rtuora commited on
Commit
8d900a6
1 Parent(s): b33947c

Readme update

Browse files
Files changed (1) hide show
  1. README.md +90 -0
README.md CHANGED
@@ -1,3 +1,93 @@
1
  ---
 
 
 
 
 
2
  license: gpl-3.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ tags:
3
+ - spacy
4
+ - token-classification
5
+ language:
6
+ - pl
7
  license: gpl-3.0
8
+ model-index:
9
+ - name: pl_nask
10
+ results:
11
+ - task:
12
+ name: NER
13
+ type: token-classification
14
+ metrics:
15
+ - name: NER Precision
16
+ type: precision
17
+ value: 0.9092043682
18
+ - name: NER Recall
19
+ type: recall
20
+ value: 0.9072229141
21
+ - name: NER F Score
22
+ type: f_score
23
+ value: 0.9082125604
24
+ - task:
25
+ name: TAG
26
+ type: token-classification
27
+ metrics:
28
+ - name: TAG (XPOS) Accuracy
29
+ type: accuracy
30
+ value: 0.9626419163,
31
+ - task:
32
+ name: UNLABELED_DEPENDENCIES
33
+ type: token-classification
34
+ metrics:
35
+ - name: Unlabeled Attachment Score (UAS)
36
+ type: f_score
37
+ value: 0.9290706682
38
+ - task:
39
+ name: LABELED_DEPENDENCIES
40
+ type: token-classification
41
+ metrics:
42
+ - name: Labeled Attachment Score (LAS)
43
+ type: f_score
44
+ value: 0.8765904858
45
+ - task:
46
+ name: SENTS
47
+ type: token-classification
48
+ metrics:
49
+ - name: Sentences F-Score
50
+ type: f_score
51
+ value: 0.9918545179
52
  ---
53
+ ### Details: https://github.com/ipipan/spacy-pl-trf
54
+ Polish transformer pipeline (herbert-base-cased). Components: transformer, tagger, parser, ner, morfeusz.
55
+
56
+ | Feature | Description |
57
+ | --- | --- |
58
+ | **Name** | `pl_nask` |
59
+ | **Version** | `0.0.7` |
60
+ | **spaCy** | `>=3.5.0,<3.6.0` |
61
+ | **Default Pipeline** | `transformer`, `tagger`, `morphologizer`, `parser`, `ner`, `morfeusz` |
62
+ | **Components** | `transformer`, `tagger`, `morphologizer`, `parser`, `ner`, `morfeusz` |
63
+ | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
64
+ | **Sources** | [Morfeusz2](http://morfeusz.sgjp.pl/en) 2-clauseBSD License<br /> [NKJP1M](http://nkjp.pl/) CC-BY<br /> [NKJP1MUD](http://git.nlp.ipipan.waw.pl/alina/PDBUD/tree/master) GNU GPL v.3<br /> [Herbert-base-cased](https://huggingface.co/allegro/herbert-base-cased) CC-BY<br /> [PDB](http://zil.ipipan.waw.pl/PDB) CC BY-NC-SA 4.0<br /> |
65
+
66
+ | **License** | `GNU GPL 3.0` |
67
+ | **Author** | [Ryszard Tuora ICS PAS](http://zil.ipipan.waw.pl/) |
68
+
69
+ ### Label Scheme
70
+
71
+ <details>
72
+
73
+ <summary>View label scheme</summary>
74
+
75
+ | Component | Labels |
76
+ | --- | --- |
77
+ | **`parser`** | `ROOT`, `acl`, `acl:relcl`, `advcl`, `advcl:cmpr`, `advcl:relcl`, `advmod`, `advmod:arg`, `advmod:emph`, `advmod:neg`, `amod`, `amod:flat`, `appos`, `aux`, `aux:cnd`, `aux:imp`, `aux:pass`, `case`, `cc`, `cc:preconj`, `ccomp`, `ccomp:cleft`, `ccomp:obj`, `conj`, `cop`, `csubj`, `dep`, `det`, `det:numgov`, `det:nummod`, `det:poss`, `discourse:intj`, `expl:pv`, `fixed`, `flat`, `flat:foreign`, `iobj`, `list`, `mark`, `nmod`, `nmod:arg`, `nmod:flat`, `nmod:poss`, `nsubj`, `nsubj:pass`, `nummod`, `nummod:flat`, `nummod:gov`, `obj`, `obl`, `obl:agent`, `obl:arg`, `obl:cmpr`, `obl:orphan`, `orphan`, `parataxis:insert`, `parataxis:obj`, `punct`, `vocative`, `xcomp`, `xcomp:cleft`, `xcomp:pred`, `xcomp:subj` |
78
+ | **`ner`** | `DATE`, `GEOGNAME`, `ORGNAME`, `PERSNAME`, `PLACENAME`, `TIME` |
79
+ </details>
80
+ ### Accuracy
81
+ | Type | Score |
82
+ | --- | --- |
83
+ | `TAG_ACC` | 96.26 |
84
+ | `POS_ACC` | 98.18 |
85
+ | `MORPH_ACC` | 96.61 |
86
+ | `SENTS_P` | 99.13 |
87
+ | `SENTS_R` | 99.24 |
88
+ | `SENTS_F` | 99.19 |
89
+ | `DEP_UAS` | 92.91 |
90
+ | `DEP_LAS` | 87.66 |
91
+ | `ENTS_P` | 90.92 |
92
+ | `ENTS_R` | 90.72 |
93
+ | `ENTS_F` | 90.82 |