我正在尝试使用 spacy 3 添加自定义 NER 标签。我找到了旧版本的教程并对 spacy 3 进行了调整。这是我正在使用的整个代码：
import random
import spacy
from spacy.training import Example
LABEL = 'ANIMAL'
TRAIN_DATA = [
("Horses are too tall and they pretend to care about your feelings", {'entities': [(0, 6, LABEL)]}),
("Do they bite?", {'entities': []}),
("horses are too tall and they pretend to care about your feelings", {'entities': [(0, 6, LABEL)]}),
("horses pretend to care about your feelings", {'entities': [(0, 6, LABEL)]}),
("they pretend to care about your feelings, those horses", {'entities': [(48, 54, LABEL)]}),
("horses?", {'entities': [(0, 6, LABEL)]})
]
nlp = spacy.load('en_core_web_sm') # load existing spaCy model
ner = nlp.get_pipe('ner')
ner.add_label(LABEL)
print(ner.move_names) # Here I see, that the new label was added
optimizer = nlp.create_optimizer()
# 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
for itn in range(20):
random.shuffle(TRAIN_DATA)
losses = {}
for text, annotations in TRAIN_DATA:
doc = nlp(text)
example = Example.from_dict(doc, annotations)
nlp.update([example], drop=0.35, sgd=optimizer, losses=losses)
print(losses)
# test the trained model # add some dummy sentences with many NERs
test_text = 'Do you like horses?'
doc = nlp(test_text)
print("Entities in '%s'" % test_text)
for ent in doc.ents:
print(ent.label_, " -- ", ent.text)
此代码输出 ValueError 异常，但仅在 2 次迭代后 - 请注意前 2 行：
{'ner': 9.862242701536594}
{'ner': 8.169456698315201}
Traceback (most recent call last):
File ".\custom_ner_training.py", line 46, in <module>
nlp.update([example], drop=0.35, sgd=optimizer, losses=losses)
File "C:\ogr\moje\python\spacy_pg\myvenv\lib\site-packages\spacy\language.py", line 1106, in update
proc.update(examples, sgd=None, losses=losses, **component_cfg[name])
File "spacy\pipeline\transition_parser.pyx", line 366, in spacy.pipeline.transition_parser.Parser.update
File "spacy\pipeline\transition_parser.pyx", line 478, in spacy.pipeline.transition_parser.Parser.get_batch_loss
File "spacy\pipeline\_parser_internals\ner.pyx", line 310, in spacy.pipeline._parser_internals.ner.BiluoPushDown.set_costs
ValueError
我看到ANIMAL标签是通过调用添加的ner.move_names。
当我更改值LABEL = 'PERSON时，代码会成功运行并将马识别为PERSON新数据。这就是我假设代码本身没有错误的原因。
有什么我想念的吗？我究竟做错了什么？请问有人可以复制吗？
注意：这是我在这里的第一个问题。我希望我提供了所有信息。如果没有，请在评论中告诉我。