# Detecting entity from a intent not describing it

**URL:** <https://forum.rasa.com/t/detecting-entity-from-a-intent-not-describing-it/32915>\
**Category:** Rasa Open Source\
**Created:** [August 24, 2020, 8:39am UTC](https://forum.rasa.com/t/detecting-entity-from-a-intent-not-describing-it/32915 "2020-08-24T08:39:34Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![aniruddha96](https://avatars.discourse-cdn.com/v4/letter/a/ecccb3/32.png) [@aniruddha96](https://forum.rasa.com/u/aniruddha96)\
**Post date:** [August 24, 2020, 8:39am UTC](https://forum.rasa.com/t/detecting-entity-from-a-intent-not-describing-it/32915/1 "2020-08-24T08:39:34Z")

</div>

Domain slots: VALUE\_MIN: type : float VALUE\_MAX: type : float

nlu

## intent: start

- start
- go

## intent: value\_min

- min value is 0-9
- minimum value is 0-9

## intent: value\_max

- max value is 0-9
- maximum value is 0-9

stories

## flow\_1

- start
  - utter\_ask\_VALUE\_MIN

- value\_min{“VALUE\_MIN”:“120”}
  - slot{“VALUE\_MIN”:“120”}
  - utter\_ask\_VALUE\_MAX

