On the iOS version of our app we are using the Apple Word Tagger Model so that it can assist us with parsing some complex sentences and that way we can extract the parts that we actually want. It is working fairly well.
What is the Android equivalent of this? Basically I would feed it a large sample of sentences and a classification for every word in the sentence and once it learns those I can pass it some new sentences and it'll tell me the classification of each of the words.
Ideally after training it, everything should run on the phone, not the cloud.
Edit: I figured I should give an example of what I want since I already played with the Bert Classifier and it isn't what I need as far as I can tell.
This isn't exactly what I need to parse but a somewhat similar type of data. I would feed training data like this:
362, house number main st, street name 345-954-5555, phone number central av, street name W., direction E., direction John Smith, person name East, direction 10th st, street name and so on.
Then I would pass to the classifier a string like "Joe Doe 999 S. 2nd st, Maimi, FL, 741-555-5555"
And the classifier will tell me "person name, person name, house number, direction, street name, city, state, phone number".
We are doing something similar with the Apple Word Tagger and while not perfect, it is working really well. Is there something like that for Android that doesn't run on the cloud?