# Making rasa nlu to identify similar entities based on trained entities

**URL:** <https://forum.rasa.com/t/making-rasa-nlu-to-identify-similar-entities-based-on-trained-entities/829>\
**Category:** Rasa Open Source\
**Created:** [September 4, 2018, 5:39am UTC](https://forum.rasa.com/t/making-rasa-nlu-to-identify-similar-entities-based-on-trained-entities/829 "2018-09-04T05:39:12Z")\
**Posts on this page:** 1\
**Showing post:** 12

<div class="post-metadata">

**Author:** ![akshay2000](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/akshay2000/32/415_2.png) [@akshay2000](https://forum.rasa.com/u/akshay2000)\
**Post date:** [May 17, 2019, 10:35am UTC](https://forum.rasa.com/t/making-rasa-nlu-to-identify-similar-entities-based-on-trained-entities/829/12 "2019-05-17T10:35:26Z")

</div>

I recently started using lookup tables. However, I suddenly start getting ill defined f scores from sklearn intent classifier if my lookup table is large. What could be the reason? I have opened a discussion over [here](http://forum.rasa.com/t/adding-larger-lookup-table-causes-ill-defined-f-scores/9501).

---

_[View the full topic](https://forum.rasa.com/t/making-rasa-nlu-to-identify-similar-entities-based-on-trained-entities/829)._