Is there a way to add list of entity valus to train for it's variation (no lookup)?

Rasa Open Source
1

I have an entity, which is a kind of ID, but the ID has many formats, almost 40 formats found manually (no one standard format). I know I can provide Lookup Tables, but the list is huge (4M values) so lookup won’t be a good idea. Is it possible to provide a list of samples for each format for an entity so that Rasa can get an idea of various formats?

For now, we are trying to add examples for each format in NLU, but the example sentence stays the same except the entity is changing. Example:

- intent: information_id
  examples: |
  - [550-1536B](product_id)
  - [127.61077CR](product_id)
  - [VWP51A](product_id)

Am I doing it right, or is there a better way of doing it?

Thank you, Abhishek

2

Hi @ashek1520, take a look at Regular Expressions for Entity Extraction.

3

Thank you, are you suggesting to include multiple regular expression for that entity as:

nlu:
- regex: product_id
  examples: |
    - reg_exp_1
    - reg_exp_2

I think this might work, will try.

4

Adding regular impressions improved the confidence level… Thanks.