如何创建Flair Huggingface输出数据

Question

我对拥抱面很陌生，我正在研究Flair (NER)模块，它给了我下面的输出：

from flair.data import Sentence
from flair.models import SequenceTagger

# load tagger
tagger = SequenceTagger.load("flair/ner-german-large")

# make example sentence
sentence = Sentence("George Washington ging nach Washington")

# predict NER tags
tagger.predict(sentence)

# print sentence
print(sentence)

# print predicted NER spans
print('The following NER tags are found:')
# iterate over entities and print
for entity in sentence.get_spans('ner'):
    print(entity)

输出

Span [1,2]: "George Washington"   [− Labels: PER (1.0)]
Span [5]: "Washington"   [− Labels: LOC (1.0)]

如何将此输出转换为dataframe，可能的列为“Token”(NER)和“Token_Type”(“ORG”或“PER”)。

生成的sentence类型为data.sentence。

Answer 1

代码中的entity部分是flair.data.Span类型，有很多属性可以使用(您可以在https://github.com/flairNLP/flair/blob/master/flair/data.py上看到Span类的源代码)。

import pandas as pd

entities = []

for entity in sentence.get_spans('ner'):
    entities.append({
        'text': entity.text,
        'type': entity.tag,
        'score': entity.score
    })

print(pd.DataFrame(entities))

>>>
                text type     score
0  George Washington  PER  0.999997
1         Washington  LOC  0.999996