CODEWITHSUNDEEP
c#machine-learningml.net
derekantrican
derekantrican

Reputation: 2283

Machine Learning to recognize important words in a sentence

I want to use machine learning to extract rock-climbing related names/locations from a sentence. I've already "classified" a bunch of data like this:

Bouldering in Central Park!!||Central Park
Not the best angle but check out that latch!!! Golden Bowl (V7) in Squamish||Golden Bowl||Squamish  
Does anyone have a used crash pad for sale?||

(where I have a sentence followed by || then all the names/locations (separated again by ||)

I'm looking at using ML.NET for this since I'm most familiar with C#, but can't seem to find out how to get started. I think the Iris classification example is probably the closest to my situation? But I'm not sure

Any suggestions for what classification model to use in ML.NET? Or a different language/framework to use?

Upvotes: 1

Views: 1043

Answers (1)

Batuhan B
Batuhan B

Reputation: 1855

You can easily try some pre-trained NER algorithms like Stanford's or Spacy. Probably, they will not become sufficient for you so at that step you need to determine your entity types and make some labeling to train your own NER algorithm.

You can start to check out Stanford NER and Spacy NER module.

Edit: You can change classifier type to take different results.

Example result on Stanford Online Demo Tool:

enter image description here

Upvotes: 2

Related Questions