Индексы объектов инструмента аннотации Spacy
String a = new String("foo");
String b = new String("foo");
System.out.println(a == b); // prints false
System.out.println(a.equals(b)); // prints true
Убедитесь, что вы понимаете, почему. Это потому, что сравнение == сравнивает только ссылки; equals() метод сопоставляет содержимое по символу.
Когда вы вызываете new для a и b, каждый получает новую ссылку, указывающую на "foo" в таблице строк. Ссылки разные, но контент один и тот же.
1 ответ
Обучение Json: - [{
"text": "This Labor-Contract ('CONTRACT'), effective as of May 12, 2017 (“Effective Date”), is made by and between Client-ABC, Inc. ('Client-ABC'), having its principal place of business at 1030 Client-ABC Street, Atlanta, GA 30318, USA and Supplier-ABC (“Supplier”), having a place of business at 100 Park Avenue, Miami, 10178, USA (hereinafter referred to individually as “Party” and collectively as “Parties”).",
"entities": [
[
50,
62,
"EFFECTIVE_DATE"
],
[
106,
116,
"VENDOR_NAME"
],
[
181,
203,
"VENDOR_ADDRESS"
],
[
205,
212,
"VENDOR_CITY"
],
[
214,
216,
"VENDOR_STATE"
],
[
217,
222,
"VENDOR_POSTAL_CODE"
],
[
224,
227,
"VENDOR_COUNTRY"
]
]
},{second training data}]
Код для обучения на заказ: -
training_pickel_file = "training_pickel_file.json"
with open(training_pickel_file) as input:
TRAIN_DATA = json.load(input)
for annotations in TRAIN_DATA:
for ent in annotations["entities"]:
ner.add_label(ent[2])
other_pipes = [pipe for pipe in nlp.pipe_names if pipe != 'ner']
with nlp.disable_pipes(*other_pipes): # only train NER
optimizer = nlp.begin_training()
for itn in range(n_iter):
random.shuffle(TRAIN_DATA)
losses = {}
for a in TRAIN_DATA:
doc = nlp.make_doc(a["text"])
gold = GoldParse(doc, entities = a["entities"])
nlp.update([doc], [gold], drop =0.5, sgd=optimizer, losses = losses)
print('Losses', losses)