# Automation for Synonym training? **URL:** \ **Category:** Rasa Open Source\ **Created:** [October 4, 2019, 11:14am UTC](https://forum.rasa.com/t/automation-for-synonym-training/18396 "2019-10-04T11:14:19Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![Marek](https://avatars.discourse-cdn.com/v4/letter/m/b2d939/32.png) [@Marek](https://forum.rasa.com/u/Marek)\ **Post date:** [October 4, 2019, 11:14am UTC](https://forum.rasa.com/t/automation-for-synonym-training/18396/1 "2019-10-04T11:14:20Z")
Hi, any idea/code how to automate entity synonym training in RASA NLU? By default, you have to make for every synonym separate training sentence. Would not be great to automate this? When polishing NLU performance, you would just add more synonyms to existing entities… Thanks for sharing ---
**Author:** ![Gehova](https://avatars.discourse-cdn.com/v4/letter/g/2acd7d/32.png) [@Gehova](https://forum.rasa.com/u/Gehova)\ **Post date:** [October 4, 2019, 1:23pm UTC](https://forum.rasa.com/t/automation-for-synonym-training/18396/2 "2019-10-04T13:23:36Z")
Use a [lookup table](https://blog.rasa.com/improving-entity-extraction/). ---
**Author:** ![Marek](https://avatars.discourse-cdn.com/v4/letter/m/b2d939/32.png) [@Marek](https://forum.rasa.com/u/Marek)\ **Post date:** [October 8, 2019, 6:17pm UTC](https://forum.rasa.com/t/automation-for-synonym-training/18396/3 "2019-10-08T18:17:57Z")
Thanks! Lookup tables are great for better entity extraction. But do not solve standardization of entity value. For languages with complex morphology (e.g. CZ/PL/SK) it is often necessary to put entity into standard form (nominativ). ---
**Author:** ![nikitamrky](https://avatars.discourse-cdn.com/v4/letter/n/4bbf92/32.png) [@nikitamrky](https://forum.rasa.com/u/nikitamrky)\ **Post date:** [August 13, 2022, 4:58pm UTC](https://forum.rasa.com/t/automation-for-synonym-training/18396/4 "2022-08-13T16:58:39Z")
I have the same question, hi from 2022. Still no solution?