0

I am wanting to create my own custom Named Entity Recognition using spaCy. Whilst I understand the principles of the process and that I need 50-100 examples to train the model.

What I am struggling to understand is if the number of examples needs to be just be done for each new entity or exponentially for each value the new entity could be?

For example say I had the phrase "The LA Rams play football at SoFi stadium" Do I need 50-100 versions of this statement to give named entities to the football team and their stadium?

Or do I need to do 50-100 sentences for all NFL teams and their stadiums individually? i.e. "The Arizonal Cardinals play ball at State Farm stadium", "The 49ers play their home games at Levi's stadium"

In American football this is made harder due to sponsorship and these name actually being organizations, but in UK football this is not so common with Wrexham Football Club playing at the Racecourse stadium.

Thank you

Improve this question
Related questions
4387
Iterating over dictionaries using 'for' loops
1952
Proper way to declare custom exceptions in modern Python?
2485
Calling a function of a module by using its name (a string)
Load 4 more related questions Show fewer related questions

0

Reset to default

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.