Identifying named entities in news headlines
News organizations often tag named entities like people, locations, and organizations in headlines to improve search, indexing, and recommendations. Your job is to use a Hugging Face pipeline to automatically detect and group these entities in a news headline.
This exercise is part of the course
Natural Language Processing (NLP) in Python
Exercise instructions
- Create a
ner_pipelineusing the"dslim/bert-base-NER"model. - Extract the named entities from the given
headline.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
from transformers import pipeline
# Create the NER pipeline
ner_pipeline = pipeline(
task="____",
model="____",
grouped_entities=True
)
headline = "Apple is planning to open a new office in San Francisco next year."
# Get named entities
entities = ____
for entity in entities:
print(f"{entity['entity_group']}: {entity['word']}")