG
12
+ type: token-classification
13
+ metrics:
14
+ - name: TAG (XPOS) Accuracy
15
+ type: accuracy
16
+ value: 0.1913594209
17
+ - task:
18
+ name: LEMMA
19
+ type: token-classification
20
+ metrics:
21
+ - name: Lemma Accuracy
22
+ type: accuracy
23
+ value: 0.1008821534
24
+ - task:
25
+ name: UNLABELED_DEPENDENCIES
26
+ type: token-classification
27
+ metrics:
28
+ - name: Unlabeled Attachment Score (UAS)
29
+ type: f_score
30
+ value: 0.0602898551
31
+ - task:
32
+ name: LABELED_DEPENDENCIES
33
+ type: token-classification
34
+ metrics:
35
+ - name: Labeled Attachment Score (LAS)
36
+ type: f_score
37
+ value: 0.0483091787
38
+ - task:
39
+ name: SENTS
40
+ type: token-classification
41
+ metrics:
42
+ - name: Sentences F-Score
43
+ type: f_score
44
+ value: 0.6068601583
45
+ ---
46
+ | Feature | Description |
47
+ | --- | --- |
48
+ | **Name** | `xx_hbo_sigtyp_trf` |
49
+ | **Version** | `0.1.0` |
50
+ | **spaCy** | `>=3.6.1,<3.7.0` |
51
+ | **Default Pipeline** | `transformer`, `parser`, `trainable_lemmatizer`, `tagger` |
52
+ | **Components** | `transformer`, `parser`, `trainable_lemmatizer`, `tagger` |
53
+ | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
54
+ | **Sources** | n/a |
55
+ | **License** | n/a |
56
+ | **Author** | [n/a]() |
57
+
58
+ ### Label Scheme
59
+
60
+ <details>
61
+
62
+ <summary>View label scheme (245 labels for 2 components)</summary>
63
+
64
+ | Component | Labels |
65
+ | --- | --- |
66
+ | **`parser`** | `ROOT`, `acl`, `advcl`, `advmod`, `amod`, `appos`, `case`, `cc`, `ccomp`, `compound:smixut`, `conj`, `cop`, `dep`, `det`, `discourse`, `dislocated`, `flat`, `mark`, `nmod`, `nmod:poss`, `nsubj`, `nummod`, `obj`, `obl`, `orphan`, `parataxis`, `punct`, `xcomp` |
67
+ | **`tagger`** | `adjv__Gender=Fem\|Number=Plur`, `adjv__Gender=Fem\|Number=Plur\|NumType=Ord`, `adjv__Gender=Fem\|Number=Sing`, `adjv__Gender=Fem\|Number=Sing\|NumType=Ord`, `adjv__Gender=Masc\|Number=Plur`, `adjv__Gender=Masc\|Number=Plur\|NumType=Ord`, `adjv__Gender=Masc\|Number=Sing`, `adjv__Gender=Masc\|Number=Sing\|NumType=Ord`, `advb`, `art`, `art__PronType=Art`, `conj`, `inrg`, `intj`, `nega__Polarity=Neg`, `nmpr__Gender=Fem\|Number=Sing`, `nmpr__Gender=Masc\|Number=Plur`, `nmpr__Gender=Masc\|Number=Sing`, `nmpr__Number=Sing`, `prde__Gender=Fem\|Number=Sing\|PronType=Dem`, `prde__Gender=Masc\|Number=Sing\|PronType=Dem`, `prde__Number=Plur\|PronType=Dem`, `prep`, `prin__PronType=Int`, `prn__Gender=Fem\|Number=Plur\|Person=2\|PronType=Prs`, `prn__Gender=Fem\|Number=Plur\|Person=3\|PronType=Prs`, `prn__Gender=Fem\|Number=Sing\|Person=2\|PronType=Prs`, `prn__Gender=Fem\|Number=Sing\|Person=3\|PronType=Prs`, `prn__Gender=Masc\|Number=Plur\|Person=2\|PronType=Prs`, `prn__Gender=Masc\|Number=Plur\|Person=3\|PronType=Prs`, `prn__Gender=Masc\|Number=Sing\|Person=2\|PronType=Prs`, `prn__Gender=Masc\|Number=Sing\|Person=3\|PronType=Prs`, `prn__Number=Plur\|Person=1\|PronType=Prs`, `prn__Number=Sing\|Person=1\|PronType=Prs`, `prps__Gender=Fem\|Number=Plur\|Person=2\|PronType=Prs`, `prps__Gender=Fem\|Number=Plur\|Person=3\|PronType=Prs`, `prps__Gender=Fem\|Number=Sing\|Person=2\|PronType=Prs`, `prps__Gender=Fem\|Number=Sing\|Person=3\|PronType=Prs`, `prps__Gender=Masc\|Number=Plur\|Person=2\|PronType=Prs`, `prps__Gender=Masc\|Number=Plur\|Person=3\|PronType=Prs`, `prps__Gender=Masc\|Number=Sing\|Person=2\|PronType=Prs`, `prps__Gender=Masc\|Number=Sing\|Person=3\|PronType=Prs`, `prps__Number=Plur\|Person=1\|PronType=Prs`, `prps__Number=Sing\|Person=1\|PronType=Prs`, `punct`, `subs`, `subs__Gender=Fem\|Number=Dual`, `subs__Gender=Fem\|Number=Dual\|NumType=Card`, `subs__Gender=Fem\|Number=Plur`, `subs__Gender=Fem\|Number=Plur\|NumType=Card`, `subs__Gender=Fem\|Number=Sing`, `subs__Gender=Fem\|Number=Sing\|NumType=Card`, `subs__Gender=Masc\|Number=Dual`, `subs__Gender=Masc\|Number=Plur`, `subs__Gender=Masc\|Number=Plur\|NumType=Card`, `subs__Gender=Masc\|Number=Sing`, `subs__Gender=Masc\|Number=Sing\|NumType=Card`, `subs__Mood=Ind\|VerbForm=Fin`, `subs__Number=Dual\|NumType=Card`, `subs__Number=Sing`, `subs__Number=Sing\|NumType=Card`, `verb`, `verb__Aspect=Imp\|Gender=Fem\|HebBinyan=HIFIL\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Fem\|HebBinyan=NIFAL\|Mood=Ind\|Number=Plur\|Person=2\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Fem\|HebBinyan=NIFAL\|Mood=Ind\|Number=Sing\|Person=2\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Fem\|HebBinyan=NIFAL\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Fem\|HebBinyan=PAAL\|Mood=Ind\|Number=Plur\|Person=2\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Fem\|HebBinyan=PAAL\|Mood=Ind\|Number=Plur\|Person=3\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Fem\|HebBinyan=PAAL\|Mood=Ind\|Number=Sing\|Person=2\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Fem\|HebBinyan=PAAL\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Fem\|HebBinyan=PIEL\|Mood=Ind\|Number=Plur\|Person=2\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Fem\|HebBinyan=PIEL\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Masc\|HebBinyan=HIFIL\|Mood=Ind\|Number=Plur\|Person=2\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Masc\|HebBinyan=HIFIL\|Mood=Ind\|Number=Plur\|Person=3\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Masc\|HebBinyan=HIFIL\|Mood=Ind\|Number=Sing\|Person=2\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Masc\|HebBinyan=HIFIL\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Masc\|HebBinyan=HITPAEL\|Mood=Ind\|Number=Plur\|Person=2\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Masc\|HebBinyan=HITPAEL\|Mood=Ind\|Number=Plur\|Person=3\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Masc\|HebBinyan=NIFAL\|Mood=Ind\|Number=Plur\|Person=2\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Masc\|HebBinyan=NIFAL\|Mood=Ind\|Number=Plur\|Person=3\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Masc\|HebBinyan=NIFAL\|Mood=Ind\|Number=Sing\|Person=2\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Masc\|HebBinyan=NIFAL\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Masc\|HebBinyan=PAAL\|Mood=Ind\|Number=Plur\|Person=2\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Masc\|HebBinyan=PAAL\|Mood=Ind\|Number=Plur\|Person=3\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Masc\|HebBinyan=PAAL\|Mood=Ind\|Number=Sing\|Person=2\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Masc\|HebBinyan=PAAL\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Masc\|HebBinyan=PIEL\|Mood=Ind\|Number=Plur\|Person=2\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Masc\|HebBinyan=PIEL\|Mood=Ind\|Number=Sing\|Person=2\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Masc\|HebBinyan=PIEL\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Masc\|Mood=Ind\|Number=Plur\|Person=3\|VerbForm=Fin`, `verb__Aspect=Imp\|Gender=Masc\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Imp\|HebBinyan=HIFIL\|Mood=Ind\|Number=Plur\|Person=1\|VerbForm=Fin`, `verb__Aspect=Imp\|HebBinyan=HIFIL\|Mood=Ind\|Number=Sing\|Person=1\|VerbForm=Fin`, `verb__Aspect=Imp\|HebBinyan=HITPAEL\|Mood=Ind\|Number=Plur\|Person=1\|VerbForm=Fin`, `verb__Aspect=Imp\|HebBinyan=NIFAL\|Mood=Ind\|Number=Plur\|Person=1\|VerbForm=Fin`, `verb__Aspect=Imp\|HebBinyan=NIFAL\|Mood=Ind\|Number=Sing\|Person=1\|VerbForm=Fin`, `verb__Aspect=Imp\|HebBinyan=PAAL\|Mood=Ind\|Number=Plur\|Person=1\|VerbForm=Fin`, `verb__Aspect=Imp\|HebBinyan=PAAL\|Mood=Ind\|Number=Sing\|Person=1\|VerbForm=Fin`, `verb__Aspect=Imp\|HebBinyan=PIEL\|Mood=Ind\|Number=Plur\|Person=1\|VerbForm=Fin`, `verb__Aspect=Imp\|HebBinyan=PIEL\|Mood=Ind\|Number=Sing\|Person=1\|VerbForm=Fin`, `verb__Aspect=Imp\|Mood=Ind\|Number=Plur\|Person=1\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Fem\|HebBinyan=HIFIL\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Fem\|HebBinyan=NIFAL\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Fem\|HebBinyan=PAAL\|Mood=Ind\|Number=Plur\|Person=2\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Fem\|HebBinyan=PAAL\|Mood=Ind\|Number=Sing\|Person=2\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Fem\|HebBinyan=PAAL\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Fem\|HebBinyan=PIEL\|Mood=Ind\|Number=Sing\|Person=2\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Fem\|HebBinyan=PIEL\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Fem\|HebBinyan=PUAL\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Fem\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Masc\|HebBinyan=HIFIL\|Mood=Ind\|Number=Plur\|Person=2\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Masc\|HebBinyan=HIFIL\|Mood=Ind\|Number=Sing\|Person=2\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Masc\|HebBinyan=HIFIL\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Masc\|HebBinyan=HITPAEL\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Masc\|HebBinyan=NIFAL\|Mood=Ind\|Number=Plur\|Person=2\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Masc\|HebBinyan=NIFAL\|Mood=Ind\|Number=Sing\|Person=2\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Masc\|HebBinyan=NIFAL\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Masc\|HebBinyan=PAAL\|Mood=Ind\|Number=Plur\|Person=2\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Masc\|HebBinyan=PAAL\|Mood=Ind\|Number=Sing\|Person=2\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Masc\|HebBinyan=PAAL\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Masc\|HebBinyan=PIEL\|Mood=Ind\|Number