如何在 spaCy 中正确更新模型?
How to properly update a model in spaCy?
我想用新实体更新模型。我正在加载 "pt" NER 模型,并尝试更新它。
在做任何事情之前,我尝试了这个短语:"meu nome é Mário e hoje eu vou para academia"。 (在英语中,这句话是“我叫马里奥,今天我要去健身房”)。
在整个过程之前,我得到了这个:
Entities [('Mário', 'PER')]
Tokens [('meu', '', 2), ('nome', '', 2), ('é', '', 2), ('Mário', 'PER', 3), ('e', '', 2), ('hoje', '', 2), ('eu', '', 2), ('vou', '', 2), ('pra', '', 2), ('academia', '', 2)]
好的,Mário 是一个名字而且是正确的。
但我希望模型将 "hoje (today)" 识别为日期,然后我 运行 下面的脚本。
在我 运行 脚本之后,我尝试了相同的设置并得到了这个:
Entities [('hoje', 'DATE')]
Tokens [('meu', '', 2), ('nome', '', 2), ('é', '', 2), ('Mário', '', 2), ('e', '', 2), ('hoje', 'DATE', 3), ('eu', '', 2), ('vou', '', 2), ('pra', '', 2), ('academia', '', 2)]
模型将 "hoje" 识别为日期,但完全忘记了马里奥作为人物。
from __future__ import unicode_literals, print_function
import plac
import random
from pathlib import Path
import spacy
from spacy.util import minibatch, compounding
# training data
TRAIN_DATA = [
("Infelizmente não, eu briguei com meus amigos hoje", {"entities": [(45, 49, "DATE")]}),
("hoje foi um bom dia.", {"entities": [(0, 4, "DATE")]}),
("ah não sei, hoje foi horrível", {"entities": [(12, 16, "DATE")]}),
("hoje eu briguei com o Mário", {"entities": [(0, 4, "DATE")]})
]
@plac.annotations(
model=("Model name. Defaults to blank 'en' model.", "option", "m", str),
output_dir=("Optional output directory", "option", "o", Path),
n_iter=("Number of training iterations", "option", "n", int),
)
def main(model="pt", output_dir="/model", n_iter=100):
"""Load the model, set up the pipeline and train the entity recognizer."""
if model is not None:
nlp = spacy.load(model) # load existing spaCy model
print("Loaded model '%s'" % model)
else:
nlp = spacy.blank("pt") # create blank Language class
print("Created blank 'en' model")
doc = nlp("meu nome é Mário e hoje eu vou pra academia")
print("Entities", [(ent.text, ent.label_) for ent in doc.ents])
print("Tokens", [(t.text, t.ent_type_, t.ent_iob) for t in doc])
# create the built-in pipeline components and add them to the pipeline
# nlp.create_pipe works for built-ins that are registered with spaCy
if "ner" not in nlp.pipe_names:
ner = nlp.create_pipe("ner")
nlp.add_pipe(ner, last=True)
# otherwise, get it so we can add labels
else:
ner = nlp.get_pipe("ner")
# add labels
for _, annotations in TRAIN_DATA:
for ent in annotations.get("entities"):
ner.add_label(ent[2])
# get names of other pipes to disable them during training
other_pipes = [pipe for pipe in nlp.pipe_names if pipe != "ner"]
with nlp.disable_pipes(*other_pipes): # only train NER
# reset and initialize the weights randomly – but only if we're
# training a new model
if model is None:
nlp.begin_training()
for itn in range(n_iter):
random.shuffle(TRAIN_DATA)
losses = {}
# batch up the examples using spaCy's minibatch
batches = minibatch(TRAIN_DATA, size=compounding(4.0, 32.0, 1.001))
for batch in batches:
texts, annotations = zip(*batch)
nlp.update(
texts, # batch of texts
annotations, # batch of annotations
drop=0.5, # dropout - make it harder to memorise data
losses=losses,
)
print("Losses", losses)
# test the trained model
# for text, _ in TRAIN_DATA:
doc = nlp("meu nome é Mário e hoje eu vou pra academia")
print("Entities", [(ent.text, ent.label_) for ent in doc.ents])
print("Tokens", [(t.text, t.ent_type_, t.ent_iob) for t in doc])
# save model to output directory
if output_dir is not None:
output_dir = Path(output_dir)
if not output_dir.exists():
output_dir.mkdir()
nlp.to_disk(output_dir)
print("Saved model to", output_dir)
# test the saved model
print("Loading from", output_dir)
nlp2 = spacy.load(output_dir)
# for text, _ in TRAIN_DATA:
# doc = nlp2(text)
# print("Entities", [(ent.text, ent.label_) for ent in doc.ents])
# print("Tokens", [(t.text, t.ent_type_, t.ent_iob) for t in doc])
在训练数据中你需要提到 "Mario" 作为 "PER"。如果你错过了它,模型将从新的训练数据中学习将 "Mario" 排除为 "PER"。
