spaCy - Span.similarity Method

This method is used to make a semantic similarity estimate. The default is cosine similarity using an average of word vectors.

Argument

The table below explains its argument −

Example

An example of Span.similarity method is as follows −

import spacy
nlp_model = spacy.load("en_core_web_sm")
doc = nlp_model("red car and black bike")
red_car = doc[:2]
black_bike = doc[3:]
car_bike = red_car.similarity(black_bike)
bike_car = black_bike.similarity(red_car)
car_bike == bike_car

Output

When you run the code, you will see the following output −

True