=Plur\|Person=2\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Masc\|HebBinyan=PIEL\|Mood=Ind\|Number=Sing\|Person=2\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Masc\|HebBinyan=PIEL\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Masc\|HebBinyan=PUAL\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Perf\|Gender=Masc\|Mood=Ind\|Number=Sing\|Person=3\|VerbForm=Fin`, `verb__Aspect=Perf\|HebBinyan=HIFIL\|Mood=Ind\|Number=Plur\|Person=1\|VerbForm=Fin`, `verb__Aspect=Perf\|HebBinyan=HIFIL\|Mood=Ind\|Number=Plur\|Person=3\|VerbForm=Fin`, `verb__Aspect=Perf\|HebBinyan=HIFIL\|Mood=Ind\|Number=Sing\|Person=1\|VerbForm=Fin`, `verb__Aspect=Perf\|HebBinyan=HITPAEL\|Mood=Ind\|Number=Plur\|Person=1\|VerbForm=Fin`, `verb__Aspect=Perf\|HebBinyan=HITPAEL\|Mood=Ind\|Number=Plur\|Person=3\|VerbForm=Fin`, `verb__Aspect=Perf\|HebBinyan=HITPAEL\|Mood=Ind\|Number=Sing\|Person=1\|VerbForm=Fin`, `verb__Aspect=Perf\|HebBinyan=NIFAL\|Mood=Ind\|Number=Plur\|Person=1\|VerbForm=Fin`, `verb__Aspect=Perf\|HebBinyan=NIFAL\|Mood=Ind\|Number=Plur\|Person=3\|VerbForm=Fin`, `verb__Aspect=Perf\|HebBinyan=NIFAL\|Mood=Ind\|Number=Sing\|Person=1\|VerbForm=Fin`, `verb__Aspect=Perf\|HebBinyan=PAAL\|Mood=Ind\|Number=Plur\|Person=1\|VerbForm=Fin`, `verb__Aspect=Perf\|HebBinyan=PAAL\|Mood=Ind\|Number=Plur\|Person=3\|VerbForm=Fin`, `verb__Aspect=Perf\|HebBinyan=PAAL\|Mood=Ind\|Number=Sing\|Person=1\|VerbForm=Fin`, `verb__Aspect=Perf\|HebBinyan=PIEL\|Mood=Ind\|Number=Plur\|Person=3\|VerbForm=Fin`, `verb__Aspect=Perf\|HebBinyan=PIEL\|Mood=Ind\|Number=Sing\|Person=1\|VerbForm=Fin`, `verb__Aspect=Perf\|HebBinyan=PUAL\|Mood=Ind\|Number=Plur\|Person=3\|VerbForm=Fin`, `verb__Aspect=Perf\|HebBinyan=PUAL\|Mood=Ind\|Number=Sing\|Person=1\|VerbForm=Fin`, `verb__Aspect=Perf\|Mood=Ind\|Number=Plur\|Person=3\|VerbForm=Fin`, `verb__Gender=Fem\|HebBinyan=HIFIL\|Mood=Imp\|Number=Sing\|Person=2\|VerbForm=Fin`, `verb__Gender=Fem\|HebBinyan=HIFIL\|Mood=Ind\|Number=Plur\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Fem\|HebBinyan=HIFIL\|Mood=Ind\|Number=Sing\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Fem\|HebBinyan=HIFIL\|Number=Plur\|VerbForm=Part`, `verb__Gender=Fem\|HebBinyan=HITPAEL\|Mood=Ind\|Number=Sing\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Fem\|HebBinyan=NIFAL\|Mood=Ind\|Number=Plur\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Fem\|HebBinyan=NIFAL\|Mood=Ind\|Number=Sing\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Fem\|HebBinyan=NIFAL\|Number=Sing\|VerbForm=Part`, `verb__Gender=Fem\|HebBinyan=PAAL\|Mood=Imp\|Number=Plur\|Person=2\|VerbForm=Fin`, `verb__Gender=Fem\|HebBinyan=PAAL\|Mood=Imp\|Number=Sing\|Person=2\|VerbForm=Fin`, `verb__Gender=Fem\|HebBinyan=PAAL\|Mood=Ind\|Number=Plur\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Fem\|HebBinyan=PAAL\|Mood=Ind\|Number=Sing\|Person=2\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Fem\|HebBinyan=PAAL\|Mood=Ind\|Number=Sing\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Fem\|HebBinyan=PAAL\|Number=Plur\|VerbForm=Part`, `verb__Gender=Fem\|HebBinyan=PAAL\|Number=Plur\|VerbForm=Part\|Voice=Pass`, `verb__Gender=Fem\|HebBinyan=PAAL\|Number=Sing\|VerbForm=Part`, `verb__Gender=Fem\|HebBinyan=PAAL\|Number=Sing\|VerbForm=Part\|Voice=Pass`, `verb__Gender=Fem\|HebBinyan=PIEL\|Mood=Ind\|Number=Sing\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Fem\|HebBinyan=PIEL\|Number=Sing\|VerbForm=Part`, `verb__Gender=Fem\|Mood=Ind\|Number=Plur\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Fem\|Mood=Ind\|Number=Sing\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Fem\|Number=Sing\|VerbForm=Part\|Voice=Pass`, `verb__Gender=Masc\|HebBinyan=HIFIL\|Mood=Imp\|Number=Plur\|Person=2\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=HIFIL\|Mood=Imp\|Number=Sing\|Person=2\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=HIFIL\|Mood=Ind\|Number=Plur\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=HIFIL\|Mood=Ind\|Number=Sing\|Person=2\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=HIFIL\|Mood=Ind\|Number=Sing\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=HIFIL\|Number=Plur\|VerbForm=Part`, `verb__Gender=Masc\|HebBinyan=HIFIL\|Number=Sing\|VerbForm=Part`, `verb__Gender=Masc\|HebBinyan=HITPAEL\|Mood=Imp\|Number=Plur\|Person=2\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=HITPAEL\|Mood=Imp\|Number=Sing\|Person=2\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=HITPAEL\|Mood=Ind\|Number=Plur\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=HITPAEL\|Mood=Ind\|Number=Sing\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=HITPAEL\|Number=Sing\|VerbForm=Part`, `verb__Gender=Masc\|HebBinyan=NIFAL\|Mood=Imp\|Number=Plur\|Person=2\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=NIFAL\|Mood=Imp\|Number=Sing\|Person=2\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=NIFAL\|Mood=Ind\|Number=Plur\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=NIFAL\|Mood=Ind\|Number=Sing\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=NIFAL\|Number=Plur\|VerbForm=Part`, `verb__Gender=Masc\|HebBinyan=NIFAL\|Number=Sing\|VerbForm=Part`, `verb__Gender=Masc\|HebBinyan=PAAL\|Mood=Imp\|Number=Plur\|Person=2\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=PAAL\|Mood=Imp\|Number=Sing\|Person=2\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=PAAL\|Mood=Ind\|Number=Plur\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=PAAL\|Mood=Ind\|Number=Sing\|Person=2\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=PAAL\|Mood=Ind\|Number=Sing\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=PAAL\|Number=Plur\|VerbForm=Part`, `verb__Gender=Masc\|HebBinyan=PAAL\|Number=Plur\|VerbForm=Part\|Voice=Pass`, `verb__Gender=Masc\|HebBinyan=PAAL\|Number=Sing\|VerbForm=Part`, `verb__Gender=Masc\|HebBinyan=PAAL\|Number=Sing\|VerbForm=Part\|Voice=Pass`, `verb__Gender=Masc\|HebBinyan=PIEL\|Mood=Imp\|Number=Plur\|Person=2\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=PIEL\|Mood=Imp\|Number=Sing\|Person=2\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=PIEL\|Mood=Ind\|Number=Plur\|Person=2\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=PIEL\|Mood=Ind\|Number=Plur\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=PIEL\|Mood=Ind\|Number=Sing\|Person=2\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=PIEL\|Mood=Ind\|Number=Sing\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Masc\|HebBinyan=PIEL\|Number=Plur\|VerbForm=Part`, `verb__Gender=Masc\|HebBinyan=PIEL\|Number=Sing\|VerbForm=Part`, `verb__Gender=Masc\|HebBinyan=PUAL\|Mood=Ind\|Number=Plur\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Masc\|Mood=Ind\|Number=Plur\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Masc\|Mood=Ind\|Number=Sing\|Person=3\|Tense=Past\|VerbForm=Fin`, `verb__Gender=Masc\|Number=Plur\|VerbForm=Part\|Voice=Pass`, `verb__Gender=Masc\|Number=Sing\|VerbForm=Part\|Voice=Pass`, `verb__HebBinyan=HIFIL\|Mood=Ind\|Number=Plur\|Person=1\|Tense=Past\|VerbForm=Fin`, `verb__HebBinyan=HIFIL\|VerbForm=Inf`, `verb__HebBinyan=HITPAEL\|VerbForm=Inf`, `verb__HebBinyan=NIFAL\|Mood=Ind\|Number=Sing\|Person=1\|Tense=Past\|VerbForm=Fin`, `verb__HebBinyan=NIFAL\|VerbForm=Inf`, `verb__HebBinyan=PAAL\|Mood=Ind\|Number=Plur\|Person=1\|Tense=Past\|VerbForm=Fin`, `verb__HebBinyan=PAAL\|Mood=Ind\|Number=Sing\|Person=1\|Tense=Past\|VerbForm=Fin`, `verb__HebBinyan=PAAL\|VerbForm=Inf`, `verb__HebBinyan=PIEL\|Mood=Ind\|Number=Plur\|Person=1\|Tense=Past\|VerbForm=Fin`, `verb__HebBinyan=PIEL\|Mood=Ind\|Number=Sing\|Person=1\|Tense=Past\|VerbForm=Fin`, `verb__HebBinyan=PIEL\|VerbForm=Inf`, `verb__Mood=Ind\|Number=Sing\|Person=1\|Tense=Past\|VerbForm=Fin`, `verb__VerbForm=Inf` |
68
+
69
+ </details>
70
+
71
+ ### Accuracy
72
+
73
+ | Type | Score |
74
+ | --- | --- |
75
+ | `DEP_UAS` | 6.03 |
76
+ | `DEP_LAS` | 4.83 |
77
+ | `SENTS_P` | 52.04 |
78
+ | `SENTS_R` | 72.78 |
79
+ | `SENTS_F` | 60.69 |
80
+ | `LEMMA_ACC` | 10.09 |
81
+ | `TAG_ACC` | 19.14 |
82
+ | `TRANSFORMER_LOSS` | 22033.75 |
83
+ | `PARSER_LOSS` | 27367.67 |
84
+ | `TRAINABLE_LEMMATIZER_LOSS` | 1633.45 |
85
+ | `TAGGER_LOSS` | 2051.87 |
config.cfg ADDED
@@ -0,0 +1,190 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [paths]
2
+ train = "corpus/train/hbo_train.spacy"
3
+ dev = "corpus/dev/hbo_valid.spacy"
4
+ vectors = null
5
+ init_tok2vec = null
6
+
7
+ [system]
8
+ gpu_allocator = "pytorch"
9
+ seed = 42
10
+
11
+ [nlp]
12
+ lang = "xx"
13
+ pipeline = ["transformer","parser","trainable_lemmatizer","tagger"]
14
+ batch_size = 128
15
+ disabled = []
16
+ before_creation = null
17
+ after_creation = null
18
+ after_pipeline_creation = null
19
+ tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
20
+
21
+ [components]
22
+
23
+ [components.parser]
24
+ factory = "parser"
25
+ learn_tokens = false
26
+ min_action_freq = 30
27
+ moves = null
28
+ scorer = {"@scorers":"spacy.parser_scorer.v1"}
29
+ update_with_oracle_cut_size = 100
30
+
31
+ [components.parser.model]
32
+ @architectures = "spacy.TransitionBasedParser.v2"
33
+ state_type = "parser"
34
+ extra_state_tokens = false
35
+ hidden_width = 128
36
+ maxout_pieces = 3
37
+ use_upper = false
38
+ nO = null
39
+
40
+ [components.parser.model.tok2vec]
41
+ @architectures = "spacy-transformers.TransformerListener.v1"
42
+ grad_factor = 1.0
43
+ pooling = {"@layers":"reduce_mean.v1"}
44
+ upstream = "*"
45
+
46
+ [components.tagger]
47
+ factory = "tagger"
48
+ label_smoothing = 0.0
49
+ neg_prefix = "!"
50
+ overwrite = false
51
+ scorer = {"@scorers":"spacy.tagger_scorer.v1"}
52
+
53
+ [components.tagger.model]
54
+ @architectures = "spacy.Tagger.v2"
55
+ nO = null
56
+ normalize = false
57
+
58
+ [components.tagger.model.tok2vec]
59
+ @architectures = "spacy-transformers.TransformerListener.v1"
60
+ grad_factor = 1.0
61
+ pooling = {"@layers":"reduce_mean.v1"}
62
+ upstream = "*"
63
+
64
+ [components.trainable_lemmatizer]
65
+ factory = "trainable_lemmatizer"
66
+ backoff = "orth"
67
+ min_tree_freq = 3
68
+ overwrite = false
69
+ scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
70
+ top_k = 1
71
+
72
+ [components.trainable_lemmatizer.model]
73
+ @architectures = "spacy.Tagger.v2"
74
+ nO = null
75
+ normalize = false
76
+
77
+ [components.trainable_lemmatizer.model.tok2vec]
78
+ @architectures = "spacy-transformers.TransformerListener.v1"
79
+ grad_factor = 1.0
80
+ pooling = {"@layers":"reduce_mean.v1"}
81
+ upstream = "*"
82
+
83
+ [components.transformer]
84
+ factory = "transformer"
85
+ max_batch_items = 4096
86
+ set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
87
+
88
+ [components.transformer.model]
89
+ @architectures = "spacy-transformers.TransformerModel.v3"
90
+ name = "ljvmiranda921/LiBERTus-base"
91
+ mixed_precision = false
92
+
93
+ [components.transformer.model.get_spans]
94
+ @span_getters = "spacy-transformers.strided_spans.v1"
95
+ window = 128
96
+ stride = 96
97
+
98
+ [components.transformer.model.grad_scaler_config]
99
+
100
+ [components.transformer.model.tokenizer_config]
101
+ use_fast = true
102
+
103
+ [components.transformer.model.transformer_config]
104
+
105
+ [corpora]
106
+
107
+ [corpora.dev]
108
+ @readers = "spacy.Corpus.v1"
109
+ path = ${paths.dev}
110
+ max_length = 0
111
+ gold_preproc = false
112
+ limit = 0
113
+ augmenter = null
114
+
115
+ [corpora.train]
116
+ @readers = "spacy.Corpus.v1"
117
+ path = ${paths.train}
118
+ max_length = 0
119
+ gold_preproc = false
120
+ limit = 0
121
+ augmenter = null
122
+
123
+ [training]
124
+ accumulate_gradient = 3
125
+ dev_corpus = "corpora.dev"
126
+ train_corpus = "corpora.train"
127
+ seed = ${system.seed}
128
+ gpu_allocator = ${system.gpu_allocator}
129
+ dropout = 0.1
130
+ patience = 1600
131
+ max_epochs = 0
132
+ max_steps = 20000
133
+ eval_frequency = 200
134
+ frozen_components = []
135
+ annotating_components = []
136
+ before_to_disk = null
137
+ before_update = null
138
+
139
+ [training.batcher]
140
+ @batchers = "spacy.batch_by_padded.v1"
141
+ discard_oversize = true
142
+ size = 2000
143
+ buffer = 256
144
+ get_length = null
145
+
146
+ [training.logger]
147
+ @loggers = "spacy.ConsoleLogger.v3"
148
+ console_output = true
149
+ progress_bar = "eval"
150
+ output_file = null
151
+
152
+ [training.optimizer]
153
+ @optimizers = "Adam.v1"
154
+ beta1 = 0.9
155
+ beta2 = 0.999
156
+ L2_is_weight_decay = true
157
+ L2 = 0.01
158
+ grad_clip = 1.0
159
+ use_averages = false
160
+ eps = 0.00000001
161
+
162
+ [training.optimizer.learn_rate]
163
+ @schedules = "warmup_linear.v1"
164
+ warmup_steps = 250
165
+ total_steps = 20000
166
+ initial_rate = 0.00005
167
+
168
+ [training.score_weights]
169
+ dep_uas = 0.17
170
+ dep_las = 0.17
171
+ dep_las_per_type = null
172
+ sents_p = null
173
+ sents_r = null
174
+ sents_f = 0.0
175
+ lemma_acc = 0.33
176
+ tag_acc = 0.33
177
+
178
+ [pretraining]
179
+
180
+ [initialize]
181
+ vectors = ${paths.vectors}
182
+ init_tok2vec = ${paths.init_tok2vec}
183
+ vocab_data = null
184
+ lookups = null
185
+ before_init = null
186
+ after_init = null
187
+
188
+ [initialize.components]
189
+
190
+ [initialize.tokenizer]
meta.json ADDED
@@ -0,0 +1,455 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "lang":"xx",
3
+ "name":"hbo_sigtyp_trf",
4
+ "version":"0.1.0",
5
+ "description":"",
6
+ "author":"",
7
+ "email":"",
8
+ "url":"",
9
+ "license":"",
10
+ "spacy_version":">=3.6.1,<3.7.0",
11
+ "spacy_git_version":"458bc5f45",
12
+ "vectors":{
13
+ "width":0,
14
+ "vectors":0,
15
+ "keys":0,
16
+ "name":null
17
+ },
18
+ "labels":{
19
+ "transformer":[
20
+
21
+ ],
22
+ "parser":[
23
+ "ROOT",
24
+ "acl",
25
+ "advcl",
26
+ "advmod",
27
+ "amod",
28
+ "appos",
29
+ "case",
30
+ "cc",
31
+ "ccomp",
32
+ "compound:smixut",
33
+ "conj",
34
+ "cop",
35
+ "dep",
36
+ "det",
37
+ "discourse",
38
+ "dislocated",
39
+ "flat",
40
+ "mark",
41
+ "nmod",
42
+ "nmod:poss",
43
+ "nsubj",
44
+ "nummod",
45
+ "obj",
46
+ "obl",
47
+ "orphan",
48
+ "parataxis",
49
+ "punct",
50
+ "xcomp"
51
+ ],
52
+ "tagger":[
53
+ "adjv__Gender=Fem|Number=Plur",
54
+ "adjv__Gender=Fem|Number=Plur|NumType=Ord",
55
+ "adjv__Gender=Fem|Number=Sing",
56
+ "adjv__Gender=Fem|Number=Sing|NumType=Ord",
57
+ "adjv__Gender=Masc|Number=Plur",
58
+ "adjv__Gender=Masc|Number=Plur|NumType=Ord",
59
+ "adjv__Gender=Masc|Number=Sing",
60
+ "adjv__Gender=Masc|Number=Sing|NumType=Ord",
61
+ "advb",
62
+ "art",
63
+ "art__PronType=Art",
64
+ "conj",
65
+ "inrg",
66
+ "intj",
67
+ "nega__Polarity=Neg",
68
+ "nmpr__Gender=Fem|Number=Sing",
69
+ "nmpr__Gender=Masc|Number=Plur",
70
+ "nmpr__Gender=Masc|Number=Sing",
71
+ "nmpr__Number=Sing",
72
+ "prde__Gender=Fem|Number=Sing|PronType=Dem",
73
+ "prde__Gender=Masc|Number=Sing|PronType=Dem",
74
+ "prde__Number=Plur|PronType=Dem",
75
+ "prep",
76
+ "prin__PronType=Int",
77
+ "prn__Gender=Fem|Number=Plur|Person=2|PronType=Prs",
78
+ "prn__Gender=Fem|Number=Plur|Person=3|PronType=Prs",
79
+ "prn__Gender=Fem|Number=Sing|Person=2|PronType=Prs",
80
+ "prn__Gender=Fem|Number=Sing|Person=3|PronType=Prs",
81
+ "prn__Gender=Masc|Number=Plur|Person=2|PronType=Prs",
82
+ "prn__Gender=Masc|Number=Plur|Person=3|PronType=Prs",
83
+ "prn__Gender=Masc|Number=Sing|Person=2|PronType=Prs",
84
+ "prn__Gender=Masc|Number=Sing|Person=3|PronType=Prs",
85
+ "prn__Number=Plur|Person=1|PronType=Prs",
86
+ "prn__Number=Sing|Person=1|PronType=Prs",
87
+ "prps__Gender=Fem|Number=Plur|Person=2|PronType=Prs",
88
+ "prps__Gender=Fem|Number=Plur|Person=3|PronType=Prs",
89
+ "prps__Gender=Fem|Number=Sing|Person=2|PronType=Prs",
90
+ "prps__Gender=Fem|Number=Sing|Person=3|PronType=Prs",
91
+ "prps__Gender=Masc|Number=Plur|Person=2|PronType=Prs",
92
+ "prps__Gender=Masc|Number=Plur|Person=3|PronType=Prs",
93
+ "prps__Gender=Masc|Number=Sing|Person=2|PronType=Prs",
94
+ "prps__Gender=Masc|Number=Sing|Person=3|PronType=Prs",
95
+ "prps__Number=Plur|Person=1|PronType=Prs",
96
+ "prps__Number=Sing|Person=1|PronType=Prs",
97
+ "punct",
98
+ "subs",
99
+ "subs__Gender=Fem|Number=Dual",
100
+ "subs__Gender=Fem|Number=Dual|NumType=Card",
101
+ "subs__Gender=Fem|Number=Plur",
102
+ "subs__Gender=Fem|Number=Plur|NumType=Card",
103
+ "subs__Gender=Fem|Number=Sing",
104
+ "subs__Gender=Fem|Number=Sing|NumType=Card",
105
+ "subs__Gender=Masc|Number=Dual",
106
+ "subs__Gender=Masc|Number=Plur",
107
+ "subs__Gender=Masc|Number=Plur|NumType=Card",
108
+ "subs__Gender=Masc|Number=Sing",
109
+ "subs__Gender=Masc|Number=Sing|NumType=Card",
110
+ "subs__Mood=Ind|VerbForm=Fin",
111
+ "subs__Number=Dual|NumType=Card",
112
+ "subs__Number=Sing",
113
+ "subs__Number=Sing|NumType=Card",
114
+ "verb",
115
+ "verb__Aspect=Imp|Gender=Fem|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
116
+ "verb__Aspect=Imp|Gender=Fem|HebBinyan=NIFAL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
117
+ "verb__Aspect=Imp|Gender=Fem|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
118
+ "verb__Aspect=Imp|Gender=Fem|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
119
+ "verb__Aspect=Imp|Gender=Fem|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
120
+ "verb__Aspect=Imp|Gender=Fem|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
121
+ "verb__Aspect=Imp|Gender=Fem|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
122
+ "verb__Aspect=Imp|Gender=Fem|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
123
+ "verb__Aspect=Imp|Gender=Fem|HebBinyan=PIEL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
124
+ "verb__Aspect=Imp|Gender=Fem|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
125
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=HIFIL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
126
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=HIFIL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
127
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
128
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
129
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=HITPAEL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
130
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=HITPAEL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
131
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=NIFAL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
132
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=NIFAL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
133
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
134
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
135
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
136
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
