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?