如何使用SpaCy和NLTK进行自定义NER标记？

Question

import spacy
import random
from spacy.gold import GoldParse
from spacy.language import EntityRecognizer

train_data = [
    ('Who is Chaka Khan?', [(7, 17, 'PERSON')]),
    ('I like London and Berlin.', [(7, 13, 'LOC'), (18, 24, 'LOC')])
]

nlp = spacy.load('en_depent_web_md', entity=False)
ner = EntityRecognizer(nlp.vocab, entity_types=['PERSON', 'LOC'])

for itn in range(1000):
    random.shuffle(train_data)
    for raw_text, entity_offsets in train_data:
        doc = nlp.make_doc(raw_text)
        gold = GoldParse(doc, entities=entity_offsets)

        nlp.tagger(doc)
        ner.update(doc, gold)
ner.model.end_training()

doc = nlp.make_doc('I like London and Berlin.')
nlp.tagger(doc)
print(ner(doc))

上面的代码无法正常使用自定义标记。我正在努力标记自定义标签名称，如NOL - ORG，GDRFA - ORG，DHONI - Cricket。

其他信息 - https://support.prodi.gy/t/custom-ner-tag-for-english/704

其他信息 - https://spacy.io/usage/training#section-ner

寻找示例代码或示例/解释

Answer 1

def main(model=None, output_dir=r'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("en")  # create blank Language class
        print("Created blank 'en' model")

    # 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(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])

    # 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)

然后，加载相同的模型：

print("Loading from", output_dir)
nlp2 = spacy.load(output_dir)
doc = nlp2("<your any text>")
print("Entities", [(ent.text, ent.label_) for ent in doc.ents])

和，

TRAIN_DATA = [
    ("my site brand is ttt.", {"entities": [(17, 20, "PERSON")]}),
]