137
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
138
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
139
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=PIEL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
140
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
141
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
142
+ "verb__Aspect=Imp|Gender=Masc|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
143
+ "verb__Aspect=Imp|Gender=Masc|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
144
+ "verb__Aspect=Imp|HebBinyan=HIFIL|Mood=Ind|Number=Plur|Person=1|VerbForm=Fin",
145
+ "verb__Aspect=Imp|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=1|VerbForm=Fin",
146
+ "verb__Aspect=Imp|HebBinyan=HITPAEL|Mood=Ind|Number=Plur|Person=1|VerbForm=Fin",
147
+ "verb__Aspect=Imp|HebBinyan=NIFAL|Mood=Ind|Number=Plur|Person=1|VerbForm=Fin",
148
+ "verb__Aspect=Imp|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=1|VerbForm=Fin",
149
+ "verb__Aspect=Imp|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=1|VerbForm=Fin",
150
+ "verb__Aspect=Imp|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=1|VerbForm=Fin",
151
+ "verb__Aspect=Imp|HebBinyan=PIEL|Mood=Ind|Number=Plur|Person=1|VerbForm=Fin",
152
+ "verb__Aspect=Imp|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=1|VerbForm=Fin",
153
+ "verb__Aspect=Imp|Mood=Ind|Number=Plur|Person=1|VerbForm=Fin",
154
+ "verb__Aspect=Perf|Gender=Fem|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
155
+ "verb__Aspect=Perf|Gender=Fem|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
156
+ "verb__Aspect=Perf|Gender=Fem|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
157
+ "verb__Aspect=Perf|Gender=Fem|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
158
+ "verb__Aspect=Perf|Gender=Fem|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
159
+ "verb__Aspect=Perf|Gender=Fem|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
160
+ "verb__Aspect=Perf|Gender=Fem|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
161
+ "verb__Aspect=Perf|Gender=Fem|HebBinyan=PUAL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
162
+ "verb__Aspect=Perf|Gender=Fem|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
163
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=HIFIL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
164
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
165
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
166
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=HITPAEL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
167
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=NIFAL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
168
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
169
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
170
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
171
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
172
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
173
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=PIEL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
174
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
175
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
176
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=PUAL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
177
+ "verb__Aspect=Perf|Gender=Masc|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
178
+ "verb__Aspect=Perf|HebBinyan=HIFIL|Mood=Ind|Number=Plur|Person=1|VerbForm=Fin",
179
+ "verb__Aspect=Perf|HebBinyan=HIFIL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
180
+ "verb__Aspect=Perf|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=1|VerbForm=Fin",
181
+ "verb__Aspect=Perf|HebBinyan=HITPAEL|Mood=Ind|Number=Plur|Person=1|VerbForm=Fin",
182
+ "verb__Aspect=Perf|HebBinyan=HITPAEL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
183
+ "verb__Aspect=Perf|HebBinyan=HITPAEL|Mood=Ind|Number=Sing|Person=1|VerbForm=Fin",
184
+ "verb__Aspect=Perf|HebBinyan=NIFAL|Mood=Ind|Number=Plur|Person=1|VerbForm=Fin",
185
+ "verb__Aspect=Perf|HebBinyan=NIFAL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
186
+ "verb__Aspect=Perf|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=1|VerbForm=Fin",
187
+ "verb__Aspect=Perf|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=1|VerbForm=Fin",
188
+ "verb__Aspect=Perf|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
189
+ "verb__Aspect=Perf|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=1|VerbForm=Fin",
190
+ "verb__Aspect=Perf|HebBinyan=PIEL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
191
+ "verb__Aspect=Perf|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=1|VerbForm=Fin",
192
+ "verb__Aspect=Perf|HebBinyan=PUAL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
193
+ "verb__Aspect=Perf|HebBinyan=PUAL|Mood=Ind|Number=Sing|Person=1|VerbForm=Fin",
194
+ "verb__Aspect=Perf|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
195
+ "verb__Gender=Fem|HebBinyan=HIFIL|Mood=Imp|Number=Sing|Person=2|VerbForm=Fin",
196
+ "verb__Gender=Fem|HebBinyan=HIFIL|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
197
+ "verb__Gender=Fem|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
198
+ "verb__Gender=Fem|HebBinyan=HIFIL|Number=Plur|VerbForm=Part",
199
+ "verb__Gender=Fem|HebBinyan=HITPAEL|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
200
+ "verb__Gender=Fem|HebBinyan=NIFAL|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
201
+ "verb__Gender=Fem|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
202
+ "verb__Gender=Fem|HebBinyan=NIFAL|Number=Sing|VerbForm=Part",
203
+ "verb__Gender=Fem|HebBinyan=PAAL|Mood=Imp|Number=Plur|Person=2|VerbForm=Fin",
204
+ "verb__Gender=Fem|HebBinyan=PAAL|Mood=Imp|Number=Sing|Person=2|VerbForm=Fin",
205
+ "verb__Gender=Fem|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
206
+ "verb__Gender=Fem|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=2|Tense=Past|VerbForm=Fin",
207
+ "verb__Gender=Fem|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
208
+ "verb__Gender=Fem|HebBinyan=PAAL|Number=Plur|VerbForm=Part",
209
+ "verb__Gender=Fem|HebBinyan=PAAL|Number=Plur|VerbForm=Part|Voice=Pass",
210
+ "verb__Gender=Fem|HebBinyan=PAAL|Number=Sing|VerbForm=Part",
211
+ "verb__Gender=Fem|HebBinyan=PAAL|Number=Sing|VerbForm=Part|Voice=Pass",
212
+ "verb__Gender=Fem|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
213
+ "verb__Gender=Fem|HebBinyan=PIEL|Number=Sing|VerbForm=Part",
214
+ "verb__Gender=Fem|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
215
+ "verb__Gender=Fem|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
216
+ "verb__Gender=Fem|Number=Sing|VerbForm=Part|Voice=Pass",
217
+ "verb__Gender=Masc|HebBinyan=HIFIL|Mood=Imp|Number=Plur|Person=2|VerbForm=Fin",
218
+ "verb__Gender=Masc|HebBinyan=HIFIL|Mood=Imp|Number=Sing|Person=2|VerbForm=Fin",
219
+ "verb__Gender=Masc|HebBinyan=HIFIL|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
220
+ "verb__Gender=Masc|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=2|Tense=Past|VerbForm=Fin",
221
+ "verb__Gender=Masc|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
222
+ "verb__Gender=Masc|HebBinyan=HIFIL|Number=Plur|VerbForm=Part",
223
+ "verb__Gender=Masc|HebBinyan=HIFIL|Number=Sing|VerbForm=Part",
224
+ "verb__Gender=Masc|HebBinyan=HITPAEL|Mood=Imp|Number=Plur|Person=2|VerbForm=Fin",
225
+ "verb__Gender=Masc|HebBinyan=HITPAEL|Mood=Imp|Number=Sing|Person=2|VerbForm=Fin",
226
+ "verb__Gender=Masc|HebBinyan=HITPAEL|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
227
+ "verb__Gender=Masc|HebBinyan=HITPAEL|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
228
+ "verb__Gender=Masc|HebBinyan=HITPAEL|Number=Sing|VerbForm=Part",
229
+ "verb__Gender=Masc|HebBinyan=NIFAL|Mood=Imp|Number=Plur|Person=2|VerbForm=Fin",
230
+ "verb__Gender=Masc|HebBinyan=NIFAL|Mood=Imp|Number=Sing|Person=2|VerbForm=Fin",
231
+ "verb__Gender=Masc|HebBinyan=NIFAL|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
232
+ "verb__Gender=Masc|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
233
+ "verb__Gender=Masc|HebBinyan=NIFAL|Number=Plur|VerbForm=Part",
234
+ "verb__Gender=Masc|HebBinyan=NIFAL|Number=Sing|VerbForm=Part",
235
+ "verb__Gender=Masc|HebBinyan=PAAL|Mood=Imp|Number=Plur|Person=2|VerbForm=Fin",
236
+ "verb__Gender=Masc|HebBinyan=PAAL|Mood=Imp|Number=Sing|Person=2|VerbForm=Fin",
237
+ "verb__Gender=Masc|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
238
+ "verb__Gender=Masc|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=2|Tense=Past|VerbForm=Fin",
239
+ "verb__Gender=Masc|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
240
+ "verb__Gender=Masc|HebBinyan=PAAL|Number=Plur|VerbForm=Part",
241
+ "verb__Gender=Masc|HebBinyan=PAAL|Number=Plur|VerbForm=Part|Voice=Pass",
242
+ "verb__Gender=Masc|HebBinyan=PAAL|Number=Sing|VerbForm=Part",
243
+ "verb__Gender=Masc|HebBinyan=PAAL|Number=Sing|VerbForm=Part|Voice=Pass",
244
+ "verb__Gender=Masc|HebBinyan=PIEL|Mood=Imp|Number=Plur|Person=2|VerbForm=Fin",
245