- value\_max{“VALUE\_MAX”:“2000”}
  - slot{“VALUE\_MAX”:“2000”}

Your input -\> go 2020-08-24 13:53:51 DEBUG rasa.core.tracker\_store - Recreating tracker for id ‘8ed2a94d33a24c959c42a04acd54cc5c’ 2020-08-24 13:53:51 DEBUG rasa.nlu.classifiers.diet\_classifier - There is no trained model for ‘ResponseSelector’: The component is either not trained or didn’t receive enough training data. 2020-08-24 13:53:51 DEBUG rasa.nlu.selectors.response\_selector - Adding following selector key to message property: default 2020-08-24 13:53:51 DEBUG rasa.core.processor - Received user message ‘go’ with intent ‘{‘name’: ‘start’, ‘confidence’: 0.7473200559616089}’ and entities ‘[]’ 2020-08-24 13:53:51 DEBUG rasa.core.processor - Logged UserUtterance - tracker now has 27 events. 2020-08-24 13:53:51 DEBUG rasa.core.policies.memoization - Current tracker state [None, None, None, {}, {‘intent\_start’: 1.0, ‘prev\_action\_listen’: 1.0}] 2020-08-24 13:53:51 DEBUG rasa.core.policies.memoization - There is a memorised next action ‘utter\_ask\_VALUE\_MIN’ 2020-08-24 13:53:51 DEBUG rasa.core.policies.ensemble - Predicted next action using policy\_0\_MemoizationPolicy 2020-08-24 13:53:51 DEBUG rasa.core.processor - Predicted next action ‘utter\_ask\_VALUE\_MIN’ with confidence 1.00. 2020-08-24 13:53:51 DEBUG rasa.core.processor - Action ‘utter\_ask\_VALUE\_MIN’ ended with events ‘[BotUttered(‘what is the min value’, {“elements”: null, “quick\_replies”: null, “buttons”: null, “attachment”: null, “image”: null, “custom”: null}, {}, 1598257431.730513)]’. 2020-08-24 13:53:51 DEBUG rasa.core.policies.memoization - Current tracker state [None, None, {}, {‘intent\_start’: 1.0, ‘prev\_action\_listen’: 1.0}, {‘intent\_start’: 1.0, ‘prev\_utter\_ask\_VALUE\_MIN’: 1.0}] 2020-08-24 13:53:51 DEBUG rasa.core.policies.memoization - There is a memorised next action ‘action\_listen’ 2020-08-24 13:53:51 DEBUG rasa.core.policies.mapping\_policy - There is no mapped action for the predicted intent, ‘start’. 2020-08-24 13:53:51 DEBUG rasa.core.policies.ensemble - Predicted next action using policy\_0\_MemoizationPolicy 2020-08-24 13:53:51 DEBUG rasa.core.processor - Predicted next action ‘action\_listen’ with confidence 1.00. 2020-08-24 13:53:51 DEBUG rasa.core.processor - Action ‘action\_listen’ ended with events ‘[]’. 2020-08-24 13:53:51 DEBUG rasa.core.lock\_store - Deleted lock for conversation ‘8ed2a94d33a24c959c42a04acd54cc5c’. what is the min value Your input -\> min values is 400 2020-08-24 13:53:59 DEBUG rasa.core.tracker\_store - Recreating tracker for id ‘8ed2a94d33a24c959c42a04acd54cc5c’ 2020-08-24 13:53:59 DEBUG rasa.nlu.classifiers.diet\_classifier - There is no trained model for ‘ResponseSelector’: The component is either not trained or didn’t receive enough training data. 2020-08-24 13:53:59 DEBUG rasa.nlu.selectors.response\_selector - Adding following selector key to message property: default 2020-08-24 13:53:59 DEBUG rasa.core.processor - Received user message ‘min values is 400’ with intent ‘{‘name’: ‘value\_min’, ‘confidence’: 0.7056987881660461}’ and entities ‘[{‘entity’: ‘VALUE\_MIN’, ‘start’: 14, ‘end’: 17, ‘value’: ‘400’, ‘extractor’: ‘DIETClassifier’}]’ 2020-08-24 13:53:59 DEBUG rasa.core.processor - Current slot values: VALUE\_MAX: None VALUE\_MIN: 400 2020-08-24 13:53:59 DEBUG rasa.core.processor - Logged UserUtterance - tracker now has 32 events. 2020-08-24 13:54:00 DEBUG rasa.core.policies.memoization - Current tracker state [None, {}, {‘intent\_start’: 1.0, ‘prev\_action\_listen’: 1.0}, {‘intent\_start’: 1.0, ‘prev\_utter\_ask\_VALUE\_MIN’: 1.0}, {‘prev\_action\_listen’: 1.0, ‘slot\_VALUE\_MIN\_0’: 1.0, ‘intent\_value\_min’: 1.0}] 2020-08-24 13:54:00 DEBUG rasa.core.policies.memoization - There is a memorised next action ‘utter\_ask\_VALUE\_MAX’ 2020-08-24 13:54:00 DEBUG rasa.core.policies.ensemble - Predicted next action using policy\_0\_MemoizationPolicy 2020-08-24 13:54:00 DEBUG rasa.core.processor - Predicted next action ‘utter\_ask\_VALUE\_MAX’ with confidence 1.00. 2020-08-24 13:54:00 DEBUG rasa.core.processor - Action ‘utter\_ask\_VALUE\_MAX’ ended with events ‘[BotUttered(‘what is the max value’, {“elements”: null, “quick\_replies”: null, “buttons”: null, “attachment”: null, “image”: null, “custom”: null}, {}, 1598257440.0605109)]’. 2020-08-24 13:54:00 DEBUG rasa.core.policies.memoization - Current tracker state [{}, {‘intent\_start’: 1.0, ‘prev\_action\_listen’: 1.0}, {‘intent\_start’: 1.0, ‘prev\_utter\_ask\_VALUE\_MIN’: 1.0}, {‘prev\_action\_listen’: 1.0, ‘slot\_VALUE\_MIN\_0’: 1.0, ‘intent\_value\_min’: 1.0}, {‘slot\_VALUE\_MIN\_0’: 1.0, ‘intent\_value\_min’: 1.0, ‘prev\_utter\_ask\_VALUE\_MAX’: 1.0}] 2020-08-24 13:54:00 DEBUG rasa.core.policies.memoization - There is a memorised next action ‘action\_listen’ 2020-08-24 13:54:00 DEBUG rasa.core.policies.mapping\_policy - There is no mapped action for the predicted intent, ‘value\_min’. 2020-08-24 13:54:00 DEBUG rasa.core.policies.ensemble - Predicted next action using policy\_0\_MemoizationPolicy 2020-08-24 13:54:00 DEBUG rasa.core.processor - Predicted next action ‘action\_listen’ with confidence 1.00. 2020-08-24 13:54:00 DEBUG rasa.core.processor - Action ‘action\_listen’ ended with events ‘[]’. 2020-08-24 13:54:00 DEBUG rasa.core.lock\_store - Deleted lock for conversation ‘8ed2a94d33a24c959c42a04acd54cc5c’. what is the max value Your input -\> max value is 90000 2020-08-24 13:54:16 DEBUG rasa.core.tracker\_store - Recreating tracker for id ‘8ed2a94d33a24c959c42a04acd54cc5c’ 2020-08-24 13:54:16 DEBUG rasa.nlu.classifiers.diet\_classifier - There is no trained model for ‘ResponseSelector’: The component is either not trained or didn’t receive enough training data. 2020-08-24 13:54:16 DEBUG rasa.nlu.selectors.response\_selector - Adding following selector key to message property: default 2020-08-24 13:54:16 DEBUG rasa.core.processor - Received user message ‘max value is 90000’ with intent ‘{‘name’: ‘value\_max’, ‘confidence’: 0.8313025236129761}’ and entities ‘[{‘entity’: ‘VALUE\_MIN’, ‘start’: 13, ‘end’: 18, ‘value’: ‘90000’, ‘extractor’: ‘DIETClassifier’}]’ 2020-08-24 13:54:16 DEBUG rasa.core.processor - Current slot values: VALUE\_MAX: None VALUE\_MIN: 90000 2020-08-24 13:54:16 DEBUG rasa.core.processor - Logged UserUtterance - tracker now has 37 events. 2020-08-24 13:54:16 DEBUG rasa.core.policies.memoization - Current tracker state [{‘intent\_start’: 1.0, ‘prev\_action\_listen’: 1.0}, {‘intent\_start’: 1.0, ‘prev\_utter\_ask\_VALUE\_MIN’: 1.0}, {‘prev\_action\_listen’: 1.0, ‘slot\_VALUE\_MIN\_0’: 1.0, ‘intent\_value\_min’: 1.0}, {‘slot\_VALUE\_MIN\_0’: 1.0, ‘intent\_value\_min’: 1.0, ‘prev\_utter\_ask\_VALUE\_MAX’: 1.0}, {‘intent\_value\_max’: 1.0, ‘prev\_action\_listen’: 1.0, ‘slot\_VALUE\_MIN\_0’: 1.0}] 2020-08-24 13:54:16 DEBUG rasa.core.policies.memoization - There is no memorised next action 2020-08-24 13:54:16 DEBUG rasa.core.policies.ensemble - Predicted next action using policy\_1\_TEDPolicy 2020-08-24 13:54:16 DEBUG rasa.core.processor - Predicted next action ‘action\_listen’ with confidence 0.92. 2020-08-24 13:54:16 DEBUG rasa.core.processor - Action ‘action\_listen’ ended with events ‘[]’. 2020-08-24 13:54:16 DEBUG rasa.core.lock\_store - Deleted lock for conversation ‘8ed2a94d33a24c959c42a04acd54cc5c’. Your input -\>

