import json
from spacy.lang.zh import Chinese
with open("exercises/zh/countries.json", encoding="utf8") as f:
COUNTRIES = json.loads(f.read())
nlp = Chinese()
doc = nlp("智利可能会从斯洛伐克进口货物")
# 导入PhraseMatcher并实例化
from spacy.____ import ____
matcher = ____(____)
# 创建Doc实例的模板然后加入matcher中
# 下面的代码比这样的表达方式更快： [nlp(country) for country in COUNTRIES]
patterns = list(nlp.pipe(COUNTRIES))
matcher.add("COUNTRY", None, *patterns)
# 在测试文档中调用matcher并打印结果
matches = ____(____)
print([doc[start:end] for match_id, start, end in matches])
from spacy.lang.es import Spanish nlp = Spanish() # Importa las clases Doc y Span from spacy.____ import ____, ____ words = ["Me", "gusta", "David", "Bowie"] spaces = [True, True, True, False] # Crea un doc a partir de las palabras y los espacios doc = ____(____, ____, ____) print(doc.text) # Crea un span para "David Bowie" a partir del doc y asígnalo al label "PERSON" span = ____(____, ____, ____, label=____) print(span.text, span.label_) # Añade el span a las entidades del doc ____.____ = [____] # Imprime en pantalla el texto y los labels de las entidades print([(ent.text, ent.label_) for ent in doc.ents])
import spacy
# Importe le Matcher
from spacy.____ import ____
nlp = spacy.load("en_core_web_sm")
doc = nlp("Upcoming iPhone X release date leaked as Apple reveals pre-orders")
# Initialise le matcher avec le vocabulaire partagé
matcher = ____(____.____)
# Crée un motif qui recherche les deux tokens : "iPhone" et "X"
pattern = [____]
# Ajoute le motif au matcher
____.____("IPHONE_X_PATTERN", None, ____)
# Utilise le matcher sur le doc
matches = ____
print("Résultats :", [doc[start:end].text for match_id, start, end in matches])