(注意:您应该在训练数据中提及句子中出现的所有实体,而不仅仅是新实体。)
我想用新实体更新模型。我正在加载 "pt" NER 模型,并尝试更新它。 在做任何事情之前,我尝试了这个短语:"meu nome é Mário e hoje eu vou para academia"。 (在英语中,这句话是“我叫马里奥,今天我要去健身房”)。 在整个过程之前,我得到了这个:
Entities [('Mário', 'PER')]
Tokens [('meu', '', 2), ('nome', '', 2), ('é', '', 2), ('Mário', 'PER', 3), ('e', '', 2), ('hoje', '', 2), ('eu', '', 2), ('vou', '', 2), ('pra', '', 2), ('academia', '', 2)]
好的,Mário 是一个名字而且是正确的。 但我希望模型将 "hoje (today)" 识别为日期,然后我 运行 下面的脚本。
在我 运行 脚本之后,我尝试了相同的设置并得到了这个:
Entities [('hoje', 'DATE')]
Tokens [('meu', '', 2), ('nome', '', 2), ('é', '', 2), ('Mário', '', 2), ('e', '', 2), ('hoje', 'DATE', 3), ('eu', '', 2), ('vou', '', 2), ('pra', '', 2), ('academia', '', 2)]
模型将 "hoje" 识别为日期,但完全忘记了马里奥作为人物。
from __future__ import unicode_literals, print_function
import plac
import random
from pathlib import Path
import spacy
from spacy.util import minibatch, compounding
# training data
TRAIN_DATA = [
("Infelizmente não, eu briguei com meus amigos hoje", {"entities": [(45, 49, "DATE")]}),
("hoje foi um bom dia.", {"entities": [(0, 4, "DATE")]}),
("ah não sei, hoje foi horrível", {"entities": [(12, 16, "DATE")]}),
("hoje eu briguei com o Mário", {"entities": [(0, 4, "DATE")]})
]
@plac.annotations(
model=("Model name. Defaults to blank 'en' model.", "option", "m", str),
output_dir=("Optional output directory", "option", "o", Path),
n_iter=("Number of training iterations", "option", "n", int),
)
def main(model="pt", output_dir="/model", n_iter=100):
"""Load the model, set up the pipeline and train the entity recognizer."""
if model is not None:
nlp = spacy.load(model) # load existing spaCy model
print("Loaded model '%s'" % model)
else:
nlp = spacy.blank("pt") # create blank Language class
print("Created blank 'en' model")
doc = nlp("meu nome é Mário e hoje eu vou pra academia")
print("Entities", [(ent.text, ent.label_) for ent in doc.ents])
print("Tokens", [(t.text, t.ent_type_, t.ent_iob) for t in doc])
# create the built-in pipeline components and add them to the pipeline
# nlp.create_pipe works for built-ins that are registered with spaCy
if "ner" not in nlp.pipe_names:
ner = nlp.create_pipe("ner")
nlp.add_pipe(ner, last=True)
# otherwise, get it so we can add labels
else:
ner = nlp.get_pipe("ner")
# add labels
for _, annotations in TRAIN_DATA:
for ent in annotations.get("entities"):
ner.add_label(ent[2])
# get names of other pipes to disable them during training
other_pipes = [pipe for pipe in nlp.pipe_names if pipe != "ner"]
with nlp.disable_pipes(*other_pipes): # only train NER
# reset and initialize the weights randomly – but only if we're
# training a new model
if model is None:
nlp.begin_training()
for itn in range(n_iter):
random.shuffle(TRAIN_DATA)
losses = {}
# batch up the examples using spaCy's minibatch
batches = minibatch(TRAIN_DATA, size=compounding(4.0, 32.0, 1.001))
for batch in batches:
texts, annotations = zip(*batch)
nlp.update(
texts, # batch of texts
annotations, # batch of annotations
drop=0.5, # dropout - make it harder to memorise data
losses=losses,
)
print("Losses", losses)
# test the trained model
# for text, _ in TRAIN_DATA:
doc = nlp("meu nome é Mário e hoje eu vou pra academia")
print("Entities", [(ent.text, ent.label_) for ent in doc.ents])
print("Tokens", [(t.text, t.ent_type_, t.ent_iob) for t in doc])
# save model to output directory
if output_dir is not None:
output_dir = Path(output_dir)
if not output_dir.exists():
output_dir.mkdir()
nlp.to_disk(output_dir)
print("Saved model to", output_dir)
# test the saved model
print("Loading from", output_dir)
nlp2 = spacy.load(output_dir)
# for text, _ in TRAIN_DATA:
# doc = nlp2(text)
# print("Entities", [(ent.text, ent.label_) for ent in doc.ents])
# print("Tokens", [(t.text, t.ent_type_, t.ent_iob) for t in doc])
在训练数据中你需要提到 "Mario" 作为 "PER"。如果你错过了它,模型将从新的训练数据中学习将 "Mario" 排除为 "PER"。
(注意:您应该在训练数据中提及句子中出现的所有实体,而不仅仅是新实体。)