Created
March 4, 2024 08:26
-
-
Save tsh-code/680efb3ae87272ff5b2500f1d7c6e0cf to your computer and use it in GitHub Desktop.
spacy spanmarker example
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import spacy | |
nlp = spacy.load("en_core_web_trf") | |
nlp.add_pipe("span_marker", config={"model": "lxyuan/span-marker-bert-base-multilingual-cased-multinerd"}) | |
def extract_people(text: str): | |
entities = nlp(text) | |
full_names = set() | |
for entity in entities.ents: | |
if entity.label_ in ['PER', 'PERSON']: | |
# Check if the entity has both a first name and a last name | |
if len(entity.text.split()) >= 2: | |
full_names.add(entity.text) | |
return list(full_names) | |
content = ‘text goes here' | |
entities = extract_people(content) | |
print(entities) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment