Frame English Fast

🚀 English Verb Disambiguation in Flair (fast model)

This is a fast verb disambiguation model for English that comes with Flair, which can effectively predict Proposition Bank verb frames.

This is the fast verb disambiguation model for English that ships with Flair.

F1-Score: 88,27 (Ontonotes) - predicts Proposition Bank verb frames.

Based on Flair embeddings and LSTM-CRF.

🚀 Quick Start

Prerequisites

Requires: Flair (pip install flair)

Usage Example

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

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

# 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)

This yields the following output:

Span [2]: "returned"   [− Labels: return.01 (0.9867)]
Span [6]: "return"   [− Labels: return.02 (0.4741)]

So, the word "returned" is labeled as return.01 (as in go back somewhere) while "return" is labeled as return.02 (as in give back something) in the sentence "George returned to Berlin to return his hat".

📦 Installation

To use this model, you need to install the Flair library. You can install it via the following command:

pip install flair

💻 Usage Examples

Basic Usage

The above code example demonstrates the basic usage of this model. You can load the model and perform verb disambiguation on a given sentence.

🔧 Technical Details

The following Flair script was used to train this model:

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-fast"),

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

📄 License

Please cite the following paper when using this model.

@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}
}

❓ Issues

The Flair issue tracker is available here.