How come for the message ‘max value is 90000’ the intent is identified correct but the entity is not ? How to rectify this ?

---

<div class="post-metadata">

**Author:** ![rudi](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/rudi/32/21369_2.png) [@rudi](https://forum.rasa.com/u/rudi)\
**Post date:** [August 24, 2020, 11:44am UTC](https://forum.rasa.com/t/detecting-entity-from-a-intent-not-describing-it/32915/2 "2020-08-24T11:44:12Z")

</div>

The NLU section isn’t rendering properly. Could you place it inside a code block (the `</>` symbol), so we can see the entity training data?

---

<div class="post-metadata">

**Author:** ![aniruddha96](https://avatars.discourse-cdn.com/v4/letter/a/ecccb3/32.png) [@aniruddha96](https://forum.rasa.com/u/aniruddha96)\
**Post date:** [August 24, 2020, 12:13pm UTC](https://forum.rasa.com/t/detecting-entity-from-a-intent-not-describing-it/32915/3 "2020-08-24T12:13:16Z")

</div>

```
## intent: start
- start
- go

## intent: value_min
- min value is [0-9](VALUE_MIN)
- minimum value is [0-9](VALUE_MIN)

## intent: value_max
- max value is [0-9](VALUE_MAX)
- maximum value is [0-9](VALUE_MAX)
```

---

<div class="post-metadata">

**Author:** ![rudi](https://dub1.discourse-cdn.com/flex013/user_avatar/forum.rasa.com/rudi/32/21369_2.png) [@rudi](https://forum.rasa.com/u/rudi)\
**Post date:** [August 24, 2020, 1:04pm UTC](https://forum.rasa.com/t/detecting-entity-from-a-intent-not-describing-it/32915/4 "2020-08-24T13:04:33Z")

</div>

Hmm interesting, that looks correct to me.

I’m wondering if this is because `VALUE_MIN` and `VALUE_MAX` entities are too similar, so it doesn’t know which one to choose for the number extraction.

I see that there are roles that might help in this case: [Entity Extraction](https://rasa.com/docs/rasa/nlu/entity-extraction/#entities-roles-and-groups)

Or you could have a `number` entity for both, and use the stories to fill the correct slot depending on the classification.
