Hello guys,
I am using these for my nlu.md file
- my name is [omkar](name)
- i am know as [omkar](name)
- you can call me [omkar](name)
this will accept name omkar when I put “my name is omkar” with same logic how can I get any name instead of omkar that are not trained in the
here is my action form handling the business logic: form_action.py (3.5 KB)
@MuraliChandran14, @mohan, @mloubser if you could answer
You need to vary the example name:
## intent: name
- my name is [omkar](name)
- i'm [john](name)
- i am known as [peter](name)
- you can call me [al](name)
... more examples ...
otherwise the NLU will assume that omkar is a constant.
You don’t have to add every single possible name, but try with around 10 different ones.
I hope you have utter_ask_name and utter_ask_email in your model so that the user knows what’s being requested.
Hope this helped.
that helped, thank you very much 
To add another option - use Spacy’s pretrained PERSON entity, either on it’s own or in conjunction with your own trained name entities. This will help pick up many more names than you include in your NLU data.
yes, you are right, if I am not wrong it happens because the Spacy library is already trained with many names.
but the library is developed with american and british names, whereas my use case i mainly for Indian names. extracting those names spacy doesnt help properly.
btw i have a new use case to train an individual end to end NER model specifically extracting Indian names, for training purpose i have 15k Indian names but dont know how i should train on them in order to extract the Indian names from any sentence.
please help me if you know about it
Gotcha, that makes sense! You can take a look at spacy’s documentation for training your own models here: https://spacy.io/usage/training If you do that, please post and let us know how it goes!
Sure thanks