# Difference between sparse features

**URL:** <https://forum.rasa.com/t/difference-between-sparse-features/33943>\
**Category:** Rasa Open Source\
**Created:** [September 19, 2020, 12:35pm UTC](https://forum.rasa.com/t/difference-between-sparse-features/33943 "2020-09-19T12:35:45Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Ghada](https://avatars.discourse-cdn.com/v4/letter/g/ac91a4/32.png) [@Ghada](https://forum.rasa.com/u/Ghada)\
**Post date:** [September 19, 2020, 12:35pm UTC](https://forum.rasa.com/t/difference-between-sparse-features/33943/1 "2020-09-19T12:35:45Z")

</div>

Hello,

I’m using: `EmbeddingIntentClassifier ` for **Intent Classification**.

According to RASA’s documentation, `EmbeddingIntentClassifier` requires `dense_features` and/or `sparse_features`.

In my NLU pipeline, I have `CountVectorsFeaturizer` and `RegexFeaturizer` and they both creates `sparse_features`.

I want to know which one of these two components’ output: `CountVectorsFeaturizer` and `RegexFeaturizer` is used as an input for `EmbeddingIntentClassifier`?

What’s the role of each `sparse_features`?

Thank you,

---

<div class="post-metadata">

**Author:** ![Ghada](https://avatars.discourse-cdn.com/v4/letter/g/ac91a4/32.png) [@Ghada](https://forum.rasa.com/u/Ghada)\
**Post date:** [September 19, 2020, 5:09pm UTC](https://forum.rasa.com/t/difference-between-sparse-features/33943/2 "2020-09-19T17:09:02Z")

</div>

`CountVectorsFeaturizer` is the component used for `EmbeddingIntentClassifier`.

Explanation here:

[![](https://img.youtube.com/vi/ET1k9OrsfYQ/hqdefault.jpg "(Ep #4 - Rasa Masterclass) Training the NLU models: understanding pipeline components | Rasa 1.8.0") ](https://www.youtube.com/watch?v=ET1k9OrsfYQ)
