# Rasa does not do well in identifying intents that are close to each other **URL:** \ **Category:** Rasa Open Source\ **Created:** [December 7, 2020, 9:57am UTC](https://forum.rasa.com/t/rasa-does-not-do-well-in-identifying-intents-that-are-close-to-each-other/37777 "2020-12-07T09:57:09Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![a\_vakily](https://avatars.discourse-cdn.com/v4/letter/a/3da27b/32.png) [@a\_vakily](https://forum.rasa.com/u/a_vakily)\ **Post date:** [December 7, 2020, 9:57am UTC](https://forum.rasa.com/t/rasa-does-not-do-well-in-identifying-intents-that-are-close-to-each-other/37777/1 "2020-12-07T09:57:09Z")
Hello I am working on a chatbot which is the Persian language. rasa does not do well in identifying intents that are close to each other. I defined between 5 and 10 examples for each intent in nlu file. Can you help? ---
**Author:** ![siriusraja](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/siriusraja/32/22306_2.png) [@siriusraja](https://forum.rasa.com/u/siriusraja)\ **Post date:** [December 9, 2020, 4:30pm UTC](https://forum.rasa.com/t/rasa-does-not-do-well-in-identifying-intents-that-are-close-to-each-other/37777/2 "2020-12-09T16:30:44Z")
Hi @a_vakily Please share couple of intents and its associated examples. Does the intents have different entities? ---
**Author:** ![Tobias\_Wochinger](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/tobias_wochinger/32/4580_2.png) [@Tobias\_Wochinger](https://forum.rasa.com/u/Tobias_Wochinger)\ **Post date:** [December 17, 2020, 9:46am UTC](https://forum.rasa.com/t/rasa-does-not-do-well-in-identifying-intents-that-are-close-to-each-other/37777/3 "2020-12-17T09:46:06Z")
5 - 10 examples are too less. I’d add more examples (at least \>20, ideally \> 100). Unfortunately there aren’t that many existing language models for Persian in contrast to “mainstream” language like English. 😬 If there are good language models available, then you can e.g. use spacy in your model to make use of the already trained language model. In your case you’re training a model from scratch which means that you need way more examples as if you could use an existing language models 😬 If you think that that examples for intents are indeed very similar, you could also try restructuring your intents and then distinguish based on extracted entities. ---
**Author:** ![victor\_sh](https://avatars.discourse-cdn.com/v4/letter/v/43a26b/32.png) [@victor\_sh](https://forum.rasa.com/u/victor_sh)\ **Post date:** [March 12, 2024, 7:30am UTC](https://forum.rasa.com/t/rasa-does-not-do-well-in-identifying-intents-that-are-close-to-each-other/37777/4 "2024-03-12T07:30:37Z")
Hello! How can I make my classifier distinguish between intents using entities? Or should I do this using custom actions?