Confusion with intent-entity-featurizer-regex

As per intent-entity-featurizer-regex documentation, regex helps with intent classification.

During training, the regex intent featurizer creates a list of regular expressions defined in the training data format. For each regex, a feature will be set marking whether this expression was found in the input, which will later be fed into intent classifier / entity extractor to simplify classification (assuming the classifier has learned during the training phase, that this set feature indicates a certain intent).

Though, when training, we only provide entity name . For example, in data.md,

    ## regex:location
    - [0-9]{5}

   ## lookup:skill
     ./Input/lookup/skills.txt

Which means, for given regex, we are specifying only entity name. It’s clear that with this, entity extraction accuracy should increase but

Question is: how does intent-entity-featurizer-regex helps with intent classification?

2 Likes

hey @kapilkathuria I also met the same problem, have you solved it? How does intent-entity-featurizer-regex helps with intent classification?

Nope, i didn’t get more information on this.