mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +03:00
Prune number of non-projective labels more aggressiely
This commit is contained in:
parent
73bca3d382
commit
6e552c9d83
|
@ -213,7 +213,7 @@ class GoldCorpus(object):
|
||||||
train_tuples = self.train_tuples
|
train_tuples = self.train_tuples
|
||||||
if projectivize:
|
if projectivize:
|
||||||
train_tuples = nonproj.preprocess_training_data(
|
train_tuples = nonproj.preprocess_training_data(
|
||||||
self.train_tuples)
|
self.train_tuples, label_freq_cutoff=100)
|
||||||
random.shuffle(train_tuples)
|
random.shuffle(train_tuples)
|
||||||
gold_docs = self.iter_gold_docs(nlp, train_tuples, gold_preproc,
|
gold_docs = self.iter_gold_docs(nlp, train_tuples, gold_preproc,
|
||||||
max_length=max_length,
|
max_length=max_length,
|
||||||
|
|
|
@ -809,7 +809,7 @@ cdef class Parser:
|
||||||
def begin_training(self, gold_tuples, pipeline=None, **cfg):
|
def begin_training(self, gold_tuples, pipeline=None, **cfg):
|
||||||
if 'model' in cfg:
|
if 'model' in cfg:
|
||||||
self.model = cfg['model']
|
self.model = cfg['model']
|
||||||
gold_tuples = nonproj.preprocess_training_data(gold_tuples)
|
gold_tuples = nonproj.preprocess_training_data(gold_tuples, label_freq_cutoff=100)
|
||||||
actions = self.moves.get_actions(gold_parses=gold_tuples)
|
actions = self.moves.get_actions(gold_parses=gold_tuples)
|
||||||
for action, labels in actions.items():
|
for action, labels in actions.items():
|
||||||
for label in labels:
|
for label in labels:
|
||||||
|
|
Loading…
Reference in New Issue
Block a user