+ "verb__Gender=Masc|HebBinyan=PIEL|Mood=Imp|Number=Sing|Person=2|VerbForm=Fin",
246
+ "verb__Gender=Masc|HebBinyan=PIEL|Mood=Ind|Number=Plur|Person=2|Tense=Past|VerbForm=Fin",
247
+ "verb__Gender=Masc|HebBinyan=PIEL|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
248
+ "verb__Gender=Masc|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=2|Tense=Past|VerbForm=Fin",
249
+ "verb__Gender=Masc|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
250
+ "verb__Gender=Masc|HebBinyan=PIEL|Number=Plur|VerbForm=Part",
251
+ "verb__Gender=Masc|HebBinyan=PIEL|Number=Sing|VerbForm=Part",
252
+ "verb__Gender=Masc|HebBinyan=PUAL|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
253
+ "verb__Gender=Masc|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
254
+ "verb__Gender=Masc|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
255
+ "verb__Gender=Masc|Number=Plur|VerbForm=Part|Voice=Pass",
256
+ "verb__Gender=Masc|Number=Sing|VerbForm=Part|Voice=Pass",
257
+ "verb__HebBinyan=HIFIL|Mood=Ind|Number=Plur|Person=1|Tense=Past|VerbForm=Fin",
258
+ "verb__HebBinyan=HIFIL|VerbForm=Inf",
259
+ "verb__HebBinyan=HITPAEL|VerbForm=Inf",
260
+ "verb__HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=1|Tense=Past|VerbForm=Fin",
261
+ "verb__HebBinyan=NIFAL|VerbForm=Inf",
262
+ "verb__HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=1|Tense=Past|VerbForm=Fin",
263
+ "verb__HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=1|Tense=Past|VerbForm=Fin",
264
+ "verb__HebBinyan=PAAL|VerbForm=Inf",
265
+ "verb__HebBinyan=PIEL|Mood=Ind|Number=Plur|Person=1|Tense=Past|VerbForm=Fin",
266
+ "verb__HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=1|Tense=Past|VerbForm=Fin",
267
+ "verb__HebBinyan=PIEL|VerbForm=Inf",
268
+ "verb__Mood=Ind|Number=Sing|Person=1|Tense=Past|VerbForm=Fin",
269
+ "verb__VerbForm=Inf"
270
+ ]
271
+ },
272
+ "pipeline":[
273
+ "transformer",
274
+ "parser",
275
+ "trainable_lemmatizer",
276
+ "tagger"
277
+ ],
278
+ "components":[
279
+ "transformer",
280
+ "parser",
281
+ "trainable_lemmatizer",
282
+ "tagger"
283
+ ],
284
+ "disabled":[
285
+
286
+ ],
287
+ "performance":{
288
+ "dep_uas":0.0602898551,
289
+ "dep_las":0.0483091787,
290
+ "dep_las_per_type":{
291
+ "cc":{
292
+ "p":0.0,
293
+ "r":0.0,
294
+ "f":0.0
295
+ },
296
+ "root":{
297
+ "p":0.2692307692,
298
+ "r":0.0886075949,
299
+ "f":0.1333333333
300
+ },
301
+ "nsubj":{
302
+ "p":0.3921568627,
303
+ "r":0.0735294118,
304
+ "f":0.1238390093
305
+ },
306
+ "case":{
307
+ "p":1.0,
308
+ "r":0.0043763676,
309
+ "f":0.0087145969
310
+ },
311
+ "obj":{
312
+ "p":0.1818181818,
313
+ "r":0.0109289617,
314
+ "f":0.0206185567
315
+ },
316
+ "mark":{
317
+ "p":0.8421052632,
318
+ "r":0.1927710843,
319
+ "f":0.3137254902
320
+ },
321
+ "advmod":{
322
+ "p":0.6153846154,
323
+ "r":0.131147541,
324
+ "f":0.2162162162
325
+ },
326
+ "ccomp":{
327
+ "p":0.125,
328
+ "r":0.012987013,
329
+ "f":0.0235294118
330
+ },
331
+ "obl":{
332
+ "p":0.0,
333
+ "r":0.0,
334
+ "f":0.0
335
+ },
336
+ "det":{
337
+ "p":0.0,
338
+ "r":0.0,
339
+ "f":0.0
340
+ },
341
+ "conj":{
342
+ "p":0.5714285714,
343
+ "r":0.0377358491,
344
+ "f":0.0707964602
345
+ },
346
+ "dislocated":{
347
+ "p":0.0,
348
+ "r":0.0,
349
+ "f":0.0
350
+ },
351
+ "nmod:poss":{
352
+ "p":0.0,
353
+ "r":0.0,
354
+ "f":0.0
355
+ },
356
+ "discourse":{
357
+ "p":0.5,
358
+ "r":0.0476190476,
359
+ "f":0.0869565217
360
+ },
361
+ "compound:smixut":{
362
+ "p":0.5476190476,
363
+ "r":0.1055045872,
364
+ "f":0.1769230769
365
+ },
366
+ "parataxis":{
367
+ "p":0.1875,
368
+ "r":0.0555555556,
369
+ "f":0.0857142857
370
+ },
371
+ "xcomp":{
372
+ "p":0.0,
373
+ "r":0.0,
374
+ "f":0.0
375
+ },
376
+ "appos":{
377
+ "p":0.5185185185,
378
+ "r":0.1866666667,
379
+ "f":0.2745098039
380
+ },
381
+ "nmod":{
382
+ "p":0.0,
383
+ "r":0.0,
384
+ "f":0.0
385
+ },
386
+ "cop":{
387
+ "p":0.5,
388
+ "r":0.0357142857,
389
+ "f":0.0666666667
390
+ },
391
+ "acl":{
392
+ "p":0.0,
393
+ "r":0.0,
394
+ "f":0.0
395
+ },
396
+ "advcl":{
397
+ "p":0.0,
398
+ "r":0.0,
399
+ "f":0.0
400
+ },
401
+ "nummod":{
402
+ "p":0.875,
403
+ "r":0.2121212121,
404
+ "f":0.3414634146
405
+ },
406
+ "vocative":{
407
+ "p":0.0,
408
+ "r":0.0,
409
+ "f":0.0
410
+ },
411
+ "amod":{
412
+ "p":0.0,
413
+ "r":0.0,
414
+ "f":0.0
415
+ },
416
+ "csubj":{
417
+ "p":0.0,
418
+ "r":0.0,
419
+ "f":0.0
420
+ },
421
+ "orphan":{
422
+ "p":0.0,
423
+ "r":0.0,
424
+ "f":0.0
425
+ },
426
+ "flat":{
427
+ "p":1.0,
428
+ "r":0.1666666667,
429
+ "f":0.2857142857
430
+ },
431
+ "flat:name":{
432
+ "p":0.0,
433
+ "r":0.0,
434
+ "f":0.0
435
+ },
436
+ "dep":{
437
+ "p":0.0,
438
+ "r":0.0,
439
+ "f":0.0
440
+ }
441
+ },
442
+ "sents_p":0.520361991,
443
+ "sents_r":0.7278481013,
444
+ "sents_f":0.6068601583,
445
+ "lemma_acc":0.1008821534,
446
+ "tag_acc":0.1913594209,
447
+ "transformer_loss":220.337518194,
448
+ "parser_loss":273.6766829933,
449
+ "trainable_lemmatizer_loss":16.3345091687,
450
+ "tagger_loss":20.5187227235
451
+ },
452
+ "requirements":[
453
+ "spacy-transformers>=1.3.3,<1.4.0"
454
+ ]
455
+ }
parser/cfg ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "moves":null,
3
+ "update_with_oracle_cut_size":100,
4
+ "multitasks":[
5
+
6
+ ],
7
+ "min_action_freq":30,
8
+ "learn_tokens":false,
9
+ "beam_width":1,
10
+ "beam_density":0.0,
11
+ "beam_update_prob":0.0,
12
+ "incorrect_spans_key":null
13
+ }
parser/model ADDED
Binary file (890 kB). View file
 
parser/moves ADDED
@@ -0,0 +1 @@
 
 
1
+ ��moves��{"0":{"":13206},"1":{"":17050},"2":{"case":4178,"cc":3525,"det":1496,"punct":893,"mark":890,"nsubj":689,"advmod":525,"nummod":223,"obl":218,"cop":152,"discourse":134,"obj":111,"dislocated":64,"advcl":57,"dep":0},"3":{"punct":3113,"conj":2479,"obl":2372,"compound:smixut":1558,"nmod:poss":1549,"obj":1366,"nsubj":1324,"ccomp":582,"appos":468,"acl":434,"parataxis":410,"advcl":395,"advmod":164,"xcomp":146,"nmod":138,"amod":136,"det":99,"nummod":59,"flat":47,"orphan":43,"discourse":43,"dep":0},"4":{"ROOT":1263}}�cfg��neg_key�
tagger/cfg ADDED
@@ -0,0 +1,224 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "label_smoothing":0.0,
3
+ "labels":[
4
+ "adjv__Gender=Fem|Number=Plur",
5
+ "adjv__Gender=Fem|Number=Plur|NumType=Ord",
6
+ "adjv__Gender=Fem|Number=Sing",
7
+ "adjv__Gender=Fem|Number=Sing|NumType=Ord",
8
+ "adjv__Gender=Masc|Number=Plur",
9
+ "adjv__Gender=Masc|Number=Plur|NumType=Ord",
10
+ "adjv__Gender=Masc|Number=Sing",
11
+ "adjv__Gender=Masc|Number=Sing|NumType=Ord",
12
+ "advb",
13
+ "art",
14
+ "art__PronType=Art",
15
+ "conj",
16
+ "inrg",
17
+ "intj",
18
+ "nega__Polarity=Neg",
19
+ "nmpr__Gender=Fem|Number=Sing",
20
+ "nmpr__Gender=Masc|Number=Plur",
21
+ "nmpr__Gender=Masc|Number=Sing",
22
+ "nmpr__Number=Sing",
23
+ "prde__Gender=Fem|Number=Sing|PronType=Dem",
24
+ "prde__Gender=Masc|Number=Sing|PronType=Dem",
25
+ "prde__Number=Plur|PronType=Dem",
26
+ "prep",
27
+ "prin__PronType=Int",
28
+ "prn__Gender=Fem|Number=Plur|Person=2|PronType=Prs",
29
+ "prn__Gender=Fem|Number=Plur|Person=3|PronType=Prs",
30
+ "prn__Gender=Fem|Number=Sing|Person=2|PronType=Prs",
31
+ "prn__Gender=Fem|Number=Sing|Person=3|PronType=Prs",
32
+ "prn__Gender=Masc|Number=Plur|Person=2|PronType=Prs",
33
+ "prn__Gender=Masc|Number=Plur|Person=3|PronType=Prs",
34
+ "prn__Gender=Masc|Number=Sing|Person=2|PronType=Prs",
35
+ "prn__Gender=Masc|Number=Sing|Person=3|PronType=Prs",
36
+ "prn__Number=Plur|Person=1|PronType=Prs",
37
+ "prn__Number=Sing|Person=1|PronType=Prs",
38
+ "prps__Gender=Fem|Number=Plur|Person=2|PronType=Prs",
39
+ "prps__Gender=Fem|Number=Plur|Person=3|PronType=Prs",
40
+ "prps__Gender=Fem|Number=Sing|Person=2|PronType=Prs",
41
+ "prps__Gender=Fem|Number=Sing|Person=3|PronType=Prs",
42
+ "prps__Gender=Masc|Number=Plur|Person=2|PronType=Prs",
43
+ "prps__Gender=Masc|Number=Plur|Person=3|PronType=Prs",
44
+ "prps__Gender=Masc|Number=Sing|Person=2|PronType=Prs",
45
+ "prps__Gender=Masc|Number=Sing|Person=3|PronType=Prs",
46
+ "prps__Number=Plur|Person=1|PronType=Prs",
47
+ "prps__Number=Sing|Person=1|PronType=Prs",
48
+ "punct",
49
+ "subs",
50
+ "subs__Gender=Fem|Number=Dual",
51
+ "subs__Gender=Fem|Number=Dual|NumType=Card",
52
+ "subs__Gender=Fem|Number=Plur",
53
+ "subs__Gender=Fem|Number=Plur|NumType=Card",
54
+ "subs__Gender=Fem|Number=Sing",
55
+ "subs__Gender=Fem|Number=Sing|NumType=Card",
56
+ "subs__Gender=Masc|Number=Dual",
57
+ "subs__Gender=Masc|Number=Plur",
58
+ "subs__Gender=Masc|Number=Plur|NumType=Card",
59
+ "subs__Gender=Masc|Number=Sing",
60
+ "subs__Gender=Masc|Number=Sing|NumType=Card",
61
+ "subs__Mood=Ind|VerbForm=Fin",
62
+ "subs__Number=Dual|NumType=Card",
63
+ "subs__Number=Sing",
64
+ "subs__Number=Sing|NumType=Card",
65
+ "verb",
66
+ "verb__Aspect=Imp|Gender=Fem|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
67
+ "verb__Aspect=Imp|Gender=Fem|HebBinyan=NIFAL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
68
+ "verb__Aspect=Imp|Gender=Fem|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
69
+ "verb__Aspect=Imp|Gender=Fem|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
70
