def main(args):
args = parser.parse_args()
# 0. Make a list of word embeddings
if args.method == 'glove':
word_embeddings = [WordEmbeddings('glove')]
elif args.method == 'flair':
word_embeddings = [
WordEmbeddings('glove'),
FlairEmbeddings('news-forward'),
FlairEmbeddings('news-backward')
]
elif args.method == 'cui_svd':
word_embeddings = [
BackOffEmbeddings(
WordEmbeddings('glove'),
WordEmbeddings('resources/embeddings/cui2vec100.npy'))
]
elif args.method == 'cui_proj':
word_embeddings = [
BackOffEmbeddings(
WordEmbeddings('glove'),
WordEmbeddings(
'resources/embeddings/cui2vec_projected_100-100.gensim'))
]
elif args.method == 'mimic':
word_embeddings = [
WordEmbeddings(
'resources/embeddings/mimic3_mixed_embeddings100.gensim')
]
elif args.method == 'cui2vec':
word_embeddings = [
BackOffEmbeddings(
WordEmbeddings('glove'),
WordEmbeddings(
'resources/embeddings/cui2vec_combined_glove_100dim.gensim'
))
]
elif args.method == 'mimic_lm':
word_embeddings = [
WordEmbeddings('glove'),
FlairEmbeddings('resources/taggers/mimic-forward/best-lm.pt'),
FlairEmbeddings('resources/taggers/mimic-backward/best-lm.pt')
]
else:
raise Exception(
"Received option for method %s that cannot be interpreted." %
(args.method))
if 'bg' in args.data_file:
multi = True
print(
"Running in multiple label setting because 'bg' was in the data file name %s"
% (args.data_file))
else:
multi = False
# 1. get the corpus
sents: List[Sentence] = NLPTaskDataFetcher.read_text_classification_file(
args.data_file)
corpus = TaggedCorpus(sents, None, None)
# 2. create the label dictionary
label_dict = corpus.make_label_dictionary()
# 3. split the training data into folds
num_folds = args.num_folds
seed = 719
kf = KFold(n_splits=num_folds, random_state=seed)
kf.get_n_splits()
# 4. iterate over folds:
total_acc = 0
fold = 1
for train_index, test_index in kf.split(corpus.train):
# 4a. initialize the text classifier trainer
split_traindev = np.array(corpus.train)[train_index].tolist()
traindev_size = len(split_traindev)
train_dev_splitpoint = int(0.9 * traindev_size)
split_train = split_traindev[:train_dev_splitpoint]
split_dev = split_traindev[train_dev_splitpoint:]
split_test = np.array(corpus.train)[test_index].tolist()
split_corpus = TaggedCorpus(split_train,
dev=split_dev,
test=split_test)
print("After split, size of splits: train=%d, dev=%d, test=%d" %
(len(split_train), len(split_dev), len(split_test)))
# 4b. do training:
with tempfile.TemporaryDirectory() as model_dir:
# init document embedding by passing list of word embeddings
document_embeddings: DocumentLSTMEmbeddings = DocumentLSTMEmbeddings(
word_embeddings,
hidden_size=128,
reproject_words=True,
reproject_words_dimension=64,
)
classifier = TextClassifier(document_embeddings,
label_dictionary=label_dict,
multi_label=multi)
trainer = ModelTrainer(classifier, split_corpus)
results = trainer.train(model_dir,
embeddings_in_memory=False,
learning_rate=0.1,
mini_batch_size=128,
anneal_factor=0.5,
patience=5,
max_epochs=100)
fold_acc = results['test_score']
total_acc += fold_acc
print(f"Finished fold {fold} with accuracy {fold_acc}")
fold += 1
total_acc /= num_folds
print("Finished with total cross-fold accuracy of %f" % (total_acc))
from typing import List
from flair.data import Sentence, TaggedCorpus
from flair.data_fetcher import NLPTaskDataFetcher, NLPTask
from flair.embeddings import WordEmbeddings, CharLMEmbeddings, DocumentLSTMEmbeddings
from flair.models.text_classification_model import TextClassifier
from flair.trainers.text_classification_trainer import TextClassifierTrainer
sentences_train: List[Sentence] = NLPTaskDataFetcher.read_text_classification_file('training.preprocessed.txt')
sentences_dev: List[Sentence] = NLPTaskDataFetcher.read_text_classification_file('dev.preprocessed.txt')
sentences_test: List[Sentence] = NLPTaskDataFetcher.read_text_classification_file('test.preprocessed.txt')
corpus = TaggedCorpus(sentences_train, sentences_dev, sentences_test)
# 2. create the label dictionary
label_dict = corpus.make_label_dictionary()
# 3. make a list of word embeddings
word_embeddings = [WordEmbeddings('de-fasttext'),
CharLMEmbeddings('german-forward'),
CharLMEmbeddings('german-backward')]
# 4. init document embedding by passing list of word embeddings
document_embeddings: DocumentLSTMEmbeddings = DocumentLSTMEmbeddings(word_embeddings, hidden_states=32)
# 5. create the text classifier
classifier = TextClassifier(document_embeddings, label_dictionary=label_dict, multi_label=False)
# 6. initialize the text classifier trainer
trainer = TextClassifierTrainer(classifier, corpus, label_dict)
