dchaplinsky commited on
Commit
d8780ff
1 Parent(s): 5b794a2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +61 -0
README.md CHANGED
@@ -58,5 +58,66 @@ Results:
58
  The model was fine-tuned on the [Ukrainian (UD) corpus](https://universaldependencies.org/treebanks/uk_iu/index.html), released by the [non-profit organization Institute for Ukrainian](https://mova.institute).
59
  Training code is also available [here](https://github.com/lang-uk/flair-pos).
60
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
 
62
  Copyright: [Dmytro Chaplynskyi](https://twitter.com/dchaplinsky), [lang-uk project](https://lang.org.ua), 2022
 
58
  The model was fine-tuned on the [Ukrainian (UD) corpus](https://universaldependencies.org/treebanks/uk_iu/index.html), released by the [non-profit organization Institute for Ukrainian](https://mova.institute).
59
  Training code is also available [here](https://github.com/lang-uk/flair-pos).
60
 
61
+ ## [Usage demo](https://github.com/egorsmkv/flair-nlp-uk/blob/main/part_of_speech.py)
62
+ ```python
63
+ from flair.data import Sentence
64
+ from flair.models import SequenceTagger
65
+
66
+ from pprint import pprint
67
+
68
+ tagger = SequenceTagger.load("dchaplinsky/flair-uk-pos")
69
+
70
+ sentence = Sentence("Я люблю Україну. Моє імʼя Марія Шевченко, я навчаюся в Київській політехніці.")
71
+
72
+ tagger.predict(sentence)
73
+
74
+ print(sentence)
75
+ print('---')
76
+
77
+ print('The following POS tags are found:')
78
+
79
+ pos_items = []
80
+ for label in sentence.get_labels():
81
+ all_labels = []
82
+ keys = label.data_point.annotation_layers.keys()
83
+
84
+ for key in keys:
85
+ all_labels.extend(
86
+ [
87
+ {'label': label.value, 'score': round(label.score, 4)}
88
+ for label in label.data_point.get_labels(key)
89
+ if label.data_point == label
90
+ ]
91
+ )
92
+
93
+ pos_items.append({
94
+ 'text': label.data_point.text,
95
+ 'all_labels': all_labels,
96
+ })
97
+
98
+ pprint(pos_items)
99
+
100
+ # Result:
101
+ """
102
+ Sentence: "Я люблю Україну . Моє імʼя Марія Шевченко , я навчаюся в Київській політехніці ." → ["Я"/PRON, "люблю"/VERB, "Україну"/PROPN, "."/PUNCT, "Моє"/DET, "імʼя"/NOUN, "Марія"/PROPN, "Шевченко"/PROPN, ","/PUNCT, "я"/PRON, "навчаюся"/VERB, "в"/ADP, "Київській"/ADJ, "політехніці"/NOUN, "."/PUNCT]
103
+ ---
104
+ The following POS tags are found:
105
+ [{'all_labels': [{'label': 'PRON', 'score': 1.0}], 'text': 'Я'},
106
+ {'all_labels': [{'label': 'VERB', 'score': 1.0}], 'text': 'люблю'},
107
+ {'all_labels': [{'label': 'PROPN', 'score': 1.0}], 'text': 'Україну'},
108
+ {'all_labels': [{'label': 'PUNCT', 'score': 1.0}], 'text': '.'},
109
+ {'all_labels': [{'label': 'DET', 'score': 0.9999}], 'text': 'Моє'},
110
+ {'all_labels': [{'label': 'NOUN', 'score': 1.0}], 'text': 'імʼя'},
111
+ {'all_labels': [{'label': 'PROPN', 'score': 1.0}], 'text': 'Марія'},
112
+ {'all_labels': [{'label': 'PROPN', 'score': 1.0}], 'text': 'Шевченко'},
113
+ {'all_labels': [{'label': 'PUNCT', 'score': 1.0}], 'text': ','},
114
+ {'all_labels': [{'label': 'PRON', 'score': 1.0}], 'text': 'я'},
115
+ {'all_labels': [{'label': 'VERB', 'score': 1.0}], 'text': 'навчаюся'},
116
+ {'all_labels': [{'label': 'ADP', 'score': 1.0}], 'text': 'в'},
117
+ {'all_labels': [{'label': 'ADJ', 'score': 1.0}], 'text': 'Київській'},
118
+ {'all_labels': [{'label': 'NOUN', 'score': 1.0}], 'text': 'політехніці'},
119
+ {'all_labels': [{'label': 'PUNCT', 'score': 1.0}], 'text': '.'}]
120
+ """
121
+ ```
122
 
123
  Copyright: [Dmytro Chaplynskyi](https://twitter.com/dchaplinsky), [lang-uk project](https://lang.org.ua), 2022