+ "verb__Aspect=Imp|Gender=Fem|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
71
+ "verb__Aspect=Imp|Gender=Fem|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
72
+ "verb__Aspect=Imp|Gender=Fem|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
73
+ "verb__Aspect=Imp|Gender=Fem|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
74
+ "verb__Aspect=Imp|Gender=Fem|HebBinyan=PIEL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
75
+ "verb__Aspect=Imp|Gender=Fem|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
76
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=HIFIL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
77
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=HIFIL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
78
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
79
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
80
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=HITPAEL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
81
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=HITPAEL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
82
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=NIFAL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
83
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=NIFAL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
84
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
85
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
86
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
87
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
88
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
89
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
90
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=PIEL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
91
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
92
+ "verb__Aspect=Imp|Gender=Masc|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
93
+ "verb__Aspect=Imp|Gender=Masc|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
94
+ "verb__Aspect=Imp|Gender=Masc|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
95
+ "verb__Aspect=Imp|HebBinyan=HIFIL|Mood=Ind|Number=Plur|Person=1|VerbForm=Fin",
96
+ "verb__Aspect=Imp|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=1|VerbForm=Fin",
97
+ "verb__Aspect=Imp|HebBinyan=HITPAEL|Mood=Ind|Number=Plur|Person=1|VerbForm=Fin",
98
+ "verb__Aspect=Imp|HebBinyan=NIFAL|Mood=Ind|Number=Plur|Person=1|VerbForm=Fin",
99
+ "verb__Aspect=Imp|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=1|VerbForm=Fin",
100
+ "verb__Aspect=Imp|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=1|VerbForm=Fin",
101
+ "verb__Aspect=Imp|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=1|VerbForm=Fin",
102
+ "verb__Aspect=Imp|HebBinyan=PIEL|Mood=Ind|Number=Plur|Person=1|VerbForm=Fin",
103
+ "verb__Aspect=Imp|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=1|VerbForm=Fin",
104
+ "verb__Aspect=Imp|Mood=Ind|Number=Plur|Person=1|VerbForm=Fin",
105
+ "verb__Aspect=Perf|Gender=Fem|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
106
+ "verb__Aspect=Perf|Gender=Fem|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
107
+ "verb__Aspect=Perf|Gender=Fem|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
108
+ "verb__Aspect=Perf|Gender=Fem|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
109
+ "verb__Aspect=Perf|Gender=Fem|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
110
+ "verb__Aspect=Perf|Gender=Fem|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
111
+ "verb__Aspect=Perf|Gender=Fem|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
112
+ "verb__Aspect=Perf|Gender=Fem|HebBinyan=PUAL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
113
+ "verb__Aspect=Perf|Gender=Fem|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
114
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=HIFIL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
115
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
116
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
117
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=HITPAEL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
118
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=NIFAL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
119
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
120
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
121
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
122
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
123
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
124
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=PIEL|Mood=Ind|Number=Plur|Person=2|VerbForm=Fin",
125
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=2|VerbForm=Fin",
126
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
127
+ "verb__Aspect=Perf|Gender=Masc|HebBinyan=PUAL|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
128
+ "verb__Aspect=Perf|Gender=Masc|Mood=Ind|Number=Sing|Person=3|VerbForm=Fin",
129
+ "verb__Aspect=Perf|HebBinyan=HIFIL|Mood=Ind|Number=Plur|Person=1|VerbForm=Fin",
130
+ "verb__Aspect=Perf|HebBinyan=HIFIL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
131
+ "verb__Aspect=Perf|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=1|VerbForm=Fin",
132
+ "verb__Aspect=Perf|HebBinyan=HITPAEL|Mood=Ind|Number=Plur|Person=1|VerbForm=Fin",
133
+ "verb__Aspect=Perf|HebBinyan=HITPAEL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
134
+ "verb__Aspect=Perf|HebBinyan=HITPAEL|Mood=Ind|Number=Sing|Person=1|VerbForm=Fin",
135
+ "verb__Aspect=Perf|HebBinyan=NIFAL|Mood=Ind|Number=Plur|Person=1|VerbForm=Fin",
136
+ "verb__Aspect=Perf|HebBinyan=NIFAL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
137
+ "verb__Aspect=Perf|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=1|VerbForm=Fin",
138
+ "verb__Aspect=Perf|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=1|VerbForm=Fin",
139
+ "verb__Aspect=Perf|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
140
+ "verb__Aspect=Perf|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=1|VerbForm=Fin",
141
+ "verb__Aspect=Perf|HebBinyan=PIEL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
142
+ "verb__Aspect=Perf|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=1|VerbForm=Fin",
143
+ "verb__Aspect=Perf|HebBinyan=PUAL|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
144
+ "verb__Aspect=Perf|HebBinyan=PUAL|Mood=Ind|Number=Sing|Person=1|VerbForm=Fin",
145
+ "verb__Aspect=Perf|Mood=Ind|Number=Plur|Person=3|VerbForm=Fin",
146
+ "verb__Gender=Fem|HebBinyan=HIFIL|Mood=Imp|Number=Sing|Person=2|VerbForm=Fin",
147
+ "verb__Gender=Fem|HebBinyan=HIFIL|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
148
+ "verb__Gender=Fem|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
149
+ "verb__Gender=Fem|HebBinyan=HIFIL|Number=Plur|VerbForm=Part",
150
+ "verb__Gender=Fem|HebBinyan=HITPAEL|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
151
+ "verb__Gender=Fem|HebBinyan=NIFAL|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
152
+ "verb__Gender=Fem|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
153
+ "verb__Gender=Fem|HebBinyan=NIFAL|Number=Sing|VerbForm=Part",
154
+ "verb__Gender=Fem|HebBinyan=PAAL|Mood=Imp|Number=Plur|Person=2|VerbForm=Fin",
155
+ "verb__Gender=Fem|HebBinyan=PAAL|Mood=Imp|Number=Sing|Person=2|VerbForm=Fin",
156
+ "verb__Gender=Fem|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
157
+ "verb__Gender=Fem|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=2|Tense=Past|VerbForm=Fin",
158
+ "verb__Gender=Fem|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
159
+ "verb__Gender=Fem|HebBinyan=PAAL|Number=Plur|VerbForm=Part",
160
+ "verb__Gender=Fem|HebBinyan=PAAL|Number=Plur|VerbForm=Part|Voice=Pass",
161
+ "verb__Gender=Fem|HebBinyan=PAAL|Number=Sing|VerbForm=Part",
162
+ "verb__Gender=Fem|HebBinyan=PAAL|Number=Sing|VerbForm=Part|Voice=Pass",
163
+ "verb__Gender=Fem|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
164
+ "verb__Gender=Fem|HebBinyan=PIEL|Number=Sing|VerbForm=Part",
165
+ "verb__Gender=Fem|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
166
+ "verb__Gender=Fem|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
167
+ "verb__Gender=Fem|Number=Sing|VerbForm=Part|Voice=Pass",
168
+ "verb__Gender=Masc|HebBinyan=HIFIL|Mood=Imp|Number=Plur|Person=2|VerbForm=Fin",
169
+ "verb__Gender=Masc|HebBinyan=HIFIL|Mood=Imp|Number=Sing|Person=2|VerbForm=Fin",
170
+ "verb__Gender=Masc|HebBinyan=HIFIL|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
171
+ "verb__Gender=Masc|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=2|Tense=Past|VerbForm=Fin",
172
+ "verb__Gender=Masc|HebBinyan=HIFIL|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
173
+ "verb__Gender=Masc|HebBinyan=HIFIL|Number=Plur|VerbForm=Part",
174
+ "verb__Gender=Masc|HebBinyan=HIFIL|Number=Sing|VerbForm=Part",
175
+ "verb__Gender=Masc|HebBinyan=HITPAEL|Mood=Imp|Number=Plur|Person=2|VerbForm=Fin",
176
+ "verb__Gender=Masc|HebBinyan=HITPAEL|Mood=Imp|Number=Sing|Person=2|VerbForm=Fin",
177
