def fit(self, dataset, epochs=10, dev=None):
"""
Trains a BIST model on an annotated dataset in CoNLL file format.
Args:
dataset (str): Path to input dataset for training, formatted in CoNLL/U format.
epochs (int, optional): Number of learning iterations.
dev (str, optional): Path to development dataset for conducting evaluations.
"""
if dev:
dev = validate_existing_filepath(dev)
dataset = validate_existing_filepath(dataset)
validate((epochs, int, 0, None))
print("\nRunning fit on " + dataset + "...\n")
words, w2i, pos, rels = utils.vocab(dataset)
self.params = words, w2i, pos, rels, self.options
from nlp_architect.models.bist.mstlstm import MSTParserLSTM
self.model = MSTParserLSTM(*self.params)
for epoch in range(epochs):
print("Starting epoch", epoch + 1)
self.model.train(dataset)
if dev:
ext = dev.rindex(".")
res_path = dev[:ext] + "_epoch_" + str(epoch +
1) + "_pred" + dev[ext:]
utils.write_conll(res_path, self.model.predict(dev))
utils.run_eval(dev, res_path)
def fit(self, dataset, epochs=10, dev=None):
"""
Trains a BIST model on an annotated dataset in CoNLL file format.
Args:
dataset (str): Path to input dataset for training, formatted in CoNLL/U format.
epochs (int, optional): Number of learning iterations.
dev (str, optional): Path to development dataset for conducting evaluations.
"""
if dev:
dev = validate_existing_filepath(dev)
dataset = validate_existing_filepath(dataset)
validate((epochs, int, 0, None))
print('\nRunning fit on ' + dataset + '...\n')
words, w2i, pos, rels = utils.vocab(dataset)
self.params = words, w2i, pos, rels, self.options
self.model = MSTParserLSTM(*self.params)
for epoch in range(epochs):
print('Starting epoch', epoch + 1)
self.model.train(dataset)
if dev:
ext = dev.rindex('.')
res_path = dev[:ext] + '_epoch_' + str(epoch + 1) + '_pred' + dev[ext:]
utils.write_conll(res_path, self.model.predict(dev))
utils.run_eval(dev, res_path)
def predict(self, dataset, evaluate=False):
"""
Runs inference with the BIST model on a dataset in CoNLL file format.
Args:
dataset (str): Path to input CoNLL file.
evaluate (bool, optional): Write prediction and evaluation files to dataset's folder.
Returns:
res (list of list of ConllEntry): The list of input sentences with predicted
dependencies attached.
"""
dataset = validate_existing_filepath(dataset)
validate((evaluate, bool))
print("\nRunning predict on " + dataset + "...\n")
res = list(self.model.predict(conll_path=dataset))
if evaluate:
ext = dataset.rindex(".")
pred_path = dataset[:ext] + "_pred" + dataset[ext:]
utils.write_conll(pred_path, res)
utils.run_eval(dataset, pred_path)
return res
def predict(self, dataset, evaluate=False):
"""
Runs inference with the BIST model on a dataset in CoNLL file format.
Args:
dataset (str): Path to input CoNLL file.
evaluate (bool, optional): Write prediction and evaluation files to dataset's folder.
Returns:
res (list of list of ConllEntry): The list of input sentences with predicted
dependencies attached.
"""
dataset = validate_existing_filepath(dataset)
validate((evaluate, bool))
print('\nRunning predict on ' + dataset + '...\n')
res = list(self.model.predict(conll_path=dataset))
if evaluate:
ext = dataset.rindex('.')
pred_path = dataset[:ext] + '_pred' + dataset[ext:]
utils.write_conll(pred_path, res)
utils.run_eval(dataset, pred_path)
return res