Flair中的英语分块（快速模型）

这是随Flair一起提供的用于英语的快速短语分块模型。

F1得分：96.22（CoNLL-2000）

预测4个标签：

基于 Flair embeddings 和LSTM-CRF。

演示：如何在Flair中使用

需要 Flair （pip install flair）

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

# load tagger
tagger = SequenceTagger.load("flair/chunk-english-fast")

# make example sentence
sentence = Sentence("The happy man has been eating at the diner")

# 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('np'):
    print(entity)

这将产生以下输出：

Span [1,2,3]: "The happy man"   [− Labels: NP (0.9958)]
Span [4,5,6]: "has been eating"   [− Labels: VP (0.8759)]
Span [7]: "at"   [− Labels: PP (1.0)]
Span [8,9]: "the diner"   [− Labels: NP (0.9991)]

因此，在句子"The happy man has been eating at the diner"中，"The happy man"和"the diner"被标记为名词短语（NP），"has been eating"被标记为动词短语（VP）。

训练：训练此模型的脚本

使用以下Flair脚本来训练此模型：

from flair.data import Corpus
from flair.datasets import CONLL_2000
from flair.embeddings import WordEmbeddings, StackedEmbeddings, FlairEmbeddings

# 1. get the corpus
corpus: Corpus = CONLL_2000()

# 2. what tag do we want to predict?
tag_type = 'np'

# 3. make the tag dictionary from the corpus
tag_dictionary = corpus.make_tag_dictionary(tag_type=tag_type)

# 4. initialize each embedding we use
embedding_types = [

    # contextual string embeddings, forward
    FlairEmbeddings('news-forward-fast'),

    # contextual string embeddings, backward
    FlairEmbeddings('news-backward-fast'),
]

# embedding stack consists of Flair and GloVe embeddings
embeddings = StackedEmbeddings(embeddings=embedding_types)

# 5. initialize sequence tagger
from flair.models import SequenceTagger

tagger = SequenceTagger(hidden_size=256,
                        embeddings=embeddings,
                        tag_dictionary=tag_dictionary,
                        tag_type=tag_type)

# 6. initialize trainer
from flair.trainers import ModelTrainer

trainer = ModelTrainer(tagger, corpus)

# 7. run training
trainer.train('resources/taggers/chunk-english-fast',
              train_with_dev=True,
              max_epochs=150)

引用

在使用此模型时，请引用以下论文。

@inproceedings{akbik2018coling,
  title={Contextual String Embeddings for Sequence Labeling},
  author={Akbik, Alan and Blythe, Duncan and Vollgraf, Roland},
  booktitle = {{COLING} 2018, 27th International Conference on Computational Linguistics},
  pages     = {1638--1649},
  year      = {2018}
}

问题？

Flair的问题跟踪器在此处 here 。