英语动词在Flair中的消歧（默认模型）

这是随 Flair 一起出现的英语标准动词消歧模型。

F1-Score: 89.34（Ontonotes）- 预测 Proposition Bank verb frames 。

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/frame-english")

# make example sentence
sentence = Sentence("George returned to Berlin to return his hat.")

# predict NER tags
tagger.predict(sentence)

# print sentence
print(sentence)

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

这将产生以下输出：

Span [2]: "returned"   [− Labels: return.01 (0.9951)]
Span [6]: "return"   [− Labels: return.02 (0.6361)]

因此，句子"George returned to Berlin to return his hat"中的单词"returned"被标记为return.01（即返回某个地方），而"return"被标记为return.02（即归还某物）。

训练：用于训练此模型的脚本

使用以下Flair脚本进行训练此模型：

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 = ColumnCorpus(
    "resources/tasks/srl", column_format={1: "text", 11: "frame"}
)

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

# 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 = [

    BytePairEmbeddings("en"),

    FlairEmbeddings("news-forward"),

    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/frame-english',
              train_with_dev=True,
              max_epochs=150)

引用

在使用此模型时，请引用以下论文。

@inproceedings{akbik2019flair,
  title={FLAIR: An easy-to-use framework for state-of-the-art NLP},
  author={Akbik, Alan and Bergmann, Tanja and Blythe, Duncan and Rasul, Kashif and Schweter, Stefan and Vollgraf, Roland},
  booktitle={{NAACL} 2019, 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations)},
  pages={54--59},
  year={2019}
}

问题？

Flair问题跟踪器可在 here 处获得。