flair/pos-english

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

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

# make example sentence
sentence = Sentence("I love Berlin.")

# 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('pos'):
    print(entity)

Span [1]: "I"   [− Labels: PRP (1.0)]
Span [2]: "love"   [− Labels: VBP (1.0)]
Span [3]: "Berlin"   [− Labels: NNP (0.9999)]
Span [4]: "."   [− Labels: . (1.0)]

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

# 1. load the corpus (Ontonotes does not ship with Flair, you need to download and reformat into a column format yourself)
corpus: Corpus = ColumnCorpus(
                "resources/tasks/onto-ner",
                column_format={0: "text", 1: "pos", 2: "upos", 3: "ner"},
                tag_to_bioes="ner",
            )

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

# 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'),

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

# 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/pos-english',
              train_with_dev=True,
              max_epochs=150)

@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}
}