+ "verb__Gender=Masc|HebBinyan=HITPAEL|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
178
+ "verb__Gender=Masc|HebBinyan=HITPAEL|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
179
+ "verb__Gender=Masc|HebBinyan=HITPAEL|Number=Sing|VerbForm=Part",
180
+ "verb__Gender=Masc|HebBinyan=NIFAL|Mood=Imp|Number=Plur|Person=2|VerbForm=Fin",
181
+ "verb__Gender=Masc|HebBinyan=NIFAL|Mood=Imp|Number=Sing|Person=2|VerbForm=Fin",
182
+ "verb__Gender=Masc|HebBinyan=NIFAL|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
183
+ "verb__Gender=Masc|HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
184
+ "verb__Gender=Masc|HebBinyan=NIFAL|Number=Plur|VerbForm=Part",
185
+ "verb__Gender=Masc|HebBinyan=NIFAL|Number=Sing|VerbForm=Part",
186
+ "verb__Gender=Masc|HebBinyan=PAAL|Mood=Imp|Number=Plur|Person=2|VerbForm=Fin",
187
+ "verb__Gender=Masc|HebBinyan=PAAL|Mood=Imp|Number=Sing|Person=2|VerbForm=Fin",
188
+ "verb__Gender=Masc|HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
189
+ "verb__Gender=Masc|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=2|Tense=Past|VerbForm=Fin",
190
+ "verb__Gender=Masc|HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
191
+ "verb__Gender=Masc|HebBinyan=PAAL|Number=Plur|VerbForm=Part",
192
+ "verb__Gender=Masc|HebBinyan=PAAL|Number=Plur|VerbForm=Part|Voice=Pass",
193
+ "verb__Gender=Masc|HebBinyan=PAAL|Number=Sing|VerbForm=Part",
194
+ "verb__Gender=Masc|HebBinyan=PAAL|Number=Sing|VerbForm=Part|Voice=Pass",
195
+ "verb__Gender=Masc|HebBinyan=PIEL|Mood=Imp|Number=Plur|Person=2|VerbForm=Fin",
196
+ "verb__Gender=Masc|HebBinyan=PIEL|Mood=Imp|Number=Sing|Person=2|VerbForm=Fin",
197
+ "verb__Gender=Masc|HebBinyan=PIEL|Mood=Ind|Number=Plur|Person=2|Tense=Past|VerbForm=Fin",
198
+ "verb__Gender=Masc|HebBinyan=PIEL|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
199
+ "verb__Gender=Masc|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=2|Tense=Past|VerbForm=Fin",
200
+ "verb__Gender=Masc|HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
201
+ "verb__Gender=Masc|HebBinyan=PIEL|Number=Plur|VerbForm=Part",
202
+ "verb__Gender=Masc|HebBinyan=PIEL|Number=Sing|VerbForm=Part",
203
+ "verb__Gender=Masc|HebBinyan=PUAL|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
204
+ "verb__Gender=Masc|Mood=Ind|Number=Plur|Person=3|Tense=Past|VerbForm=Fin",
205
+ "verb__Gender=Masc|Mood=Ind|Number=Sing|Person=3|Tense=Past|VerbForm=Fin",
206
+ "verb__Gender=Masc|Number=Plur|VerbForm=Part|Voice=Pass",
207
+ "verb__Gender=Masc|Number=Sing|VerbForm=Part|Voice=Pass",
208
+ "verb__HebBinyan=HIFIL|Mood=Ind|Number=Plur|Person=1|Tense=Past|VerbForm=Fin",
209
+ "verb__HebBinyan=HIFIL|VerbForm=Inf",
210
+ "verb__HebBinyan=HITPAEL|VerbForm=Inf",
211
+ "verb__HebBinyan=NIFAL|Mood=Ind|Number=Sing|Person=1|Tense=Past|VerbForm=Fin",
212
+ "verb__HebBinyan=NIFAL|VerbForm=Inf",
213
+ "verb__HebBinyan=PAAL|Mood=Ind|Number=Plur|Person=1|Tense=Past|VerbForm=Fin",
214
+ "verb__HebBinyan=PAAL|Mood=Ind|Number=Sing|Person=1|Tense=Past|VerbForm=Fin",
215
+ "verb__HebBinyan=PAAL|VerbForm=Inf",
216
+ "verb__HebBinyan=PIEL|Mood=Ind|Number=Plur|Person=1|Tense=Past|VerbForm=Fin",
217
+ "verb__HebBinyan=PIEL|Mood=Ind|Number=Sing|Person=1|Tense=Past|VerbForm=Fin",
218
+ "verb__HebBinyan=PIEL|VerbForm=Inf",
219
+ "verb__Mood=Ind|Number=Sing|Person=1|Tense=Past|VerbForm=Fin",
220
+ "verb__VerbForm=Inf"
221
+ ],
222
+ "neg_prefix":"!",
223
+ "overwrite":false
224
+ }
tagger/model ADDED
Binary file (668 kB). View file
 
tokenizer ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ ��prefix_search� �^§|^%|^=|^—|^–|^\+(?![0-9])|^…|^……|^,|^:|^;|^\!|^\?|^¿|^؟|^¡|^\(|^\)|^\[|^\]|^\{|^\}|^<|^>|^_|^#|^\*|^&|^。|^?|^!|^,|^、|^;|^:|^~|^·|^।|^،|^۔|^؛|^٪|^\.\.+|^…|^\'|^"|^”|^“|^`|^‘|^´|^’|^‚|^,|^„|^»|^«|^「|^」|^『|^』|^(|^)|^〔|^〕|^【|^】|^《|^》|^〈|^〉|^〈|^〉|^⟦|^⟧|^\$|^£|^€|^¥|^฿|^US\$|^C\$|^A\$|^₽|^﷼|^₴|^₠|^₡|^₢|^₣|^₤|^₥|^₦|^₧|^₨|^₩|^₪|^₫|^€|^₭|^₮|^₯|^₰|^₱|^₲|^₳|^₴|^₵|^₶|^₷|^₸|^₹|^₺|^₻|^₼|^₽|^₾|^₿|^[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]�suffix_search�2�…$|……$|,$|:$|;$|\!$|\?$|¿$|؟$|¡$|\($|\)$|\[$|\]$|\{$|\}$|<$|>$|_$|#$|\*$|&$|。$|?$|!$|,$|、$|;$|:$|~$|·$|।$|،$|۔$|؛$|٪$|\.\.+$|…$|\'$|"$|”$|“$|`$|‘$|´$|’$|‚$|,$|„$|»$|«$|「$|」$|『$|』$|($|)$|〔$|〕$|【$|】$|《$|》$|〈$|〉$|〈$|〉$|⟦$|⟧$|[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]$|'s$|'S$|’s$|’S$|—$|–$|(?<=[0-9])\+$|(?<=°[FfCcKk])\.$|(?<=[0-9])(?:\$|£|€|¥|฿|US\$|C\$|A\$|₽|﷼|₴|₠|₡|₢|₣|₤|₥|₦|₧|₨|₩|₪|₫|€|₭|₮|₯|₰|₱|₲|₳|₴|₵|₶|₷|₸|₹|₺|₻|₼|₽|₾|₿)$|(?<=[0-9])(?:km|km²|km³|m|m²|m³|dm|dm²|dm³|cm|cm²|cm³|mm|mm²|mm³|ha|µm|nm|yd|in|ft|kg|g|mg|µg|t|lb|oz|m/s|km/h|kmh|mph|hPa|Pa|mbar|mb|MB|kb|KB|gb|GB|tb|TB|T|G|M|K|%|км|км²|км³|м|м²|м³|дм|дм²|дм³|см|см²|см³|мм|мм²|мм³|нм|кг|г|мг|м/с|км/ч|кПа|Па|мбар|Кб|КБ|кб|Мб|МБ|мб|Гб|ГБ|гб|Тб|ТБ|тбكم|كم²|كم³|م|م²|م³|سم|سم²|سم³|مم|مم²|مم³|كم|غرام|جرام|جم|كغ|ملغ|كوب|اكواب)$|(?<=[0-9a-z\uFF41-\uFF5A\u00DF-\u00F6\u00F8-\u00FF\u0101\u0103\u0105\u0107\u0109\u010B\u010D\u010F\u0111\u0113\u0115\u0117\u0119\u011B\u011D\u011F\u0121\u0123\u0125\u0127\u0129\u012B\u012D\u012F\u0131\u0133\u0135\u0137\u0138\u013A\u013C\u013E\u0140\u0142\u0144\u0146\u0148\u0149\u014B\u014D\u014F\u0151\u0153\u0155\u0157\u0159\u015B\u015D\u015F\u0161\u0163\u0165\u0167\u0169\u016B\u016D\u016F\u0171\u0173\u0175\u0177\u017A\u017C\u017E\u017F\u0180\u0183\u0185\u0188\u018C\u018D\u0192\u0195\u0199-\u019B\u019E\u01A1\u01A3\u01A5\u01A8\u01AA\u01AB\u01AD\u01B0\u01B4\u01B6\u01B9\u01BA\u01BD-\u01BF\u01C6\u01C9\u01CC\u01CE\u01D0\u01D2\u01D4\u01D6\u01D8\u01DA\u01DC\u01DD\u01DF\u01E1\u01E3\u01E5\u01E7\u01E9\u01EB\u01ED\u01EF\u01F0\u01F3\u01F5\u01F9\u01FB\u01FD\u01FF\u0201\u0203\u0205\u0207\u0209\u020B\u020D\u020F\u0211\u0213\u0215\u0217\u0219\u021B\u021D\u021F\u0221\u0223\u0225\u0227\u0229\u022B\u022D\u022F\u0231\u0233-\u0239\u023C\u023F\u0240\u0242\u0247\u0249\u024B\u024D\u024F\u2C61\u2C65\u2C66\u2C68\u2C6A\u2C6C\u2C71\u2C73\u2C74\u2C76-\u2C7B\uA723\uA725\uA727\uA729\uA72B\uA72D\uA72F-\uA731\uA733\uA735\uA737\uA739\uA73B\uA73D\uA73F\uA741\uA743\uA745\uA747\uA749\uA74B\uA74D\uA74F\uA751\uA753\uA755\uA757\uA759\uA75B\uA75D\uA75F\uA761\uA763\uA765\uA767\uA769\uA76B\uA76D\uA76F\uA771-\uA778\uA77A\uA77C\uA77F\uA781\uA783\uA785\uA787\uA78C\uA78E\uA791\uA793-\uA795\uA797\uA799\uA79B\uA79D\uA79F\uA7A1\uA7A3\uA7A5\uA7A7\uA7A9\uA7AF\uA7B5\uA7B7\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E01\u1E03\u1E05\u1E07\u1E09\u1E0B\u1E0D\u1E0F\u1E11\u1E13\u1E15\u1E17\u1E19\u1E1B\u1E1D\u1E1F\u1E21\u1E23\u1E25\u1E27\u1E29\u1E2B\u1E2D\u1E2F\u1E31\u1E33\u1E35\u1E37\u1E39\u1E3B\u1E3D\u1E3F\u1E41\u1E43\u1E45\u1E47\u1E49\u1E4B\u1E4D\u1E4F\u1E51\u1E53\u1E55\u1E57\u1E59\u1E5B\u1E5D\u1E5F\u1E61\u1E63\u1E65\u1E67\u1E69\u1E6B\u1E6D\u1E6F\u1E71\u1E73\u1E75\u1E77\u1E79\u1E7B\u1E7D\u1E7F\u1E81\u1E83\u1E85\u1E87\u1E89\u1E8B\u1E8D\u1E8F\u1E91\u1E93\u1E95-\u1E9D\u1E9F\u1EA1\u1EA3\u1EA5\u1EA7\u1EA9\u1EAB\u1EAD\u1EAF\u1EB1\u1EB3\u1EB5\u1EB7\u1EB9\u1EBB\u1EBD\u1EBF\u1EC1\u1EC3\u1EC5\u1EC7\u1EC9\u1ECB\u1ECD\u1ECF\u1ED1\u1ED3\u1ED5\u1ED7\u1ED9\u1EDB\u1EDD\u1EDF\u1EE1\u1EE3\u1EE5\u1EE7\u1EE9\u1EEB\u1EED\u1EEF\u1EF1\u1EF3\u1EF5\u1EF7\u1EF9\u1EFB\u1EFD\u1EFFёа-яәөүҗңһα-ωάέίόώήύа-щюяіїєґѓѕјљњќѐѝ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F%²\-\+…|……|,|:|;|\!|\?|¿|؟|¡|\(|\)|\[|\]|\{|\}|<|>|_|#|\*|&|。|?|!|,|、|;|:|~|·|।|،|۔|؛|٪(?:\'"”“`‘´’‚,„»«「」『』()〔〕【】《》〈〉〈〉⟦⟧)])\.$|(?<=[A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F][A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])\.$�infix_finditer�>�\.\.+|…|[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]|(?<=[0-9])[+\-\*^](?=[0-9-])|(?<=[a-z\uFF41-\uFF5A\u00DF-\u00F6\u00F8-\u00FF\u0101\u0103\u0105\u0107\u0109\u010B\u010D\u010F\u0111\u0113\u0115\u0117\u0119\u011B\u011D\u011F\u0121\u0123\u0125\u0127\u0129\u012B\u012D\u012F\u0131\u0133\u0135\u0137\u0138\u013A\u013C\u013E\u0140\u0142\u0144\u0146\u0148\u0149\u014B\u014D\u014F\u0151\u0153\u0155\u0157\u0159\u015B\u015D\u015F\u0161\u0163\u0165\u0167\u0169\u016B\u016D\u016F\u0171\u0173\u0175\u0177\u017A\u017C\u017E\u017F\u0180\u0183\u0185\u0188\u018C\u018D\u0192\u0195\u0199-\u019B\u019E\u01A1\u01A3\u01A5\u01A8\u01AA\u01AB\u01AD\u01B0\u01B4\u01B6\u01B9\u01BA\u01BD-\u01BF\u01C6\u01C9\u01CC\u01CE\u01D0\u01D2\u01D4\u01D6\u01D8\u01DA\u01DC\u01DD\u01DF\u01E1\u01E3\u01E5\u01E7\u01E9\u01EB\u01ED\u01EF\u01F0\u01F3\u01F5\u01F9\u01FB\u01FD\u01FF\u0201\u0203\u0205\u0207\u0209\u020B\u020D\u020F\u0211\u0213\u0215\u0217\u0219\u021B\u021D\u021F\u0221\u0223\u0225\u0227\u0229\u022B\u022D\u022F\u0231\u0233-\u0239\u023C\u023F\u0240\u0242\u0247\u0249\u024B\u024D\u024F\u2C61\u2C65\u2C66\u2C68\u2C6A\u2C6C\u2C71\u2C73\u2C74\u2C76-\u2C7B\uA723\uA725\uA727\uA729\uA72B\uA72D\uA72F-\uA731\uA733\uA735\uA737\uA739\uA73B\uA73D\uA73F\uA741\uA743\uA745\uA747\uA749\uA74B\uA74D\uA74F\uA751\uA753\uA755\uA757\uA759\uA75B\uA75D\uA75F\uA761\uA763\uA765\uA767\uA769\uA76B\uA76D\uA76F\uA771-\uA778\uA77A\uA77C\uA77F\uA781\uA783\uA785\uA787\uA78C\uA78E\uA791\uA793-\uA795\uA797\uA799\uA79B\uA79D\uA79F\uA7A1\uA7A3\uA7A5\uA7A7\uA7A9\uA7AF\uA7B5\uA7B7\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E01\u1E03\u1E05\u1E07\u1E09\u1E0B\u1E0D\u1E0F\u1E11\u1E13\u1E15\u1E17\u1E19\u1E1B\u1E1D\u1E1F\u1E21\u1E23\u1E25\u1E27\u1E29\u1E2B\u1E2D\u1E2F\u1E31\u1E33\u1E35\u1E37\u1E39\u1E3B\u1E3D\u1E3F\u1E41\u1E43\u1E45\u1E47\u1E49\u1E4B\u1E4D\u1E4F\u1E51\u1E53\u1E55\u1E57\u1E59\u1E5B\u1E5D\u1E5F\u1E61\u1E63\u1E65\u1E67\u1E69\u1E6B\u1E6D\u1E6F\u1E71\u1E73\u1E75\u1E77\u1E79\u1E7B\u1E7D\u1E7F\u1E81\u1E83\u1E85\u1E87\u1E89\u1E8B\u1E8D\u1E8F\u1E91\u1E93\u1E95-\u1E9D\u1E9F\u1EA1\u1EA3\u1EA5\u1EA7\u1EA9\u1EAB\u1EAD\u1EAF\u1EB1\u1EB3\u1EB5\u1EB7\u1EB9\u1EBB\u1EBD\u1EBF\u1EC1\u1EC3\u1EC5\u1EC7\u1EC9\u1ECB\u1ECD\u1ECF\u1ED1\u1ED3\u1ED5\u1ED7\u1ED9\u1EDB\u1EDD\u1EDF\u1EE1\u1EE3\u1EE5\u1EE7\u1EE9\u1EEB\u1EED\u1EEF\u1EF1\u1EF3\u1EF5\u1EF7\u1EF9\u1EFB\u1EFD\u1EFFёа-яәөүҗңһα-ωάέίόώήύа-щюяіїєґѓѕјљњќѐѝ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F\'"”“`‘´’‚,„»«「」『』()〔〕【】《》〈〉〈〉⟦⟧])\.(?=[A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F\'"”“`‘´’‚,„»«「」『』()〔〕【】《》〈〉〈〉⟦⟧])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F]),(?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])(?:-|–|—|--|---|——|~)(?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F0-9])[:<>=/](?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])�token_match��url_match�
2
+ ��A�
3
+ � ��A� �'��A�'�''��A�''�(*_*)��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
@@ -0,0 +1,616 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "labels":[
3
+ 0,
4
+ 5,
5
+ 8,
6
+ 13,
7
+ 16,
8
+ 22,
9
+ 26,
10
+ 31,
11
+ 35,
12
+ 37,
13
+ 42,
14
+ 46,
15
+ 51,
16
+ 57,
17
+ 61,
18
+ 67,
19
+ 71,
20
+ 75,
21
+ 77,
22
+ 79,
23
+ 82,
24
+ 86,
25
+ 93,
26
+ 97,
27
+ 100,
28
+ 103,
29
+ 106,
30
+ 109,
31
+ 113,
32
+ 115,
33
+ 119,
34
+ 122,
35
+ 127,
36
+ 130,
37
+ 133,
38
+ 134,
39
+ 137,
40
+ 139,
41
+ 140,
42
+ 145,
43
+ 148,
44
+ 151,
45
+ 154,
46
+ 155,
47
+ 158,
48
+ 161,
49
+ 164,
50
+ 169,
51
+ 172,
52
+ 176,
53
+ 181,
54
+ 184,
55
+ 186,
56
+ 190,
57
+ 194,
58
+ 197,
59
+ 201,
60
+ 204,
61
+ 210,
62
+ 213,
63
+ 216,
64
+ 220,
65
+ 223,
66
+ 226,
67
+ 228,
68
+ 231,
69
+ 234,
70
+ 237,
71
+ 239,
72
+ 242,
73
+ 244,
74
+ 247,
75
+ 248,
76
+ 253,
77
+ 257,
78
+ 259,
79
+ 262,
80
+ 266,
81
+ 269,
82
+ 272,
83
+ 274,
84
+ 277,
85
+ 281,
86
+ 284,
87
+ 286,
88
+ 291,
89
+ 294,
90
+ 298,
91
+ 302,
92
+ 307,
93
+ 311,
94
+ 312,
95
+ 313,
96
+ 316,
97
+ 319,
98
+ 323,
99
+ 325,
100
+ 328,
101
+ 329,
102
+ 333,
103
+ 336,
104
+ 339,
105
+ 342,
106
+ 344,
107
+ 346,
108
+ 349,
109
+ 350,
110
+ 354,
111
+ 355,
112
+ 357,
113
+ 358,
114
+ 361,
115
+ 364,
116
+ 369,
117
+ 373,
118
+ 378,
119
+ 380,
120
+ 383,
121
+ 385,
122
+ 389,
123
+ 392,
124
+ 396,
125
+ 399,
126
+ 403,
127
+ 404,
128
+ 407,
129
+ 411,
130
+ 412,
131
+ 415,
132
+ 417,
133
+ 420,
134
+ 424,
135
+ 426,
136
+ 428,
137
+ 430,
138
+ 432,
139
+ 436,
140
+ 441,
141
+ 444,
142
+ 448,
143
+ 449,
144
+ 452,
145
+ 456,
146
+ 458,
147
+ 459,
148
+ 461,
149
+ 464,
150
+ 467,
151
+ 469,
152
+ 470,
153
+ 473,
154
+ 478,
155
+ 480,
156
+ 483,
157
+ 484,
158
+ 488,
159
+ 490,
160
+ 493,
161
+ 494,
162
+ 496,
163
+ 502,
164
+ 504,
165
+ 505,
166
+ 509,
167
+ 512,
168
+ 514,
169
+ 516,
170
+ 519,
171
+ 523,
172
+ 527,
173
+ 531,
174
+ 534,
175
+ 536,
176
+ 539,
177
+ 542,
178
+ 543,
179
+ 544,
180
+ 549,
181
+ 552,
182
+ 553,
183
+ 556,
184
+ 558,
185
+ 560,
186
+ 561,
187
+ 564,
188
+ 567,
189
+ 569,
190
+ 572,
191
+ 575,
192
+ 576,
193
+ 581,
194
+ 583,
195
+ 584,
196
+ 585,
197
+ 588,
198
+ 589,
199
+ 591,
200
+ 596,
201
+ 598,
202
+ 600,
203
+ 604,
204
+ 607,
205
+ 610,
206
+ 612,
207
+ 613,
208
+ 615,
209
+ 618,
210
+ 619,
211
+ 622,
212
+ 624,
213
+ 627,
214
+ 629,
215
+ 631,
216
+ 634,
217
+ 638,
218
+ 639,
219
+ 640,
220
+ 643,
221
+ 646,
222
+ 651,
223
+ 653,
224
+ 656,
225
+ 659,
226
+ 664,
227
+ 666,
228
+ 671,
229
+ 674,
230
+ 675,
231
+ 679,
232
+ 682,
233
+ 686,
234
+ 688,
235
+ 690,
236
+ 691,
237
+ 692,
238
+ 693,
239
+ 695,
240
+ 700,
241
+ 701,
242
+ 704,
243
+ 707,
244
+ 710,
245
+ 712,
246
+ 715,
247
+ 717,
248
+ 720,
249
+ 722,
250
+ 724,
251
+ 728,
252
+ 733,
253
+ 738,
254
+ 741,
255
+ 745,
256
+ 746,
257
+ 749,
258
+ 753,
259
+ 757,
260
+ 760,
261
+ 763,
262
+ 767,
263
+ 770,
264
+ 771,
265
+ 773,
266
+ 775,
267
+ 777,
268
+ 778,
269
+ 782,
270
+ 786,
271
+ 791,
272
+ 793,
273
+ 794,
274
+ 795,
275
+ 797,
276
+ 799,
277
+ 802,
278
+ 805,
279
+ 807,
280
+ 809,
281
+ 811,
282
+ 813,
283
+ 815,
284
+ 816,
285
+ 819,
286
+ 822,
287
+ 824,
288
+ 827,
289
+ 830,
290
+ 832,
291
+ 835,
292
+ 838,
293
+ 841,
294
+ 843,
295
+ 844,
296
+ 847,
297
+ 849,
298
+ 851,
299
+ 854,
300
+ 857,
301
+ 859,
302
+ 860,
303
+ 862,
304
+ 866,
305
+ 869,
306
+ 871,
307
+ 872,
308
+ 873,
309
+ 877,
310
+ 879,
311
+ 881,
312
+ 882,
313
+ 884,
314
+ 887,
315
+ 888,
316
+ 889,
317
+ 890,
318
+ 892,
319
+ 894,
320
+ 897,
321
+ 899,
322
+ 904,
323
+ 906,
324
+ 908,
325
+ 910,
326
+ 912,
327
+ 913,
328
+ 918,
329
+ 919,
330
+ 922,
331
+ 925,
332
+ 929,
333
+ 933,
334
+ 935,
335
+ 938,
336
+ 941,
337
+ 943,
338
+ 946,
339
+ 949,
340
+ 952,
341
+ 954,
342
+ 958,
343
+ 959,
344
+ 960,
345
+ 962,
346
+ 966,
347
+ 969,
348
+ 974,
349
+ 977,
350
+ 981,
351
+ 984,
352
+ 987,
353
+ 989,
354
+ 993,
355
+ 996,
356
+ 998,
357
+ 1000,
358
+ 1002,
359
+ 1005,
360
+ 1006,
361
+ 1007,
362
+ 1009,
363
+ 1010,
364
+ 1013,
365
+ 1017,
366
+ 1019,
367
+ 1021,
368
+ 1023,
369
+ 1025,
370
+ 1028,
371
+ 1031,
372
+ 1036,
373
+ 1039,
374
+ 1041,
375
+ 1045,
376
+ 1046,
377
+ 1048,
378
+ 1051,
379
+ 1054,
380
+ 1058,
381
+ 1060,
382
+ 1063,
383
+ 1067,
384
+ 1069,
385
+ 1071,
386
+ 1075,
387
+ 1076,
388
+ 1078,
389
+ 1082,
390
+ 1084,
391
+ 1087,
392
+ 1089,
393
+ 1091,
394
+ 1092,
395
+ 1094,
396
+ 1099,
397
+ 1101,
398
+ 1104,
399
+ 1106,
400
+ 1108,
401
+ 1113,
402
+ 1117,
403
+ 1118,
404
+ 1120,
405
+ 1123,
406
+ 1126,
407
+ 1127,
408
+ 1129,
409
+ 1132,
410
+ 1134,
411
+ 1136,
412
+ 1139,
413
+ 1141,
414
+ 1144,
415
+ 1147,
416
+ 1150,
417
+ 1152,
418
+ 1153,
419
+ 1155,
420
+ 1157,
421
+ 1158,
422
+ 1160,
423
+ 1163,
424
+ 1166,
425
+ 1169,
426
+ 1170,
427
+ 1173,
428
+ 1176,
429
+ 1180,
430
+ 1182,
431
+ 1185,
432
+ 1188,
433
+ 1190,
434
+ 1193,
435
+ 1194,
436
+ 1197,
437
+ 1199,
438
+ 1201,
439
+ 1202,
440
+ 1204,
441
+ 1205,
442
+ 1206,
443
+ 1209,
444
+ 1211,
445
+ 1213,
446
+ 1217,
447
+ 1218,
448
+ 1220,
449
+ 1222,
450
+ 1224,
451
+ 1225,
452
+ 1226,
453
+ 1231,
454
+ 1234,
455
+ 1236,
456
+ 1237,
457
+ 1239,
458
+ 1240,
459
+ 1244,
460
+ 1245,
461
+ 1248,
462
+ 1250,
463
+ 1253,
464
+ 1257,
465
+ 1260,
466
+ 1262,
467
+ 1265,
468
+ 1267,
469
+ 1269,
470
+ 1271,
471
+ 1274,
472
+ 1276,
473
+ 1278,
474
+ 1281,
475
+ 1282,
476
+ 1284,
477
+ 1286,
478
+ 1288,
479
+ 1290,
480
+ 1292,
481
+ 1294,
482
+ 1296,
483
+ 1297,
484
+ 1299,
485
+ 1301,
486
+ 1304,
487
+ 1307,
488
+ 1311,
489
+ 1312,
490
+ 1316,
491
+ 1320,
492
+ 1322,
493
+ 1324,
494
+ 1328,
495
+ 1330,
496
+ 1334,
497
+ 1336,
498
+ 1338,
499
+ 1340,
500
+ 1342,
501
+ 1346,
502
+ 1351,
503
+ 1352,
504
+ 1354,
505
+ 1356,
506
+ 1359,
507
+ 1362,
508
+ 1364,
509
+ 1367,
510
+ 1369,
511
+ 1371,
512
+ 1373,
513
+ 1375,
514
+ 1376,
515
+ 1378,
516
+ 1380,
517
+ 1383,
518
+ 1386,
519
+ 1389,
520
+ 1391,
521
+ 1393,
522
+ 1396,
523
+ 1398,
524
+ 1400,
525
+ 1403,
526
+ 1406,
527
+ 1408,
528
+ 1414,
529
+ 1416,
530
+ 1420,
531
+ 1422,
532
+ 1423,
533
+ 1424,
534
+ 1427,
535
+ 1430,
536
+ 1431,
537
+ 1433,
538
+ 1435,
539
+ 1437,
540
+ 1439,
541
+ 1443,
542
+ 1444,
543
+ 1448,
544
+ 1451,
545
+ 1454,
546
+ 1455,
547
+ 1457,
548
+ 1458,
549
+ 1459,
550
+ 1461,
551
+ 1462,
552
+ 1463,
553
+ 1467,
554
+ 1469,
555
+ 1471,
556
+ 1473,
557
+ 1476,
558
+ 1479,
559
+ 1485,
560
+ 1489,
561
+ 1491,
562
+ 1495,
563
+ 1497,
564
+ 1498,
565
+ 1499,
566
+ 1500,
567
+ 1502,
568
+ 1505,
569
+ 1508,
570
+ 1510,
571
+ 1513,
572
+ 1515,
573
+ 1517,
574
+ 1518,
575
+ 1522,
576
+ 1523,
577
+ 1525,
578
+ 1528,
579
+ 1530,
580
+ 1532,
581
+ 1534,
582
+ 1535,
583
+ 1536,
584
+ 1540,
585
+ 1541,
586
+ 1545,
587
+ 1547,
588
+ 1548,
589
+ 1550,
590
+ 1553,
591
+ 1555,
592
+ 1559,
593
+ 1561,
594
+ 1564,
595
+ 1567,
596
+ 1568,
597
+ 1571,
598
+ 1574,
599
+ 1576,
600
+ 1578,
601
+ 1581,
602
+ 1583,
603
+ 1585,
604
+ 1588,
605
+ 1591,
606
+ 1595,
607
+ 1598,
608
+ 1601,
609
+ 1603,
610
+ 1605,
611
+ 1606,
612
+ 1608,
613
+ 1611,
614
+ 1615
615
+ ]
616
+ }
trainable_lemmatizer/model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c67ec87414a145dada346394a467e0096732239a1bcf611e127a56a76a0c7a4
3
+ size 1883165
trainable_lemmatizer/trees ADDED
Binary file (319 kB). View file
 
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 sha256:1fc7e8e531e2a18dafc60161c88726b85ce9435b9bc388745bf2de37da9c424b
3
+ size 509231398
vocab/key2row ADDED
@@ -0,0 +1 @@
 
 
1
+
vocab/lookups.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
3
+ size 1
vocab/strings.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab/vectors ADDED
Binary file (128 Bytes). View file
 
vocab/vectors.cfg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "mode":"default"
3
+ }
xx_hbo_sigtyp_trf-any-py3-none-any.whl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84c61482aecd6842ac837a82cc56a5eda31a2cb6630ce64599b4e7677d9906cc
3
+ size 468853398